WO2022068228A1 - Lesion mark verification method and apparatus, and computer device and storage medium - Google Patents

Abstract

A lesion mark verification method and apparatus, and a computer device and a storage medium. The method comprises: receiving medical image data, in which lesion marks have been added, from a user terminal, and obtaining two lesion marks of any image in the medical image data as mark information to be verified (S110); determining whether type information of the two lesion marks in said mark information is the same (S120); if the type information of the two lesion marks is the same, determining whether marking curves in the two lesion marks are closed curves, so as to obtain curve type determination results (S130); if the marking curves in the two lesion marks both are non-closed curves, determining, according to a preset curve determination rule, whether the two marking curves are similar, so as to obtain a result of verifying whether said mark information is consistent, the curve determination rule being a determination rule based on a dynamic time warping algorithm (S140); if the marking curves in the two lesion marks both are closed curves, determining, according to a preset overlap ratio determination rule, whether closed areas corresponding to the two marking curves overlap, so as to obtain a result of verifying whether said mark information is consistent (S150); and if the marking curves in the two lesion marks are respectively a closed curve and a non-closed curve, determining, according to a preset proportion threshold, whether pixels corresponding to the two marking curves overlap, so as to obtain a result of verifying whether said mark information is consistent (S160). The present method is based on an intelligent decision-making technology, relates to the field of artificial intelligence, can verify the consistency of the lesion marks by using a unified standard, and can greatly improve the verification efficiency and quality of the lesion marks.

Description

Translated fromChinese

病灶标注的验证方法、装置、计算机设备及存储介质Verification method, device, computer equipment and storage medium for lesion labeling

本申请要求于2020年09月29日提交中国专利局、申请号为202011053234.4，发明名称为“病灶标注的验证方法、装置、计算机设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of the Chinese patent application filed with the China Patent Office on September 29, 2020, the application number is 202011053234.4, and the invention name is "verification method, device, computer equipment and storage medium for lesion marking", the entire content of which has passed Reference is incorporated in this application.

技术领域technical field

本申请涉及智能决策技术领域，属于智慧城市中病灶标注的验证的应用场景，尤其涉及一种病灶标注的验证方法、装置、计算机设备及存储介质。The present application relates to the technical field of intelligent decision-making, belongs to the application scenario of verification of lesion labeling in smart cities, and in particular relates to a verification method, device, computer equipment and storage medium for lesion labeling.

背景技术Background technique

随着医疗技术的进步和发展，伴随互联网的普及，远程诊断作为一种新型的诊断方式越来越多地得到应用，远程诊断通常会将检测设备采集到的医疗影像资料发送至多位医生，每位医生均对同一套医疗影像资料添加病灶标注，之后通过人工检验的方式对每位医生所添加的病灶标注是否一致进行检验，然而发明人发现人工检验因受主观判断的影响，难以保持统一的检验标准，且人工检验需耗费大量人力资源，不利于提高检验效率，导致对病灶标注进行一致性检验的效率及质量受到影响。因此，现有的技术方法中对医疗影像资料所添加的病灶标注进行一致性检验时，存在检验的效率及质量不高的问题。With the advancement and development of medical technology and the popularization of the Internet, remote diagnosis has been increasingly used as a new type of diagnosis method. Remote diagnosis usually sends the medical image data collected by the detection equipment to multiple doctors. Each doctor added lesion labels to the same set of medical imaging data, and then checked whether the lesion labels added by each doctor were consistent through manual inspection. However, the inventor found that manual inspection was affected by subjective judgment, and it was difficult to maintain a unified Inspection standards are required, and manual inspection requires a lot of human resources, which is not conducive to improving inspection efficiency, and affects the efficiency and quality of consistent inspection of lesion labeling. Therefore, in the prior art method, when the consistency test is performed on the lesion annotation added to the medical image data, there are problems of low test efficiency and quality.

发明内容SUMMARY OF THE INVENTION

本申请实施例提供了一种病灶标注的验证方法、装置、计算机设备及存储介质，旨在解决技术方法中对医疗影像资料所添加的病灶标注进行一致性检验时所存在的检验效率及质量不高的问题。The embodiments of the present application provide a verification method, device, computer equipment, and storage medium for lesion labeling, which aim to solve the inconsistency in inspection efficiency and quality when performing consistency inspection on lesion labeling added to medical image data in the technical method. high question.

第一方面，本申请实施例提供了一种病灶标注的验证方法，其包括：In a first aspect, the embodiments of the present application provide a verification method for lesion labeling, which includes:

接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息；Receive the medical image data to which the lesion label has been added from the user terminal, and obtain two lesion labels of any image in the medical image data as the label information to be verified;

判断所述待验证标注信息中的两个所述病灶标注的类型信息是否相同；Determine whether the type information of the two lesion annotations in the to-be-verified annotation information is the same;

若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果；If the type information of the two lesion annotations is the same, determine whether the marked curves in the two lesion annotations are closed curves to obtain a curve type determination result;

若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则；If the marked curves in the two lesion markings are both non-closed curves, according to the preset curve judgment rule, it is judged whether the two marked curves are similar to obtain the verification result of whether the marked information to be verified is consistent, and the curve The judgment rule is a judgment rule based on the dynamic time warping algorithm;

若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果；If the marked curves in the two lesion markings are closed curves, determine whether the closed areas corresponding to the two marked curves overlap according to the preset coincidence degree judgment rule, so as to obtain the verification of whether the marked information to be verified is consistent result;

若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结果。If the annotation curves in the two lesion annotations are closed curves and non-closed curves respectively, it is determined whether the pixels corresponding to the two annotation curves overlap according to the preset proportion threshold, so as to obtain whether the annotation information to be verified is consistent verification result.

第二方面，本申请实施例提供了一种病灶标注的验证装置，其包括：In a second aspect, an embodiment of the present application provides a verification device for lesion labeling, which includes:

待验证标注信息获取单元，用于接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息；A to-be-verified annotation information acquisition unit, configured to receive the medical image data to which the lesion annotation has been added from the user terminal, and to acquire two lesion annotations of any image in the medical image data as the to-be-verified annotation information;

类型信息判断单元，用于判断所述待验证标注信息中的两个所述病灶标注的类型信息是 否相同；Type information judging unit, used for judging whether the type information marked by two described lesions in the marked information to be verified is the same;

曲线类型判断单元，用于若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果；a curve type determination unit, configured to determine whether the marked curve in the two lesion annotations is a closed curve if the type information of the two lesion annotations is the same, so as to obtain a curve type determination result;

第一验证单元，用于若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则；A first verification unit, configured to determine whether the two marked curves are similar according to a preset curve judgment rule if the marked curves in the two lesion markings are both non-closed curves, so as to obtain whether the marked information to be verified is consistent The verification result, the curve judgment rule is a judgment rule based on the dynamic time warping algorithm;

第二验证单元，用于若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果；The second verification unit is configured to, if the marked curves in the two lesion markings are closed curves, determine whether the closed areas corresponding to the two marked curves overlap according to a preset coincidence degree judgment rule, so as to obtain the Verify that the annotation information is consistent with the verification result;

第三验证单元，用于若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结果。The third verification unit is configured to determine whether the pixels corresponding to the two annotation curves overlap according to the preset proportion threshold if the annotation curves in the two lesion annotations are closed curves and non-closed curves respectively, so as to obtain the obtained Describe the verification result of whether the annotation information to be verified is consistent.

第三方面，本申请实施例又提供了一种计算机设备，其包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述第一方面所述的病灶标注的验证方法。In a third aspect, an embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer During the program, the verification method for lesion labeling described in the first aspect above is implemented.

第四方面，本申请实施例还提供了一种计算机可读存储介质，其中所述计算机可读存储介质存储有计算机程序，所述计算机程序当被处理器执行时使所述处理器执行上述第一方面所述的病灶标注的验证方法。In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when executed by a processor, the computer program causes the processor to execute the above-mentioned first step. In one aspect, the method for verifying lesion annotation is described.

本申请实施例提供了一种病灶标注的验证方法、装置、计算机设备及存储介质。获取医疗影像资料中任意一张图像的两个病灶标注作为待验证标注信息，判断两个病灶标注的类型信息是否相同；若相同，则判断两个病灶标注中的标注曲线是否为非闭合曲线；若两个标注曲线均为非闭合曲线，根据基于动态时间规整算法的曲线判断规则判断两个标注曲线是否相似得到是否一致的验证结果；若两个标注曲线均为闭合曲线，根据重合度判断规则判断两个标注曲线的闭合区域是否重合得到是否一致的验证结果；若两个标注曲线分别为闭合曲线及非闭合曲线，根据占比阈值判断两个标注曲线对应的像素是否重叠得到是否一致的验证结果。通过上述方法，可采用统一标准对病灶标注的一致性进行验证，可大幅提高对病灶标注进行验证的效率及质量。The embodiments of the present application provide a verification method, device, computer equipment and storage medium for lesion labeling. Obtain the two lesion annotations of any image in the medical imaging data as the annotation information to be verified, and determine whether the type information of the two lesion annotations is the same; if they are the same, determine whether the annotation curves in the two lesion annotations are non-closed curves; If the two marked curves are both non-closed curves, judge whether the two marked curves are similar according to the curve judgment rule based on the dynamic time warping algorithm to obtain a consistent verification result; if the two marked curves are both closed curves, according to the coincidence judgment rule Determine whether the closed areas of the two annotation curves overlap to obtain the consistent verification result; if the two annotation curves are closed curves and non-closed curves, respectively, determine whether the pixels corresponding to the two annotation curves overlap to obtain the consistency verification according to the proportion threshold. result. Through the above method, a unified standard can be used to verify the consistency of lesion annotation, which can greatly improve the efficiency and quality of lesion annotation verification.

附图说明Description of drawings

为了更清楚地说明本申请实施例技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to explain the technical solutions of the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. For those of ordinary skill, other drawings can also be obtained from these drawings without any creative effort.

图1为本申请实施例提供的病灶标注的验证方法的流程示意图；1 is a schematic flowchart of a verification method for lesion labeling provided by an embodiment of the present application;

图2为本申请实施例提供的病灶标注的验证方法的应用场景示意图；FIG. 2 is a schematic diagram of an application scenario of the verification method for lesion labeling provided by the embodiment of the present application;

图3为本申请实施例提供的病灶标注的验证方法的另一流程示意图；FIG. 3 is another schematic flowchart of the verification method for lesion labeling provided by the embodiment of the present application;

图4为本申请实施例提供的病灶标注的验证方法的子流程示意图；FIG. 4 is a schematic sub-flow diagram of the verification method for lesion labeling provided by the embodiment of the present application;

图5为本申请实施例提供的病灶标注的验证方法的另一子流程示意图；5 is a schematic diagram of another sub-flow of the verification method for lesion labeling provided by the embodiment of the present application;

图6为本申请实施例提供的病灶标注的验证方法的另一子流程示意图；6 is a schematic diagram of another sub-flow of the verification method for lesion labeling provided by the embodiment of the present application;

图7为本申请实施例提供的病灶标注的验证方法的另一子流程示意图；FIG. 7 is a schematic diagram of another sub-flow of the verification method for lesion labeling provided by the embodiment of the present application;

图8为本申请实施例提供的病灶标注的验证方法的另一子流程示意图；8 is a schematic diagram of another sub-flow of the verification method for lesion labeling provided by the embodiment of the present application;

图9为本申请实施例提供的病灶标注的验证装置的示意性框图；FIG. 9 is a schematic block diagram of a verification device for lesion labeling provided by an embodiment of the present application;

图10为本申请实施例提供的计算机设备的示意性框图。FIG. 10 is a schematic block diagram of a computer device provided by an embodiment of the present application.

具体实施方式Detailed ways

下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

应当理解，当在本说明书和所附权利要求书中使用时，术语“包括”和“包含”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。It is to be understood that, when used in this specification and the appended claims, the terms "comprising" and "comprising" indicate the presence of the described features, integers, steps, operations, elements and/or components, but do not exclude one or The presence or addition of a number of other features, integers, steps, operations, elements, components, and/or sets thereof.

还应当理解，在此本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。It should also be understood that the terminology used in the specification of the application herein is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural unless the context clearly dictates otherwise.

还应当进一步理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。It should also be further understood that, as used in this specification and the appended claims, the term "and/or" refers to and including any and all possible combinations of one or more of the associated listed items .

请参阅图1及图2，图1是本申请实施例提供的病灶标注的验证方法的流程示意图，图2为本申请实施例提供的病灶标注的验证方法的应用场景示意图；该病灶标注的验证方法应用于管理服务器10中，该方法通过安装于管理服务器10中的应用软件进行执行，多台用户终端20通过与管理服务器10建立网络连接以实现数据信息的传输，管理服务器10即是用于对同一图像的两个病灶标注是否一致进行验证的服务器端，用户终端20即是供用户对来自管理服务器的医疗影像资料添加病灶标注的终端设备，例如台式电脑、笔记本电脑、平板电脑或手机等，用户可以是医师。如图1所示，该方法包括步骤S110～S160。Please refer to FIG. 1 and FIG. 2 , FIG. 1 is a schematic flowchart of the verification method for lesion labeling provided by the embodiment of the present application, and FIG. 2 is a schematic diagram of an application scenario of the verification method for lesion labeling provided by the embodiment of the present application; The method is applied to themanagement server 10, the method is executed by the application software installed in themanagement server 10, andmultiple user terminals 20 establish network connections with themanagement server 10 to realize the transmission of data information, and themanagement server 10 is used for The server side that verifies whether the two lesion labels of the same image are consistent, and theuser terminal 20 is a terminal device for users to add lesion labels to the medical image data from the management server, such as a desktop computer, a laptop computer, a tablet computer or a mobile phone, etc. , the user can be a physician. As shown in FIG. 1, the method includes steps S110-S160.

S110、接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息。S110. Receive the medical image data to which the lesion label has been added from the user terminal, and acquire two lesion labels of any image in the medical image data as label information to be verified.

接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息。医疗影像资料为检测设备所采集得到的图像信息，医疗影像资料中包含至少一张图像，诊断过程中用户接收医疗影像资料，并在医疗影像资料所包含的每一图像中依次添加病灶标注得到已添加病灶标注的医疗影像资料，其中，用户可以是进行诊断的医生，医疗影像资料中的每一图像均添加有多个病灶标注。具体的，可依次获取医疗影像资料中所包含的任意一张图像的两个病灶标注作为待验证标注信息，对待验证标注信息进行一致性检验也即是检验待验证标注信息中所包含的两个病灶标注是否一致。Receive the medical image data to which the lesion annotation has been added from the user terminal, and acquire two lesion annotations of any image in the medical image data as the annotation information to be verified. The medical image data is the image information collected by the detection equipment. The medical image data contains at least one image. During the diagnosis process, the user receives the medical image data, and sequentially adds the lesion label to each image included in the medical image data to obtain the medical image data. The medical image data with lesion annotation is added, wherein the user can be a doctor who makes a diagnosis, and each image in the medical image data is added with a plurality of lesion annotations. Specifically, the two lesion annotations of any image included in the medical image data can be sequentially obtained as the annotation information to be verified, and the consistency check of the annotation information to be verified is to check the two lesions included in the annotation information to be verified. Whether the lesion labeling is consistent.

具体的，病灶标注可以包括类型信息及标注曲线，类型信息即是在图像中所添加的具体病灶类型的信息，可从预置的多个病灶类型中选择一个作为对应的类型信息并添加至该图像中，例如，类型信息可以是积水、感染、出血等，标注曲线即是在图像中所添加的对病灶区域进行标注的信息，标注曲线可以为闭合曲线或非闭合曲线，标注曲线可以是圆形、椭圆形、多边形或折线等任意形状，例如，闭合曲线可用于对块状的病灶区域进行标注，非闭合曲线可用于对线状或长条状的病灶区域进行标注。Specifically, the lesion labeling may include type information and labeling curve. The type information is the information of the specific lesion type added to the image. One can be selected from a plurality of preset lesion types as the corresponding type information and added to the image. In the image, for example, the type information can be stagnant water, infection, hemorrhage, etc. The labeling curve is the information added to the image to label the lesion area. The labeling curve can be a closed curve or a non-closed curve, and the labeling curve can be Any shape such as circle, ellipse, polygon or polyline can be used. For example, closed curve can be used to label the block-shaped lesion area, and non-closed curve can be used to label the linear or long-shaped lesion area.

在一实施例中，如图3所示，步骤S110之前还包括步骤S1101。In one embodiment, as shown in FIG. 3 , step S1101 is further included before step S110 .

S1101、发送未添加病灶标注的所述医疗影像资料至多台所述用户终端，以获取对应的多个用户通过多台所述用户终端添加的病灶标注，得到所述已添加病灶标注的医疗影像资料。S1101. Send the medical image data without the lesion labeling added to a plurality of the user terminals, so as to obtain the lesion labeling added by the corresponding plurality of users through the plurality of the user terminals, and obtain the medical image data with the lesion labeling added. .

具体的，用户终端接收到医疗影像资料后，可在所述用户终端的显示装置中显示所述医疗影像资料中的任意一张图像，获取用户从预置的多个病灶类型中选择的一个病灶类型作为对应的类型信息并添加至所述图像中；根据预置的间隔时间，周期性采集画笔接触所述显示装置的时间段内所述画笔在显示装置中所处的位置点，将所述位置点的连线作为对应的标注曲线并添加至所述图像中。Specifically, after receiving the medical image data, the user terminal can display any image in the medical image data on the display device of the user terminal, and acquire a lesion selected by the user from a plurality of preset lesion types The type is added to the image as the corresponding type information; according to the preset interval time, the position of the brush in the display device during the period when the brush contacts the display device is periodically collected, and the Lines connecting the location points are added to the image as corresponding annotation curves.

在获取标注曲线时，可以是用户手持画笔在显示装置上画出曲线，显示装置用于显示图像，显示装置每隔一个间隔时间(例如0.1秒)采集画笔在显示装置中所处的位置点，得到画笔接触显示装置的时间段内对应采集得到的多个位置点，每一位置点对应一个采集时间，将所得到的多个位置点连线即可得到一条标注曲线。When acquiring the labeling curve, the user can hold a paintbrush to draw a curve on the display device, the display device is used to display the image, and the display device collects the position point of the paintbrush in the display device at intervals (for example, 0.1 seconds), A plurality of position points corresponding to the collection are obtained within the time period when the brush contacts the display device, each position point corresponds to a collection time, and a mark curve can be obtained by connecting the obtained plurality of position points.

S120、判断所述待验证标注信息中的两个所述病灶标注的类型信息是否相同。S120. Determine whether the type information of the two lesion annotations in the to-be-verified annotation information is the same.

判断所述待验证标注信息中的两个所述病灶标注的类型信息是否相同。在对待验证标注信息所包含的两个病灶标注是否一致进行检验时，首先需判断两个病灶标注的类型信息是否相同。若两个病灶标注的类型信息不相同，则得到待验证标注信息不一致的验证结果；若两个病灶标注的类型信息相同，则对两个病灶标注的标注曲线进行下一步检验。Determine whether the type information of the two lesion annotations in the annotation information to be verified is the same. When checking whether the two lesion annotations included in the annotation information to be verified are consistent, it is first necessary to determine whether the type information of the two lesion annotations is the same. If the type information of the two lesions annotated is different, a verification result that the annotation information to be verified is inconsistent is obtained; if the type information of the two lesion annotations is the same, the next step is performed on the annotation curves of the two lesion annotations.

S130、若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果。S130. If the type information of the two lesion annotations is the same, determine whether the marked curves in the two lesion annotations are closed curves to obtain a curve type determination result.

若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果。对一条标注曲线进行判断后，即可确定该标注曲线为闭合曲线还是非闭合曲线；对两个病灶标注的标注曲线进行曲线类型判断，即可得到曲线类型判断结果，曲线类型判断结果包括三种：两个标注曲线均为闭合曲线、两个标注曲线均为非闭合曲线或一个标注曲线为闭合曲线另一个标注曲线为非闭合曲线。也可以是直接获取病灶标注中用于记载标注曲线形状的字段值，以得到每一病灶标注中标注曲线为闭合曲线或非闭合曲线的信息。例如圆形、椭圆形或多边形的标注曲线均为闭合曲线，折线的标注曲线则为非闭合曲线。If the type information of the two lesion annotations is the same, it is determined whether the marked curves in the two lesion annotations are closed curves to obtain a curve type determination result. After judging a marked curve, it can be determined whether the marked curve is a closed curve or a non-closed curve; by judging the curve types of the marked curves marked by two lesions, the curve type judgment results can be obtained, and the curve type judgment results include three types. : Both label curves are closed curves, both label curves are non-closed curves, or one label curve is a closed curve and the other label curve is a non-closed curve. It is also possible to directly obtain the field value used to record the shape of the labeling curve in the lesion labeling, so as to obtain the information that the labeling curve in each lesion labeling is a closed curve or a non-closed curve. For example, circle, ellipse, or polygon dimension curves are closed curves, while polyline dimension curves are non-closed curves.

在一实施例中，如图4所示，步骤S130包括子步骤S131和S132。In one embodiment, as shown in FIG. 4 , step S130 includes sub-steps S131 and S132.

S131、根据一条所述标注曲线中位置点的采集时间确定所述标注曲线的起点和终点。S131. Determine the starting point and the end point of the marking curve according to the collection time of the position point in one of the marking curves.

根据一条所述标注曲线中位置点的采集时间确定所述标注曲线的起点和终点。具体的，标注曲线由多个位置点组成，可根据位置点对应的采集时间获取标注曲线的起点和终点，具体的，将标注曲线中采集时间最早的一个位置点确定为起点，将采集时间最晚的一个位置点确定为终点，即可得到该标注曲线的起点和终点。The starting point and the end point of the marking curve are determined according to the collection time of a position point in one of the marking curves. Specifically, the labeling curve is composed of multiple position points, and the starting point and the end point of the labeling curve can be obtained according to the collection time corresponding to the position point. A later position point is determined as the end point, and the start point and end point of the marked curve can be obtained.

S132、判断所述起点和所述终点的距离差是否小于预设的距离阈值，以得到所述标注曲线是否为闭合曲线的判断结果。S132 , judging whether the distance difference between the starting point and the ending point is less than a preset distance threshold, so as to obtain a judgment result of whether the marked curve is a closed curve.

判断所述起点和所述终点的距离差是否小于预设的距离阈值，以得到所述标注曲线是否为闭合曲线的判断结果。可通过判断所述标注曲线中起点和终点的距离差是否小于预设的距离阈值，以判断标注曲线的起点和终点是否重合，若某条标注曲线的起点和终点的距离差小于距离阈值，则判断得到该标注曲线的起点和终点重合，该标注曲线为闭合曲线；若某条标注曲线的起点和终点的距离差不小于距离阈值，则判断得到该标注曲线的起点和终点不重合， 该标注曲线不为闭合曲线。其中，预设的距离阈值可以是像素数或长度值。It is judged whether the distance difference between the starting point and the ending point is less than a preset distance threshold, so as to obtain a judgment result of whether the marked curve is a closed curve. By judging whether the distance difference between the start point and the end point in the labeling curve is less than the preset distance threshold, it can be judged whether the start point and the end point of the labeling curve coincide. It is judged that the starting point and the end point of the marked curve are coincident, and the marked curve is a closed curve; if the distance difference between the starting point and the end point of a marked curve is not less than the distance threshold, it is judged that the starting point and the end point of the marked curve do not overlap, and the mark The curve is not a closed curve. The preset distance threshold may be the number of pixels or the length value.

例如，若预设的距离阈值设置为5个像素，若某条标注曲线的起点和终点的距离差小于5个像素，则得到该标注曲线为闭合曲线的判断结果；否则得到该标注曲线为非闭合曲线的判断结果。For example, if the preset distance threshold is set to 5 pixels, if the distance difference between the start point and the end point of an annotation curve is less than 5 pixels, the judgment result of the annotation curve as a closed curve is obtained; otherwise, it is obtained that the annotation curve is not Judgment result of closed curve.

采用上述方法分别对两个病灶标注中的标注曲线进行曲线类型判断，综合两个标记曲线的判断结果即可得到最终的曲线类型判断结果。The above method is used to judge the curve types of the marked curves in the two lesion markings respectively, and the final curve type judgment result can be obtained by combining the judgment results of the two marked curves.

S140、若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则。S140. If the marked curves in the two lesion markings are both non-closed curves, determine whether the two marked curves are similar according to a preset curve judgment rule to obtain a verification result of whether the marked information to be verified is consistent, so The above curve judgment rule is a judgment rule based on the dynamic time warping algorithm.

若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则。所述曲线判断规则包括路径相似度阈值、跨度阈值、偏移阈值、动态时间规整算法、跨度获取规则、偏移距离获取规则、相似度计算公式及相似度阈值。具体的，首先根据跨度获取规则获取两个标注曲线的跨度差；若判断跨度差不大于跨度阈值，则根据偏移距离获取规则获取两个标注曲线的偏移距离；若偏移距离大于偏移阈值，则根据动态时间规整算法获取两个标注曲线的路径相似度；若路径相似度大于路径相似度阈值，则根据相似度计算公式计算两个标注曲线的相似度，相似度基于跨度差、路径相似度及偏移距离三个维度计算得到，若相似度大于相似度阈值，得到待验证标注信息的验证结果为一致。若跨度差小于跨度阈值或路径相似度不大于路径相似度阈值或偏移距离不大于偏移阈值或相似度不大于相似度阈值，则得到验证标注信息的验证结果为不一致。If the marked curves in the two lesion markings are both non-closed curves, according to the preset curve judgment rule, it is judged whether the two marked curves are similar to obtain the verification result of whether the marked information to be verified is consistent, and the curve The judgment rule is a judgment rule based on the dynamic time warping algorithm. The curve judgment rule includes path similarity threshold, span threshold, offset threshold, dynamic time warping algorithm, span acquisition rule, offset distance acquisition rule, similarity calculation formula and similarity threshold. Specifically, first obtain the span difference of the two labeled curves according to the span acquisition rule; if it is judged that the span difference is not greater than the span threshold, then obtain the offset distance of the two labeled curves according to the offset distance acquisition rule; if the offset distance is greater than the offset If the path similarity is greater than the path similarity threshold, the similarity of the two marked curves is calculated according to the similarity calculation formula, and the similarity is based on the span difference, path The three dimensions of similarity and offset distance are calculated. If the similarity is greater than the similarity threshold, the verification result of the annotation information to be verified is consistent. If the span difference is less than the span threshold or the path similarity is not greater than the path similarity threshold or the offset distance is not greater than the offset threshold or the similarity is not greater than the similarity threshold, the verification result of the verification annotation information is inconsistent.

其中，本案中所采用的动态时间规整算法(Dynamic Time Warping，DTW)获取两个标注曲线的路径相似度，动态时间规整算法动态规划(DP)的思想，基于动态时间规整算法可对路径重合度较高的两条曲线的路径相似度进行计算。Among them, the Dynamic Time Warping (DTW) algorithm used in this case obtains the path similarity of two marked curves, and the idea of the dynamic time warping algorithm dynamic programming (DP), based on the dynamic time warping algorithm, can calculate the path coincidence degree. The path similarity of the higher two curves is calculated.

在一实施例中，如图5所示，步骤S140包括子步骤S141、S142、S143和S144。In one embodiment, as shown in FIG. 5 , step S140 includes sub-steps S141 , S142 , S143 and S144 .

S141、根据所述跨度获取规则获取两个所述标注曲线的跨度差，判断所述跨度差是否不大于所述跨度阈值。S141. Acquire the span difference between the two marked curves according to the span obtaining rule, and determine whether the span difference is not greater than the span threshold.

根据所述跨度获取规则获取两个所述标注曲线的跨度差，判断所述跨度差是否不大于所述跨度阈值。为获取两个标注曲线的路径相似度，需先判断两条标注曲线的路径重合度，可通过获取两个标注曲线的跨度差对两条标注曲线是否具有较高的路径重合度进行判断。其中，两个标注曲线的跨度差包括横向跨度差及纵向跨度差，所述跨度阈值包括横向跨度阈值及纵向跨度阈值。The span difference between the two marked curves is obtained according to the span obtaining rule, and it is judged whether the span difference is not greater than the span threshold. In order to obtain the path similarity of the two marked curves, it is necessary to first judge the path coincidence degree of the two marked curves. By obtaining the span difference of the two marked curves, it is possible to judge whether the two marked curves have a high degree of path coincidence. The span difference between the two marked curves includes a horizontal span difference and a vertical span difference, and the span threshold includes a horizontal span threshold and a vertical span threshold.

在一实施例中，如图6所示，步骤S141包括子步骤S1411和S1442。In one embodiment, as shown in FIG. 6 , step S141 includes sub-steps S1411 and S1442.

S1411、根据所述跨度获取规则分别获取两个所述标注曲线的横向跨度差及纵向跨度差；S1442、判断所述横向跨度差是否不大于横向跨度阈值且所述纵向跨度差是否不大于所述纵向跨度阈值，以得到所述跨度差是否不大于所述跨度阈值的判断结果。S1411. Obtain the horizontal span difference and the vertical span difference of the two marked curves respectively according to the span obtaining rule; S1442. Determine whether the horizontal span difference is not greater than a horizontal span threshold and whether the vertical span difference is not greater than the The longitudinal span threshold is used to obtain a judgment result of whether the span difference is not greater than the span threshold.

横向跨度即为一个标注曲线在横坐标方向上的跨度，纵向跨度即为一个标注曲线在纵坐标方向上的跨度。分别获取两个标注曲线的横向跨度，计算两个标注曲线中横向跨度的较小值与较大值的比值，即可得到横向跨度差X_r，纵向跨度差Y_r的获取方式与横向跨度差的获取方式类似。若横向跨度差不大于横向跨度阈值且纵向跨度差不大于纵向跨度阈值，则得到跨 度差不大于跨度阈值的判断结果；否则得到跨度差大于跨度阈值的判断结果。其中，X_r及Y_r的取值范围均为(0，1]。The horizontal span is the span of a labeling curve in the abscissa direction, and the longitudinal span is the span of a labeling curve in the ordinate direction. Obtain the horizontal spans of the two marked curves respectively, and calculate the ratio of the smaller value to the larger value of the horizontal spans in the two marked curves, then the horizontal span difference X_r and the vertical span difference Y_r can be obtained in the same way as the horizontal span difference. is obtained in a similar manner. If the horizontal span difference is not greater than the horizontal span threshold and the vertical span difference is not greater than the vertical span threshold, the judgment result that the span difference is not greater than the span threshold is obtained; otherwise, the judgment result that the span difference is greater than the span threshold is obtained. The value ranges of X_r and Y_r are both (0, 1].

S142、若所述跨度差不大于所述跨度阈值，根据所述偏移距离获取规则获取两个所述标注曲线的偏移距离，判断所述偏移距离是否大于所述偏移阈值。S142. If the span difference is not greater than the span threshold, obtain the offset distances of the two labeled curves according to the offset distance acquisition rule, and determine whether the offset distance is greater than the offset threshold.

若所述跨度差不大于所述跨度阈值，根据所述偏移距离获取规则获取两个所述标注曲线的偏移距离，判断所述偏移距离是否大于所述偏移阈值。在计算偏移距离时，可先对两个标注曲线所包含的位置点的数量是否相等进行判断，若位置点的数量不相等，则可对较短的一个标注曲线进行均匀填充以使两个标注曲线所包含的位置点的数量相等。具体的，位置点数量较多的标注曲线记为曲线A，其数量为C_A，较少的标注曲线记为曲线B，其数量为C_B，点数差值C_D＝C_A-C_B，向曲线B中的某两个位置点(例如第n个位置点与第n+1个位置点)之间填充C_P＝ceil(C_D/C_B)个点，其中ceil是向上取整，填充方式为每隔(L_n+1-L_n)/C_D的距离增加一个点，L_n+1-L_n为第n个位置点与第n+1个位置点之间的距离差，每两个点之间一共填充C_P个点。偏移距离获取规则为基于弗雷歇距离的获取规则，使用σ(A)和σ(B)分别表示曲线A及曲线B中位置点的顺序集合，则有σ(A)＝(u₁，u₂，...，u_A)和σ(B)＝(v₁，v₂，...，v_B)；则可以进一步得到如下位置点对的顺序集合可采用公式(4)进行表示If the span difference is not greater than the span threshold, obtain the offset distances of the two labeled curves according to the offset distance acquisition rule, and determine whether the offset distance is greater than the offset threshold. When calculating the offset distance, you can first judge whether the number of position points contained in the two annotation curves is equal. The callout curve contains an equal number of location points. Specifically, the marked curve with a large number of position points is marked as curve A, and its number is marked as C_A , and the marked curve with less number of points is marked as curve B, and its number is marked as C_B , and the point difference value C_D =C_A -C_B , Fill C_P =ceil(C_D /C_B ) points between some two position points in the curve B (for example, the nth position point and the n+1th position point), where ceil is rounded up, The filling method is to add a point every (L_n+1 -L_n )/C_D distance, L_n+1 -L_n is the distance difference between the nth position point and the n+1th position point, A total of C_P points are filled between every two points. The offset distance acquisition rule is based on the Frecher distance acquisition rule, using σ(A) and σ(B) to represent the sequence set of the position points in curve A and curve B respectively, then σ(A)=(u₁ ,_{u2,._}

L＝(u_a1，v_b1)，(u_a2，v_b2)，...，(u_ai，v_bi)     (4)；L=(u_a1 , v_b1 ), (u_a2 , v_b2 ), ..., (u_ai , v_bi ) (4);

其中，a_i＝1，2，…A，a_i＝1，2，…B(B＝A)，对于任意一个a_i，均可得到a_i+1＝a_i，或者a_i+1＝a_i+1及b_i+1＝b_i+1；曲线A及曲线B的位置点对之间的长度||L||可定义为各位置点对的欧氏距离最大值的累加值，也即是

对应的得到曲线A与曲线B的弗雷歇距离为δ_dF(A，B)＝min||L||，偏移距离为f_rd＝δ_dF/min(L_A，L_B)，f_rd的取值范围为(0，1]，min(L_A，L_B)为曲线A的欧氏距离及曲线B的欧氏距离中欧氏距离的最小值，判断所得到的偏移距离是否大于偏移阈值。where a_i =1,2,...A, a_i =1,2,...B(B=A), for any a_i , a_i+1 =a_i , or a_i+1 = a_i +1 and b_i+1 =b_i +1; the length ||L|| between the position point pairs of curve A and curve B can be defined as the cumulative value of the maximum Euclidean distance of each position point pair, that is

Correspondingly, the Frechet distance between curve A and curve B is obtained as δ_dF (A, B)=min||L||, and the offset distance is f_rd =δ_dF /min(L_A ,L_B ),f_rd The value range of is (0, 1], min(L_A , L_B ) is the minimum value of the Euclidean distance between the Euclidean distance of curve A and the Euclidean distance of curve B, and judge whether the obtained offset distance is greater than the offset distance. shift the threshold.

在一实施例中，如图7所示，步骤S143之前还包括步骤S1431和S1432。In one embodiment, as shown in FIG. 7 , steps S1431 and S1432 are further included before step S143 .

S1431、根据每一所述标注曲线的时间轴获取与每一所述标注曲线对应的时间序列并判断两个所述时间序列是否统一。S1431. Acquire a time series corresponding to each of the labeled curves according to the time axis of each of the labeled curves, and determine whether the two time series are unified.

根据每一所述标注曲线的时间轴获取与每一所述标注曲线对应的时间序列并判断两个所述时间序列是否统一。每一标注曲线均由多个位置点组成，每一位置点均对比一个采集时间，位置点可采用像素坐标进行表示，由于画笔在显示装置上沿水平方向进行移动的速度可能存在变化，上一位置点与下一位置点之间均间隔一个固定的间隔时间，上一位置点与下一位置点也即构成一组前后位置点，多个前后位置点在横坐标上的投影距离可能存在变化，一个标注曲线中多个前后位置点在横坐标上的投影距离组合后即构成一个标注曲线的时间序列，判断两个时间序列是否统一，只需判断两个时间序列中对应的两组前后位置点在横坐标上的投影距离是否相等，若两个时间序列所包含的前后位置点的数量不相等，则以数量较少的时间序列中前后位置点的数量作为比较基准。Acquire a time series corresponding to each of the labeled curves according to the time axis of each of the labeled curves, and determine whether the two time series are unified. Each annotation curve is composed of multiple position points, and each position point is compared with a collection time. The position point can be represented by pixel coordinates. Since the speed of the brush moving in the horizontal direction on the display device may vary, the There is a fixed interval between the position point and the next position point. The previous position point and the next position point also constitute a group of front and rear position points. The projection distance of multiple front and rear position points on the abscissa may vary. , the projection distances of multiple front and rear position points in a labeling curve on the abscissa form a time series of labeling curve. To judge whether the two time series are unified, it is only necessary to judge the corresponding two sets of front and rear positions in the two time series. Whether the projection distances of points on the abscissa are equal, if the number of before and after position points contained in the two time series is not equal, the number of before and after position points in the time series with the smaller number is used as the comparison benchmark.

例如，一个时间序列对应的信息如表1所示。For example, the information corresponding to a time series is shown in Table 1.

前后位置点编号Front and rear position point number112233445566投影距离/像素数Projection Distance/Number of Pixels447733665544

表1Table 1

S1432、若两个所述时间序列不统一，对两个所述标注曲线进行调整以使两个所述标注曲线的时间序列统一。S1432. If the two time series are not unified, adjust the two labeled curves to make the time series of the two labeled curves unified.

若两个时间序列不统一，对两个所述标注曲线进行调整以使两个所述标注曲线的时间序列统一。若两个时间序列不统一，则可以对两个标注曲线进行调整以统一时间序列。例如，若两个时间序列中对应的两组前后位置点的投影距离分别为3个像素及5个像素，则可将两组前后位置点的投影距离均调整为3个像素，并根据标注曲线中前后位置点进行调整的一段曲线进行压缩调整，压缩的调整的过程也即是对标注曲线中的位置点进行调整，经过调整后所得到的两个标注曲线的时间序列统一。若两个时间序列所包含的前后位置点的数量不相等，则以数量较少的时间序列中前后位置点的数量作为调准基准。If the two time series are not unified, the two labeled curves are adjusted so that the time series of the two labeled curves are unified. If the two time series are not unified, the two label curves can be adjusted to unify the time series. For example, if the projection distances of the corresponding two groups of front and rear position points in the two time series are 3 pixels and 5 pixels, respectively, the projection distance of the two groups of front and rear position points can be adjusted to 3 pixels, and according to the labeling curve A segment of the curve whose front and rear position points are adjusted is compressed and adjusted. The process of compression adjustment is to adjust the position points in the labeling curve, and the time series of the two labeling curves obtained after adjustment are unified. If the number of before and after position points contained in the two time series is not equal, the number of before and after position points in the time series with the smaller number is used as the alignment reference.

S143、若所述偏移距离大于所述偏移阈值，根据所述动态时间规整算法获取两个所述标注曲线的路径相似度，判断所述路径相似度是否大于所述路径相似度阈值。S143. If the offset distance is greater than the offset threshold, obtain the path similarity of the two labeled curves according to the dynamic time warping algorithm, and determine whether the path similarity is greater than the path similarity threshold.

若所述偏移距离大于所述偏移阈值，根据所述动态时间规整算法获取两个所述标注曲线的路径相似度，判断所述路径相似度是否大于所述路径相似度阈值。动态时间规整算法可获取两个标注曲线之间的最短规整距离及最长规整距离，并根据动态时间规整算法中的计算公式计算得到路径相似度，判断路径相似度是否大于路径相似度阈值。If the offset distance is greater than the offset threshold, obtain the path similarity of the two labeled curves according to the dynamic time warping algorithm, and determine whether the path similarity is greater than the path similarity threshold. The dynamic time warping algorithm can obtain the shortest and longest normalizing distance between two marked curves, and calculate the path similarity according to the calculation formula in the dynamic time warping algorithm, and judge whether the path similarity is greater than the path similarity threshold.

例如，两条标注曲线分别为曲线A和曲线B，他们的最短规整距离可采用公式(1)进行表示，最长规整距离可采用公式(2)进行表示。For example, two marked curves are curve A and curve B respectively, their shortest regular distance can be expressed by formula (1), and their longest regular distance can be expressed by formula (2).

D(i,j)＝Dist(i,j)+min{D(i-1,j),D(i,j-1),D(i-1,j-1)}    (1)；D(i,j)=Dist(i,j)+min{D(i-1,j),D(i,j-1),D(i-1,j-1)} (1);

D’(i,j)＝Dist(i,j)+max{D’(i-1,j),D’(i,j-1),D’(i-1,j-1)}    (2)；D'(i,j)=Dist(i,j)+max{D'(i-1,j),D'(i,j-1),D'(i-1,j-1)}  ( 2);

其中，i和j均为大于等于1的正整数，Dist(i,j)为曲线A的第i个位置点与曲线B的第j个位置点之间的路径距离(两个位置点在纵坐标上的投影距离)，D(i,j)表示曲线A的前i个位置点与曲线B的前j个位置点的规整距离，需基于公式(1)进行迭代得到两个曲线的最短规整距离：从i＝1及j＝1(由于i-1或j-1对应的位置点不存在，因此此时min{D(i-1,j),D(i,j-1),D(i-1,j-1)}＝0)开始进行计算。Among them, i and j are both positive integers greater than or equal to 1, and Dist(i, j) is the path distance between the i-th position point of curve A and the j-th position point of curve B (the two position points are in the vertical direction). The projected distance on the coordinates), D(i,j) represents the regular distance between the first i position points of curve A and the first j position points of curve B, and it is necessary to iterate based on formula (1) to obtain the shortest regularity of the two curves. Distance: from i=1 and j=1 (since the position corresponding to i-1 or j-1 does not exist, so min{D(i-1,j), D(i,j-1), D (i-1,j-1)}=0) to start the calculation.

基于所得到的最短规整距离及最长规整距离即可计算得到对应的路径相似度，对路径相似度进行计算的公式可采用公式(3)进行表示。The corresponding path similarity can be calculated based on the obtained shortest regular distance and the longest regular distance, and the formula for calculating the path similarity can be expressed by formula (3).

Ds＝1-D(i,j)/D’(i,j)     (3)；Ds=1-D(i,j)/D'(i,j) (3);

其中，Ds为计算得到的路径相似度，Ds的取值范围为(0，1]。Among them, Ds is the calculated path similarity, and the value range of Ds is (0, 1].

S144、若所述路径相似度不小于所述路径相似度阈值，根据所述相似度计算公式、所述跨度差、所述路径相似度及所述偏移距离计算得到相似度，判断所述相似度是否大于所述相似度阈值以得到所述待验证标注信息的验证结果为一致。S144. If the path similarity is not less than the path similarity threshold, calculate the similarity according to the similarity calculation formula, the span difference, the path similarity and the offset distance, and determine the similarity Whether the degree is greater than the similarity threshold is consistent with obtaining the verification result of the annotation information to be verified.

若所述路径相似度不小于所述路径相似度阈值，根据所述相似度计算公式、所述跨度差、所述路径相似度及所述偏移距离计算得到相似度，判断所述相似度是否大于所述相似度阈值以得到所述待验证标注信息的验证结果为一致。具体的，相似度计算公式可采用公式(5)进行表示：If the path similarity is not less than the path similarity threshold, calculate the similarity according to the similarity calculation formula, the span difference, the path similarity and the offset distance, and determine whether the similarity is If the similarity threshold is greater than the similarity threshold, the verification result of the annotation information to be verified is consistent. Specifically, the similarity calculation formula can be expressed by formula (5):

S＝s₁×X_r+s₂×Y_r+s₃×Ds+s₄×(1-f_rd)      (5)；S=s₁ ×X_r +s₂ ×Y_r +s₃ ×Ds+s₄ ×(1-f_rd ) (5);

其中，s₁、s₂、s₃及s₄均为相似度计算公式中预设的参数值，具体的，可设置参数值满足以下条件：s₁+s₂+s₃+s₄＝1，所得到的相似度S的取值范围为(0，1]。判断计算得到的相似度是否大于相似度阈值，若大于，则得到两个标注曲线相似的判断结果，也即是得到待验证标 注信息的验证结果为一致，若不大于则得到两个标注曲线不相似的判断结果，也即是得到待验证标注信息的验证结果为不一致。例如，可设置相似度阈值为0.8。Wherein, s₁ , s₂ , s₃ and s₄ are all preset parameter values in the similarity calculation formula. Specifically, the parameter values can be set to satisfy the following conditions: s₁ +s₂ +s₃ +s₄ =1 , the value range of the obtained similarity S is (0, 1]. Determine whether the calculated similarity is greater than the similarity threshold. If it is greater, then the judgment result that the two marked curves are similar is obtained, that is, the result to be verified is obtained. The verification result of the annotation information is consistent, if it is not greater than the two annotation curves are not similar, that is, the verification result of the annotation information to be verified is inconsistent. For example, the similarity threshold can be set to 0.8.

S150、若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果。S150. If the marked curves in the two lesion markings are closed curves, determine whether the closed regions corresponding to the two marked curves overlap according to a preset coincidence degree judgment rule, so as to obtain whether the marked information to be verified is consistent verification result.

若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果。所述重合度判断规则包括重合度计算公式及重合度阈值。若两个病灶标注中的标注曲线均为闭合曲线，则可根据重合度判断规则获取对应的重合度，并基于重合度判断两个标注曲线对应的闭合区域是否重合。If the marked curves in the two lesion markings are closed curves, determine whether the closed areas corresponding to the two marked curves overlap according to the preset coincidence degree judgment rule, so as to obtain the verification of whether the marked information to be verified is consistent result. The coincidence degree judgment rule includes a coincidence degree calculation formula and a coincidence degree threshold. If the marked curves in the two lesion markings are closed curves, the corresponding coincidence degree can be obtained according to the coincidence degree judgment rule, and based on the coincidence degree, it is judged whether the closed areas corresponding to the two marked curves overlap.

在一实施例中，如图8所示，步骤S150包括子步骤S151、S152和S153。In one embodiment, as shown in FIG. 8 , step S150 includes sub-steps S151 , S152 and S153 .

S151、对两个所述标注曲线对应的闭合区域进行像素填充以得到对应的两个像素图像。S151. Fill the closed regions corresponding to the two marked curves with pixels to obtain two corresponding pixel images.

对两个所述标注曲线对应的闭合区域进行像素填充以得到对应的两个像素图像。获取两个标注曲线对应的闭合区域，并在闭合区域内进行像素填充，从而得到对应的两个像素图像，所得到的像素图像的尺寸相同(像素图像的尺寸与医疗影像资料中图像的尺寸相同)，在像素图像中被填充的像素点的值为1，未被填充的像素点的值为0。Pixel filling is performed on the closed regions corresponding to the two marked curves to obtain corresponding two pixel images. Obtain the closed area corresponding to the two annotation curves, and fill in the pixels in the closed area to obtain the corresponding two pixel images, and the obtained pixel images have the same size (the size of the pixel image is the same as that of the image in the medical imaging data). ), the value of the filled pixel in the pixel image is 1, and the value of the unfilled pixel is 0.

S152、根据重合度计算公式及两个所述像素图像之间的重叠像素及两个所述像素图像分别对应的有效像素计算得到对应的重合度。S152: Calculate the corresponding degree of coincidence according to the calculation formula of the degree of coincidence, the overlapping pixels between the two pixel images, and the effective pixels corresponding to the two pixel images respectively.

根据重合度计算公式及两个所述像素图像之间的重叠像素及两个所述像素图像分别对应的有效像素计算得到对应的重合度。将两个像素图像重叠，两张像素图像中的像素点的值累加，像素点的值为2即表明该像素点为两个像素图像中的重叠像素，统计像素点的值为2的数量，任意一张像素图像中像素点的值为1的像素点即为该像素图像中的有效像素。则重合度计算公式可采用公式(6)进行表示：The corresponding coincidence degree is calculated according to the calculation formula of the coincidence degree, the overlapping pixels between the two pixel images, and the effective pixels corresponding to the two pixel images respectively. The two pixel images are overlapped, and the values of the pixel points in the two pixel images are accumulated. The value of the pixel point is 2, which means that the pixel point is an overlapping pixel in the two pixel images. Count the number of pixel points whose value is 2. A pixel whose pixel value is 1 in any pixel image is an effective pixel in the pixel image. Then the calculation formula of the coincidence degree can be expressed by formula (6):

Sx＝2×S₂/(S_A+S_B)      (6)；Sx=2×S₂ /(S_A +S_B ) (6);

其中，Sx为所得到的重合度，Sx的取值范围为(0，1]，S₂为两个像素图像中重叠像素的数量，S_A为像素图像A的有效像素的数量，S_B为像素图像B的有效像素的数量。Among them, Sx is the obtained degree of coincidence, the value range of Sx is (0, 1], S2 is the number of overlapping pixels in the_two pixel images, S_A is the number of effective pixels in pixel image A, and S_B is The number of valid pixels of pixel image B.

S153、判断所述重合度是否不小于所述重合度阈值以得到两个所述标注曲线对应的闭合区域是否重合以得到所述待验证标注信息的验证结果为一致。S153 , judging whether the coincidence degree is not less than the coincidence degree threshold to obtain whether the closed regions corresponding to the two labeling curves overlap to obtain the verification result of the labeling information to be verified is consistent.

对所得到的重合度是否不小于重合度阈值进行判断，若重合度不小于重合度阈值，则得到两个标注曲线对应的闭合区域重合的判断结果，也即是得到待验证标注信息的验证结果为一致；否则得到不重合的判断结果，也即是得到验证标注信息的验证结果为不一致。例如，重合度阈值可预设为80％。It is judged whether the obtained coincidence degree is not less than the coincidence degree threshold. If the coincidence degree is not less than the coincidence degree threshold, the judgment result of the overlap of the closed regions corresponding to the two annotation curves is obtained, that is, the verification result of the annotation information to be verified is obtained. It is consistent; otherwise, a non-coincident judgment result is obtained, that is, the verification result obtained from the verification annotation information is inconsistent. For example, the coincidence threshold may be preset to 80%.

S160、若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结果。S160. If the annotation curves in the two lesion annotations are closed curves and non-closed curves respectively, determine whether the pixels corresponding to the two annotation curves overlap according to a preset proportion threshold, so as to obtain the to-be-verified annotation information Whether the verification results are consistent.

若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结果。若一个病灶标注中的标注曲线为闭合曲线，另一个为非闭合曲线，则可获取两个标注曲线的像素占比，并判断像素占比是否不小于占比阈值，以得到两个标注曲线对应的像素是否 重叠的判断结果。If the annotation curves in the two lesion annotations are closed curves and non-closed curves respectively, it is determined whether the pixels corresponding to the two annotation curves overlap according to the preset proportion threshold, so as to obtain whether the annotation information to be verified is consistent verification result. If the labeled curve in one lesion labeling is a closed curve and the other is a non-closed curve, the pixel proportions of the two labeled curves can be obtained, and it can be determined whether the pixel proportion is not less than the proportion threshold, so as to obtain the corresponding pixels of the two labeled curves. The judgment result of whether the pixels overlap.

具体的步骤包括：对所述闭合曲线对应的闭合区域进行像素填充以得到对应的像素图像；获取所述非闭合曲线与所述像素图像之间的重叠像素在所述非闭合曲线中的占比得到对比的像素占比；判断所述像素占比是否不小于所述占比阈值，以得到所述待验证标注信息是否一致的验证结果The specific steps include: filling the closed area corresponding to the closed curve with pixels to obtain a corresponding pixel image; acquiring the proportion of the overlapping pixels between the open curve and the pixel image in the open curve Obtain the pixel ratio of the comparison; determine whether the pixel ratio is not less than the ratio threshold, so as to obtain the verification result of whether the label information to be verified is consistent

对所述闭合曲线对应的闭合区域进行像素填充以得到对应的像素图像，获取其中为闭合曲线的标注曲线所对应的闭合区域，并在闭合区域内进行像素填充，从而得到对应的一个像素图像，所得到的像素图像的尺寸相同(像素图像的尺寸与医疗影像资料中图像的尺寸相同)，在像素图像中被填充的像素点的值为1，未被填充的像素点的值为0。Filling the closed area corresponding to the closed curve with pixels to obtain a corresponding pixel image, obtaining the closed area corresponding to the labeling curve of the closed curve, and performing pixel filling in the closed area, thereby obtaining a corresponding pixel image, The size of the obtained pixel image is the same (the size of the pixel image is the same as the size of the image in the medical image data), the value of the filled pixel in the pixel image is 1, and the value of the unfilled pixel is 0.

获取所述非闭合曲线与所述像素图像之间的重叠像素的数量，计算重叠像素的数量与非闭合曲线中像素数量的比值，也即是计算重叠像素在非闭合曲线中的占比，所得到的比值即为像素占比。Obtain the number of overlapping pixels between the non-closed curve and the pixel image, calculate the ratio of the number of overlapping pixels to the number of pixels in the non-closed curve, that is, calculate the proportion of overlapping pixels in the non-closed curve, so The resulting ratio is the pixel ratio.

对所得到的像素占比是否不小于占比阈值进行判断，若像素占比不小于占比阈值，得到两个标注曲线对应的像素重叠的判断结果，也即是得到待验证标注信息的验证结果为一致；否则得到两个标注曲线对应的像素不重叠的判断结果，也即是得到待验证标注信息的验证结果为不一致。It is judged whether the obtained pixel proportion is not less than the proportion threshold. If the pixel proportion is not less than the proportion threshold, the judgment result of overlapping pixels corresponding to the two annotation curves is obtained, that is, the verification result of the annotation information to be verified is obtained. Otherwise, the judgment result that the pixels corresponding to the two annotation curves do not overlap will be obtained, that is, the verification result of the annotation information to be verified is inconsistent.

本申请中的技术方法可应用于智慧医疗等包含对病灶标注信息是否一致进行验证的应用场景中，从而推动智慧城市的建设。The technical methods in this application can be applied to application scenarios such as smart medical care, which include verifying whether the labeling information of lesions is consistent, so as to promote the construction of smart cities.

在本申请实施例所提供的病灶标注的验证方法中，获取医疗影像资料中任意一张图像的两个病灶标注作为待验证标注信息，判断两个病灶标注的类型信息是否相同；若相同，则判断两个病灶标注中的标注曲线是否为非闭合曲线；若两个标注曲线均为非闭合曲线，根据基于动态时间规整算法的曲线判断规则判断两个标注曲线是否相似得到是否一致的验证结果；若两个标注曲线均为闭合曲线，根据重合度判断规则判断两个标注曲线的闭合区域是否重合得到是否一致的验证结果；若两个标注曲线分别为闭合曲线及非闭合曲线，根据占比阈值判断两个标注曲线对应的像素是否重叠得到是否一致的验证结果。通过上述方法，可采用统一标准对病灶标注的一致性进行验证，可大幅提高对病灶标注进行验证的效率及质量。In the verification method for lesion annotation provided by the embodiment of the present application, two lesion annotations of any image in the medical imaging data are obtained as the annotation information to be verified, and it is judged whether the type information of the two lesion annotations is the same; if they are the same, then Determine whether the marked curves in the two lesion annotations are non-closed curves; if both marked curves are non-closed curves, determine whether the two marked curves are similar according to the curve judgment rule based on the dynamic time warping algorithm to obtain the same verification result; If the two marked curves are closed curves, determine whether the closed areas of the two marked curves overlap according to the coincidence judgment rule to obtain the same verification result; if the two marked curves are closed curves and non-closed curves respectively, according to the proportion threshold Determine whether the pixels corresponding to the two annotation curves overlap to obtain the same verification result. Through the above method, a unified standard can be used to verify the consistency of lesion annotation, which can greatly improve the efficiency and quality of lesion annotation verification.

本申请实施例还提供一种病灶标注的验证装置，该病灶标注的验证装置用于执行前述病灶标注的验证方法的任一实施例。具体地，请参阅图9，图9是本申请实施例提供的病灶标注的验证装置的示意性框图。该病灶标注的验证装置可以配置于管理服务器10中。An embodiment of the present application further provides a verification device for lesion labeling, which is used for performing any embodiment of the foregoing verification method for lesion labeling. Specifically, please refer to FIG. 9. FIG. 9 is a schematic block diagram of a verification device for lesion labeling provided by an embodiment of the present application. The verification device for lesion marking may be configured in themanagement server 10 .

如图9所示，病灶标注的验证装置100包括待验证标注信息获取单元110、类型信息判断单元120、曲线类型判断单元130、第一验证单元140、第二验证单元150和第三验证单元160。As shown in FIG. 9 , theverification device 100 for lesion labeling includes a to-be-verified labelinginformation acquisition unit 110 , a type information determination unit 120 , a curvetype determination unit 130 , afirst verification unit 140 , asecond verification unit 150 and athird verification unit 160 .

待验证标注信息获取单元110，用于接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息。The to-be-verified annotationinformation acquisition unit 110 is configured to receive the medical image data to which the lesion annotation has been added from the user terminal, and to acquire two lesion annotations of any image in the medical image data as the to-be-verified annotation information.

在一实施例中，所述病灶标注的验证装置100还包括子单元：医疗影像资料发送单元。In an embodiment, theverification apparatus 100 for lesion marking further includes a subunit: a medical image data sending unit.

医疗影像资料发送单元，用于发送未添加病灶标注的所述医疗影像资料至多台所述用户终端，以获取对应的多个用户通过多台所述用户终端添加的病灶标注，得到所述已添加病灶标注的医疗影像资料。A medical image data sending unit, configured to send the medical image data without the lesion label added to a plurality of the user terminals, so as to obtain the lesion labels added by the corresponding plurality of users through the plurality of user terminals, and obtain the added The medical imaging data of the lesion labeling.

类型信息判断单元120，用于判断所述待验证标注信息中的两个所述病灶标注的类型信 息是否相同。The type information determination unit 120 is configured to determine whether the type information of the two lesion annotations in the to-be-verified annotation information is the same.

曲线类型判断单元130，用于若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果。The curvetype determination unit 130 is configured to determine whether the marked curve in the two lesion annotations is a closed curve to obtain a curve type determination result if the type information of the two lesion annotations is the same.

在一实施例中，所述曲线类型判断单元130包括子单元：确定单元和距离差判断单元。In one embodiment, the curvetype determination unit 130 includes subunits: a determination unit and a distance difference determination unit.

确定单元，用于根据一条所述标注曲线中位置点的采集时间确定所述标注曲线的起点和终点；距离差判断单元，用于判断所述起点和所述终点的距离差是否小于预设的距离阈值，以得到所述标注曲线是否为闭合曲线的判断结果。A determination unit, used for determining the start point and end point of the label curve according to the collection time of a position point in one of the label curves; a distance difference judgment unit, used for judging whether the distance difference between the start point and the end point is less than a preset distance threshold to obtain the judgment result of whether the marked curve is a closed curve.

第一验证单元140，用于若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则。Thefirst verification unit 140 is configured to determine whether the two marked curves are similar according to a preset curve judgment rule if the marked curves in the two lesion markings are both non-closed curves, so as to obtain whether the marked information to be verified is not. Consistent verification results, the curve judgment rule is a judgment rule based on a dynamic time warping algorithm.

在一实施例中，所述第一验证单元140包括子单元：跨度差判断单元、偏移距离判断单元、路径相似度判断单元和相似度判断单元。In one embodiment, thefirst verification unit 140 includes subunits: a span difference judgment unit, an offset distance judgment unit, a path similarity judgment unit, and a similarity judgment unit.

跨度差判断单元，用于根据所述跨度获取规则获取两个所述标注曲线的跨度差，判断所述跨度差是否不大于所述跨度阈值。A span difference judging unit, configured to obtain the span difference between the two marked curves according to the span obtaining rule, and judge whether the span difference is not greater than the span threshold.

在一实施例中，所述跨度差判断单元包括子单元：跨度差获取单元和判断单元。In an embodiment, the span difference judgment unit includes subunits: a span difference acquisition unit and a judgment unit.

跨度差获取单元，用于根据所述跨度获取规则分别获取两个所述标注曲线的横向跨度差及纵向跨度差；判断单元，用于判断所述横向跨度差是否不大于横向跨度阈值且所述纵向跨度差是否不大于所述纵向跨度阈值，以得到所述跨度差是否不大于所述跨度阈值的判断结果。a span difference obtaining unit, used to obtain the horizontal span difference and the vertical span difference of the two marked curves according to the span obtaining rule; a judgment unit, used to judge whether the horizontal span difference is not greater than the horizontal span threshold and the Whether the longitudinal span difference is not greater than the longitudinal span threshold is obtained to obtain a judgment result of whether the span difference is not greater than the span threshold.

偏移距离判断单元，用于若所述跨度差不大于所述跨度阈值，根据所述偏移距离获取规则获取两个所述标注曲线的偏移距离，判断所述偏移距离是否大于所述偏移阈值。an offset distance judgment unit, configured to obtain the offset distances of the two marked curves according to the offset distance acquisition rule if the span difference is not greater than the span threshold, and determine whether the offset distance is greater than the offset distance offset threshold.

在一实施例中，所述第一验证单元140包括子单元：时间序列判断单元和曲线调整单元。In one embodiment, thefirst verification unit 140 includes subunits: a time series judgment unit and a curve adjustment unit.

时间序列判断单元，用于根据每一所述标注曲线的时间轴获取与每一所述标注曲线对应的时间序列并判断两个所述时间序列是否统一；曲线调整单元，用于若两个所述时间序列不统一，对两个所述标注曲线进行调整以使两个所述标注曲线的时间序列统一。The time series judgment unit is used to obtain the time series corresponding to each of the marked curves according to the time axis of each of the marked curves and judge whether the two time series are unified; the curve adjustment unit is used for if the two marked curves are unified If the time series are not unified, the two labeled curves are adjusted so that the time series of the two labeled curves are unified.

路径相似度判断单元，用于若所述偏移距离大于所述偏移阈值，根据所述动态时间规整算法获取两个所述标注曲线的路径相似度，判断所述路径相似度是否大于所述路径相似度阈值。A path similarity judgment unit, configured to obtain the path similarity of the two labeled curves according to the dynamic time warping algorithm if the offset distance is greater than the offset threshold, and determine whether the path similarity is greater than the path similarity Path similarity threshold.

相似度判断单元，用于若所述路径相似度不小于所述路径相似度阈值，根据所述相似度计算公式、所述跨度差、所述路径相似度及所述偏移距离计算得到相似度，判断所述相似度是否大于所述相似度阈值以得到所述待验证标注信息的验证结果为一致。A similarity judgment unit, configured to calculate the similarity according to the similarity calculation formula, the span difference, the path similarity and the offset distance if the path similarity is not less than the path similarity threshold , judging whether the similarity is greater than the similarity threshold, so that the verification result of the annotation information to be verified is consistent.

第二验证单元150，用于若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果。Thesecond verification unit 150 is configured to, if the marked curves in the two lesion markings are closed curves, determine whether the closed regions corresponding to the two marked curves overlap according to a preset coincidence degree judgment rule, so as to obtain the said The verification result of whether the annotation information to be verified is consistent.

在一实施例中，所述第二验证单元150包括子单元：像素图像获取单元、重合度计算单元和重合度判断单元。In one embodiment, thesecond verification unit 150 includes subunits: a pixel image acquisition unit, a coincidence degree calculation unit, and a coincidence degree determination unit.

像素图像获取单元，用于对两个所述标注曲线对应的闭合区域进行像素填充以得到对应的两个像素图像；重合度计算单元，用于根据重合度计算公式及两个所述像素图像之间的重叠像素及两个所述像素图像分别对应的有效像素计算得到对应的重合度；重合度判断单元，用于判断所述重合度是否不小于所述重合度阈值以得到两个所述标注曲线对应的闭合区域是 否重合以得到所述待验证标注信息的验证结果为一致。The pixel image acquisition unit is used to fill the closed area corresponding to the two marked curves with pixels to obtain the corresponding two pixel images; the coincidence degree calculation unit is used to calculate the coincidence degree according to the formula and the difference between the two pixel images. The overlapping pixels between the two pixels and the effective pixels corresponding to the two pixel images are calculated to obtain the corresponding coincidence degree; the coincidence degree judgment unit is used for judging whether the coincidence degree is not less than the coincidence degree threshold to obtain two of the labels Whether the closed areas corresponding to the curves are overlapped is consistent with the verification result obtained for the label information to be verified.

第三验证单元160，用于若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结果。Thethird verification unit 160 is configured to, if the marked curves in the two lesion markings are closed curves and non-closed curves respectively, determine whether the pixels corresponding to the two marked curves overlap according to a preset proportion threshold, so as to obtain The verification result of whether the annotation information to be verified is consistent.

在本申请实施例所提供的病灶标注的验证装置应用上述病灶标注的验证方法，获取医疗影像资料中任意一张图像的两个病灶标注作为待验证标注信息，判断两个病灶标注的类型信息是否相同；若相同，则判断两个病灶标注中的标注曲线是否为非闭合曲线；若两个标注曲线均为非闭合曲线，根据基于动态时间规整算法的曲线判断规则判断两个标注曲线是否相似得到是否一致的验证结果；若两个标注曲线均为闭合曲线，根据重合度判断规则判断两个标注曲线的闭合区域是否重合得到是否一致的验证结果；若两个标注曲线分别为闭合曲线及非闭合曲线，根据占比阈值判断两个标注曲线对应的像素是否重叠得到是否一致的验证结果。通过上述方法，可采用统一标准对病灶标注的一致性进行验证，可大幅提高对病灶标注进行验证的效率及质量。The lesion labeling verification device provided by the embodiment of the present application applies the above-mentioned lesion labeling verification method, acquires two lesion labels of any image in the medical image data as the label information to be verified, and determines whether the type information of the two lesion labels is not. If they are the same, judge whether the marked curves in the two lesion markings are non-closed curves; if both marked curves are non-closed curves, judge whether the two marked curves are similar according to the curve judgment rule based on the dynamic time warping algorithm. Whether the verification results are consistent; if the two marked curves are closed curves, determine whether the closed areas of the two marked curves overlap to obtain the same verification result according to the coincidence judgment rule; if the two marked curves are closed curves and non-closed curves respectively According to the proportion threshold, it is judged whether the pixels corresponding to the two marked curves overlap to obtain the same verification result. Through the above method, a unified standard can be used to verify the consistency of lesion annotation, which can greatly improve the efficiency and quality of lesion annotation verification.

上述病灶标注的验证装置可以实现为计算机程序的形式，该计算机程序可以在如图10所示的计算机设备上运行。The above-mentioned verification device for lesion marking can be implemented in the form of a computer program, and the computer program can be executed on the computer device as shown in FIG. 10 .

请参阅图10，图10是本申请实施例提供的计算机设备的示意性框图。该计算机设备可以是用于执行病灶标注的验证方法以对病灶标注的一致性进行验证的管理服务器。Please refer to FIG. 10. FIG. 10 is a schematic block diagram of a computer device provided by an embodiment of the present application. The computer device may be a management server for performing the verification method of the lesion annotation to verify the consistency of the lesion annotation.

参阅图10，该计算机设备500包括通过系统总线501连接的处理器502、存储器和网络接口505，其中，存储器可以包括非易失性存储介质503和内存储器504。Referring to FIG. 10 , thecomputer device 500 includes aprocessor 502 , a memory and anetwork interface 505 connected by asystem bus 501 , wherein the memory may include anon-volatile storage medium 503 and aninternal memory 504 .

该非易失性存储介质503可存储操作系统5031和计算机程序5032。该计算机程序5032被执行时，可使得处理器502执行病灶标注的验证方法。Thenonvolatile storage medium 503 can store anoperating system 5031 and acomputer program 5032 . When executed, thecomputer program 5032 can cause theprocessor 502 to execute the verification method of the lesion annotation.

该处理器502用于提供计算和控制能力，支撑整个计算机设备500的运行。Theprocessor 502 is used to provide computing and control capabilities to support the operation of theentire computer device 500 .

该内存储器504为非易失性存储介质503中的计算机程序5032的运行提供环境，该计算机程序5032被处理器502执行时，可使得处理器502执行病灶标注的验证方法。Theinternal memory 504 provides an environment for running thecomputer program 5032 in thenon-volatile storage medium 503. When thecomputer program 5032 is executed by theprocessor 502, theprocessor 502 can execute the verification method for lesion marking.

该网络接口505用于进行网络通信，如提供数据信息的传输等。本领域技术人员可以理解，图10中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备500的限定，具体的计算机设备500可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。Thenetwork interface 505 is used for network communication, such as providing transmission of data information. Those skilled in the art can understand that the structure shown in FIG. 10 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on thecomputer device 500 to which the solution of the present application is applied. Thespecific computer device 500 may include more or fewer components than shown, or combine certain components, or have a different arrangement of components.

其中，所述处理器502用于运行存储在存储器中的计算机程序5032，以实现上述的病灶标注的验证方法中对应的功能。Wherein, theprocessor 502 is configured to run thecomputer program 5032 stored in the memory, so as to realize the corresponding functions in the above-mentioned verification method of lesion labeling.

本领域技术人员可以理解，图10中示出的计算机设备的实施例并不构成对计算机设备具体构成的限定，在其他实施例中，计算机设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。例如，在一些实施例中，计算机设备可以仅包括存储器及处理器，在这样的实施例中，存储器及处理器的结构及功能与图10所示实施例一致，在此不再赘述。Those skilled in the art can understand that the embodiment of the computer device shown in FIG. 10 does not constitute a limitation on the specific structure of the computer device. Either some components are combined, or different component arrangements. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structures and functions of the memory and the processor are the same as those of the embodiment shown in FIG. 10 , which will not be repeated here.

应当理解，在本申请实施例中，处理器502可以是中央处理单元(Central Processing Unit，CPU)，该处理器502还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑 器件、分立硬件组件等。其中，通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。It should be understood that, in this embodiment of the present application, theprocessor 502 may be a central processing unit (Central Processing Unit, CPU), and theprocessor 502 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Wherein, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like.

在本申请的另一实施例中提供计算机可读存储介质。该计算机可读存储介质可以为非易失性的计算机可读存储介质。该计算机可读存储介质存储有计算机程序，其中计算机程序被处理器执行时实现上述的病灶标注的验证方法中所包含的步骤。In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by the processor, the steps included in the above-mentioned verification method for lesion marking are implemented.

所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的设备、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the above-described devices, devices and units, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. Interchangeability, the above description has generally described the components and steps of each example in terms of function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

在本申请所提供的几个实施例中，应该理解到，所揭露的设备、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为逻辑功能划分，实际实现时可以有另外的划分方式，也可以将具有相同功能的单元集合成一个单元，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接，也可以是电的，机械的或其它的形式连接。In the several embodiments provided in this application, it should be understood that the disclosed apparatus, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only logical function division. In actual implementation, there may be other division methods, or units with the same function may be grouped into one Units, such as multiple units or components, may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may also be electrical, mechanical or other forms of connection.

所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本申请实施例方案的目的。The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solutions of the embodiments of the present application.

另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以是两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分，或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个计算机可读存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的计算机可读存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、磁碟或者光盘等各种可以存储程序代码的介质。The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application are essentially or part of contributions to the prior art, or all or part of the technical solutions can be embodied in the form of software products, and the computer software products are stored in a computer that can The read storage medium includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned computer-readable storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), magnetic disk or optical disk and other media that can store program codes.

以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalents within the technical scope disclosed in the present application. Modifications or substitutions shall be covered by the protection scope of this application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (20)

Translated fromChinese

一种病灶标注的验证方法，应用于管理服务器中，所述管理服务器与多台用户终端进行通信，其中，所述方法包括：A verification method for lesion labeling, which is applied in a management server, wherein the management server communicates with multiple user terminals, wherein the method includes:接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息；Receive the medical image data to which the lesion label has been added from the user terminal, and obtain two lesion labels of any image in the medical image data as the label information to be verified;判断所述待验证标注信息中的两个所述病灶标注的类型信息是否相同；Determine whether the type information of the two lesion annotations in the to-be-verified annotation information is the same;若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果；If the type information of the two lesion annotations is the same, determine whether the marked curves in the two lesion annotations are closed curves to obtain a curve type determination result;若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则；If the marked curves in the two lesion markings are both non-closed curves, according to the preset curve judgment rule, it is judged whether the two marked curves are similar to obtain the verification result of whether the marked information to be verified is consistent, and the curve The judgment rule is a judgment rule based on the dynamic time warping algorithm;若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果；If the marked curves in the two lesion markings are closed curves, determine whether the closed areas corresponding to the two marked curves overlap according to the preset coincidence degree judgment rule, so as to obtain the verification of whether the marked information to be verified is consistent result;若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结果。If the annotation curves in the two lesion annotations are closed curves and non-closed curves respectively, it is determined whether the pixels corresponding to the two annotation curves overlap according to the preset proportion threshold, so as to obtain whether the annotation information to be verified is consistent verification result.根据权利要求1所述的病灶标注的验证方法，其中，所述接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息之前，还包括：The method for verifying lesion labeling according to claim 1, wherein the receiving medical image data to which the lesion labeling has been added from the user terminal, acquires two lesion labels for any image in the medical image data Before being used as the annotation information to be verified, it also includes:发送未添加病灶标注的所述医疗影像资料至多台所述用户终端，以获取对应的多个用户通过多台所述用户终端添加的病灶标注，得到所述已添加病灶标注的医疗影像资料。Sending the medical image data without the lesion labeling added to multiple user terminals to obtain the lesion labeling added by the corresponding multiple users through the multiple user terminals, and obtaining the medical image data with the lesion labeling added.根据权利要求1所述的病灶标注的验证方法，其中，所述判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果，包括：The verification method for lesion marking according to claim 1, wherein the determining whether the marked curves in the two lesion markings are closed curves to obtain a curve type judgment result comprises:根据一条所述标注曲线中位置点的采集时间确定所述标注曲线的起点和终点；Determine the starting point and the end point of the marking curve according to the collection time of the position point in one of the marking curves;判断所述起点和所述终点的距离差是否小于预设的距离阈值，以得到所述标注曲线是否为闭合曲线的判断结果。It is judged whether the distance difference between the starting point and the ending point is less than a preset distance threshold, so as to obtain a judgment result of whether the marked curve is a closed curve.根据权利要求1所述的病灶标注的验证方法，其中，所述曲线判断规则包括路径相似度阈值、跨度阈值、偏移阈值、动态时间规整算法、跨度获取规则、偏移距离获取规则、相似度计算公式及相似度阈值，所述根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，包括：The verification method for lesion labeling according to claim 1, wherein the curve judgment rules include path similarity threshold, span threshold, offset threshold, dynamic time warping algorithm, span acquisition rule, offset distance acquisition rule, similarity The calculation formula and the similarity threshold, and the determination of whether the two marked curves are similar according to the preset curve judgment rule to obtain the verification result of whether the marked information to be verified is consistent, including:根据所述跨度获取规则获取两个所述标注曲线的跨度差，判断所述跨度差是否不大于所述跨度阈值；Obtain the span difference between the two marked curves according to the span acquisition rule, and determine whether the span difference is not greater than the span threshold;若所述跨度差不大于所述跨度阈值，根据所述偏移距离获取规则获取两个所述标注曲线的偏移距离，判断所述偏移距离是否大于所述偏移阈值；If the span difference is not greater than the span threshold, obtain the offset distances of the two labeled curves according to the offset distance acquisition rule, and determine whether the offset distance is greater than the offset threshold;若所述偏移距离大于所述偏移阈值，根据所述动态时间规整算法获取两个所述标注曲线的路径相似度，判断所述路径相似度是否大于所述路径相似度阈值；If the offset distance is greater than the offset threshold, obtain the path similarity of the two labeled curves according to the dynamic time warping algorithm, and determine whether the path similarity is greater than the path similarity threshold;若所述路径相似度不小于所述路径相似度阈值，根据所述相似度计算公式、所述跨度差、所述路径相似度及所述偏移距离计算得到相似度，判断所述相似度是否大于所述相似度阈值 以得到所述待验证标注信息的验证结果为一致。If the path similarity is not less than the path similarity threshold, calculate the similarity according to the similarity calculation formula, the span difference, the path similarity and the offset distance, and determine whether the similarity is If the similarity threshold is greater than the similarity threshold, the verification result of the annotation information to be verified is consistent.根据权利要求4所述的病灶标注的验证方法，其中，所述偏移距离根据公式f_rd＝δ_dF/min(L_A，L_B)计算得到；min(L_A，L_B)为两个所述标注曲线的欧氏距离的最小值，δ_dF为两个所述标注曲线的弗雷歇距离。The verification method for lesion labeling according to claim₄ , wherein the offset distance is calculated according to the formula f_rd= δ_dF /min(LA ,_LB ); min(LA ,_LB ) is two The minimum value of the Euclidean distance of the marked curves, δ_dF is the Frechet distance of the two marked curves.根据权利要求4所述的病灶标注的验证方法，其中，所述根据所述偏移距离获取规则获取两个所述标注曲线的偏移距离之前，还包括：对两个所述标注曲线所包含的位置点的数量是否相等进行判断，若位置点的数量不相等，对较短的一个所述标注曲线进行均匀填充以使两个所述标注曲线所包含的位置点的数量相等。The method for verifying lesion labeling according to claim 4, wherein, before obtaining the offset distances of the two labeling curves according to the offset distance obtaining rule, the method further comprises: comparing the data included in the two labeling curves It is judged whether the number of the position points is equal. If the number of the position points is not equal, the shorter one of the labeling curves is evenly filled to make the number of the position points included in the two labeling curves equal.根据权利要求4所述的病灶标注的验证方法，其中，所述根据所述动态时间规整算法获取两个所述标注曲线的路径相似度，根据公式Ds＝1-D(i,j)/D’(i,j)计算得到，其中，Ds为计算得到的路径相似度，D(i,j)为两条曲线之间的最短规整距离，D’(i,j)为两条曲线之间的最长规整距离。The verification method for lesion labeling according to claim 4, wherein the path similarity of the two labeling curves is obtained according to the dynamic time warping algorithm, and the path similarity is obtained according to the formula Ds=1-D(i,j)/D '(i,j) is calculated, where Ds is the calculated path similarity, D(i,j) is the shortest regular distance between the two curves, and D'(i,j) is the distance between the two curves The longest regular distance of .根据权利要求4所述的病灶标注的验证方法，其中，所述跨度阈值包括横向跨度阈值及纵向跨度阈值，所述根据所述跨度获取规则获取两个所述标注曲线的跨度差，判断所述跨度差是否不大于所述跨度阈值，包括：The verification method for lesion labeling according to claim 4, wherein the span threshold includes a horizontal span threshold and a vertical span threshold, and the span difference between the two labeled curves is obtained according to the span acquisition rule, and the judgment of the Whether the span difference is not greater than the span threshold, including:根据所述跨度获取规则分别获取两个所述标注曲线的横向跨度差及纵向跨度差；According to the span acquisition rule, the horizontal span difference and the vertical span difference of the two marked curves are obtained respectively;判断所述横向跨度差是否不大于横向跨度阈值且所述纵向跨度差是否不大于所述纵向跨度阈值，以得到所述跨度差是否不大于所述跨度阈值的判断结果。It is judged whether the horizontal span difference is not greater than the horizontal span threshold and whether the vertical span difference is not greater than the vertical span threshold to obtain a judgment result of whether the span difference is not greater than the span threshold.根据权利要求4所述的病灶标注的验证方法，其中，所述根据所述动态时间规整算法获取两个所述标注曲线的路径相似度之前，还包括：The verification method for lesion labeling according to claim 4, wherein before the obtaining the path similarity of the two labeling curves according to the dynamic time warping algorithm, the method further comprises:根据每一所述标注曲线的时间轴获取与每一所述标注曲线对应的时间序列并判断两个所述时间序列是否统一；Acquire a time series corresponding to each of the labeled curves according to the time axis of each of the labeled curves, and determine whether the two time series are unified;若两个所述时间序列不统一，对两个所述标注曲线进行调整以使两个所述标注曲线的时间序列统一。If the two time series are not unified, the two labeling curves are adjusted so that the time series of the two labeling curves are unified.根据权利要求1所述的病灶标注的验证方法，其中，所述重合度判断规则包括重合度计算公式及重合度阈值，所述根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果，包括：The verification method for lesion labeling according to claim 1, wherein the coincidence degree judgment rule comprises a coincidence degree calculation formula and a coincidence degree threshold value, and the coincidence degree judgment rule is used to judge the corresponding coincidence degree of the two marked curves according to the preset coincidence degree judgment rule. Whether the closed areas overlap, so as to obtain the verification result of whether the label information to be verified is consistent, including:对两个所述标注曲线对应的闭合区域进行像素填充以得到对应的两个像素图像；Filling the closed regions corresponding to the two marked curves with pixels to obtain two corresponding pixel images;根据重合度计算公式及两个所述像素图像之间的重叠像素及两个所述像素图像分别对应的有效像素计算得到对应的重合度；The corresponding degree of coincidence is calculated according to the calculation formula of the degree of coincidence, the overlapping pixels between the two pixel images and the effective pixels corresponding to the two pixel images respectively;判断所述重合度是否不小于所述重合度阈值以得到两个所述标注曲线对应的闭合区域是否重合以得到所述待验证标注信息的验证结果为一致。It is determined whether the coincidence degree is not less than the coincidence degree threshold to obtain whether the closed regions corresponding to the two labeling curves are coincident, and the verification result of the labeling information to be verified is consistent.一种病灶标注的验证装置，包括：A verification device for lesion labeling, comprising:待验证标注信息获取单元，用于接收来自用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息；A to-be-verified annotation information acquisition unit, configured to receive the medical image data to which the lesion annotation has been added from the user terminal, and to acquire two lesion annotations of any image in the medical image data as the to-be-verified annotation information;类型信息判断单元，用于判断所述待验证标注信息中的两个所述病灶标注的类型信息是否相同；a type information judging unit, configured to judge whether the type information of the two lesion annotations in the to-be-verified annotation information is the same;曲线类型判断单元，用于若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果；a curve type determination unit, configured to determine whether the marked curve in the two lesion annotations is a closed curve if the type information of the two lesion annotations is the same, so as to obtain a curve type determination result;第一验证单元，用于若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则；A first verification unit, configured to determine whether the two marked curves are similar according to a preset curve judgment rule if the marked curves in the two lesion markings are both non-closed curves, so as to obtain whether the marked information to be verified is consistent The verification result, the curve judgment rule is a judgment rule based on the dynamic time warping algorithm;第二验证单元，用于若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果；The second verification unit is configured to, if the marked curves in the two lesion markings are closed curves, determine whether the closed areas corresponding to the two marked curves overlap according to a preset coincidence degree judgment rule, so as to obtain the Verify that the annotation information is consistent with the verification result;第三验证单元，用于若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结果。The third verification unit is configured to determine whether the pixels corresponding to the two annotation curves overlap according to the preset proportion threshold if the annotation curves in the two lesion annotations are closed curves and non-closed curves respectively, so as to obtain the obtained Describe the verification result of whether the annotation information to be verified is consistent.一种计算机设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现以下步骤：A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息；Receive the medical image data to which the lesion label has been added from the user terminal, and obtain two lesion labels of any image in the medical image data as the label information to be verified;判断所述待验证标注信息中的两个所述病灶标注的类型信息是否相同；Determine whether the type information of the two lesion annotations in the to-be-verified annotation information is the same;若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果；If the type information of the two lesion annotations is the same, determine whether the marked curves in the two lesion annotations are closed curves to obtain a curve type determination result;若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则；If the marked curves in the two lesion markings are both non-closed curves, according to the preset curve judgment rule, it is judged whether the two marked curves are similar to obtain the verification result of whether the marked information to be verified is consistent, and the curve The judgment rule is a judgment rule based on the dynamic time warping algorithm;若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果；If the marked curves in the two lesion markings are closed curves, determine whether the closed areas corresponding to the two marked curves overlap according to the preset coincidence degree judgment rule, so as to obtain the verification of whether the marked information to be verified is consistent result;若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结果。If the annotation curves in the two lesion annotations are closed curves and non-closed curves respectively, it is determined whether the pixels corresponding to the two annotation curves overlap according to the preset proportion threshold, so as to obtain whether the annotation information to be verified is consistent verification result.根据权利要求12所述的计算机设备，其中，所述接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息之前，还包括：The computer device according to claim 12, wherein the receiving medical image data from the user terminal to which the lesion label has been added, and acquiring two lesion labels of any image in the medical image data as to-be-verified Before labeling the information, it also includes:发送未添加病灶标注的所述医疗影像资料至多台所述用户终端，以获取对应的多个用户通过多台所述用户终端添加的病灶标注，得到所述已添加病灶标注的医疗影像资料。Sending the medical image data without the lesion labeling added to multiple user terminals to obtain the lesion labeling added by the corresponding multiple users through the multiple user terminals, and obtaining the medical image data with the lesion labeling added.根据权利要求12所述的计算机设备，其中，所述判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果，包括：The computer device according to claim 12, wherein the judging whether the marked curves in the two lesion markings are closed curves to obtain a curve type judgment result comprises:根据一条所述标注曲线中位置点的采集时间确定所述标注曲线的起点和终点；Determine the starting point and the end point of the marking curve according to the collection time of the position point in one of the marking curves;判断所述起点和所述终点的距离差是否小于预设的距离阈值，以得到所述标注曲线是否为闭合曲线的判断结果。It is judged whether the distance difference between the starting point and the ending point is less than a preset distance threshold, so as to obtain a judgment result of whether the marked curve is a closed curve.根据权利要求12所述的计算机设备，其中，所述曲线判断规则包括路径相似度阈值、跨度阈值、偏移阈值、动态时间规整算法、跨度获取规则、偏移距离获取规则、相似度计算公式及相似度阈值，所述根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，包括：The computer device according to claim 12, wherein the curve judgment rules include path similarity threshold, span threshold, offset threshold, dynamic time warping algorithm, span acquisition rule, offset distance acquisition rule, similarity calculation formula and Similarity threshold, according to the preset curve judging rule to determine whether the two marked curves are similar to obtain the verification result of whether the marked information to be verified is consistent, including:根据所述跨度获取规则获取两个所述标注曲线的跨度差，判断所述跨度差是否不大于所 述跨度阈值；Obtain the span difference of two described marked curves according to the span acquisition rule, and judge whether the span difference is not greater than the span threshold;若所述跨度差不大于所述跨度阈值，根据所述偏移距离获取规则获取两个所述标注曲线的偏移距离，判断所述偏移距离是否大于所述偏移阈值；If the span difference is not greater than the span threshold, obtain the offset distances of the two labeled curves according to the offset distance acquisition rule, and determine whether the offset distance is greater than the offset threshold;若所述偏移距离大于所述偏移阈值，根据所述动态时间规整算法获取两个所述标注曲线的路径相似度，判断所述路径相似度是否大于所述路径相似度阈值；If the offset distance is greater than the offset threshold, obtain the path similarity of the two labeled curves according to the dynamic time warping algorithm, and determine whether the path similarity is greater than the path similarity threshold;若所述路径相似度不小于所述路径相似度阈值，根据所述相似度计算公式、所述跨度差、所述路径相似度及所述偏移距离计算得到相似度，判断所述相似度是否大于所述相似度阈值以得到所述待验证标注信息的验证结果为一致。If the path similarity is not less than the path similarity threshold, calculate the similarity according to the similarity calculation formula, the span difference, the path similarity and the offset distance, and determine whether the similarity is If the similarity threshold is greater than the similarity threshold, the verification result of the annotation information to be verified is consistent.根据权利要求15所述的计算机设备，其中，所述偏移距离根据公式f_rd＝δ_dF/min(L_A，L_B)计算得到；min(L_A，L_B)为两个所述标注曲线的欧氏距离的最小值，δ_dF为两个所述标注曲线的弗雷歇距离。The computer device according to claim 15, wherein the offset distance is calculated according to the formula f_rd= δ_dF /min(LA ,_LB ); min(LA ,_LB) is two of the labels The minimum value of the Euclidean distance of the curve, δ_dF is the Frechet distance of the two labeled curves.根据权利要求15所述的计算机设备，其中，所述根据所述偏移距离获取规则获取两个所述标注曲线的偏移距离之前，还包括：对两个所述标注曲线所包含的位置点的数量是否相等进行判断，若位置点的数量不相等，对较短的一个所述标注曲线进行均匀填充以使两个所述标注曲线所包含的位置点的数量相等。The computer device according to claim 15, wherein before acquiring the offset distances of the two annotation curves according to the offset distance acquisition rule, the method further comprises: determining the position points included in the two annotation curves. It is judged whether the number of points is equal, and if the number of position points is not equal, uniformly fill the shorter one of the labeling curves to make the number of the location points included in the two labeling curves equal.根据权利要求15所述的计算机设备，其中，所述根据所述动态时间规整算法获取两个所述标注曲线的路径相似度，根据公式Ds＝1-D(i,j)/D’(i,j)计算得到，其中，Ds为计算得到的路径相似度，D(i,j)为两条曲线之间的最短规整距离，D’(i,j)为两条曲线之间的最长规整距离。The computer device according to claim 15, wherein, according to the dynamic time warping algorithm, the path similarity of the two labeled curves is obtained, according to the formula Ds=1-D(i,j)/D'(i ,j) calculated, where Ds is the calculated path similarity, D(i,j) is the shortest regular distance between the two curves, D'(i,j) is the longest distance between the two curves Regular distance.根据权利要求15所述的计算机设备，其中，所述跨度阈值包括横向跨度阈值及纵向跨度阈值，所述根据所述跨度获取规则获取两个所述标注曲线的跨度差，判断所述跨度差是否不大于所述跨度阈值，包括：The computer device according to claim 15, wherein the span threshold includes a horizontal span threshold and a vertical span threshold, the span difference between the two labeled curves is obtained according to the span acquisition rule, and it is determined whether the span difference is not greater than the span threshold, including:根据所述跨度获取规则分别获取两个所述标注曲线的横向跨度差及纵向跨度差；According to the span acquisition rule, the horizontal span difference and the vertical span difference of the two marked curves are obtained respectively;判断所述横向跨度差是否不大于横向跨度阈值且所述纵向跨度差是否不大于所述纵向跨度阈值，以得到所述跨度差是否不大于所述跨度阈值的判断结果。It is judged whether the horizontal span difference is not greater than the horizontal span threshold and whether the vertical span difference is not greater than the vertical span threshold to obtain a judgment result of whether the span difference is not greater than the span threshold.一种计算机可读存储介质，其中，所述计算机可读存储介质存储有计算机程序，所述计算机程序当被处理器执行时使所述处理器执行以下操作：A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the following operations:接收来自所述用户终端的已添加病灶标注的医疗影像资料，获取所述医疗影像资料中的任意一张图像的两个病灶标注作为待验证标注信息；Receive the medical image data to which the lesion label has been added from the user terminal, and obtain two lesion labels of any image in the medical image data as the label information to be verified;判断所述待验证标注信息中的两个所述病灶标注的类型信息是否相同；Determine whether the type information of the two lesion annotations in the to-be-verified annotation information is the same;若两个所述病灶标注的类型信息相同，判断两个所述病灶标注中的标注曲线是否为闭合曲线以得到曲线类型判断结果；If the type information of the two lesion annotations is the same, determine whether the marked curves in the two lesion annotations are closed curves to obtain a curve type determination result;若两个所述病灶标注中的标注曲线均为非闭合曲线，根据预置的曲线判断规则判断两个所述标注曲线是否相似以得到所述待验证标注信息是否一致的验证结果，所述曲线判断规则为基于动态时间规整算法的判断规则；If the marked curves in the two lesion markings are both non-closed curves, according to the preset curve judgment rule, it is judged whether the two marked curves are similar to obtain the verification result of whether the marked information to be verified is consistent, and the curve The judgment rule is a judgment rule based on the dynamic time warping algorithm;若两个所述病灶标注中的标注曲线均为闭合曲线，根据预置的重合度判断规则判断两个所述标注曲线对应的闭合区域是否重合，以得到所述待验证标注信息是否一致的验证结果；If the marked curves in the two lesion markings are closed curves, determine whether the closed areas corresponding to the two marked curves overlap according to the preset coincidence degree judgment rule, so as to obtain the verification of whether the marked information to be verified is consistent result;若两个所述病灶标注中的标注曲线分别为闭合曲线及非闭合曲线，根据预置的占比阈值判断两个所述标注曲线对应的像素是否重叠，以得到所述待验证标注信息是否一致的验证结 果。If the annotation curves in the two lesion annotations are closed curves and non-closed curves respectively, it is determined whether the pixels corresponding to the two annotation curves overlap according to the preset proportion threshold, so as to obtain whether the annotation information to be verified is consistent verification result.

Images