CN114693571A - Medical scanning imaging method, device and system - Google Patents
Medical scanning imaging method, device and systemDownload PDFInfo
- Publication number
- CN114693571A CN114693571ACN202011636907.9ACN202011636907ACN114693571ACN 114693571 ACN114693571 ACN 114693571ACN 202011636907 ACN202011636907 ACN 202011636907ACN 114693571 ACN114693571 ACN 114693571A
- Authority
- CN
- China
- Prior art keywords
- scanning
- medical
- frame
- initial
- imaging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及医学影像扫描技术领域，尤其涉及一种医学扫描成像方法、装置及系统。The invention relates to the technical field of medical image scanning, in particular to a medical scanning imaging method, device and system.
背景技术Background technique
DICOM(Digital Imaging and Communications in Medicine)即医学数字成像和通信，是医学影像和相关信息的国际标准(ISO 12052)。它定义了质量能满足临床需要的可用于数据交换的医学影像格式。DICOM被广泛应用于放射医疗，心血管成像以及放射诊疗诊断设备(X射线，CT，MR，超声等)，并且在眼科和牙科等其它医学领域得到越来越深入广泛的应用。在数以万计的在用医学成像设备中，DICOM是部署最为广泛的医疗信息标准之一。当前大约有百亿级符合DICOM标准的医学影像用于临床使用。DICOM (Digital Imaging and Communications in Medicine) is an international standard for medical imaging and related information (ISO 12052). It defines a medical image format that can be used for data exchange with a quality that meets clinical needs. DICOM is widely used in radiology, cardiovascular imaging and radiology diagnostic equipment (X-ray, CT, MR, ultrasound, etc.), and has been more and more widely used in other medical fields such as ophthalmology and dentistry. With tens of thousands of medical imaging devices in use, DICOM is one of the most widely deployed medical information standards. Currently, there are about 10 billion DICOM-compliant medical images for clinical use.
在现有的医院现状中，DICOM扫描形成的生理结构图一般用于定位各个生理位置和确定病变情况，为影像摆位提供指导。DICOM数据一般为后处理数据，经过采集和重建后生成的2D或者3D矩阵。In the current hospital situation, the physiological structure map formed by DICOM scanning is generally used to locate each physiological position and determine the lesion condition, and provide guidance for image placement. DICOM data is generally post-processing data, a 2D or 3D matrix generated after acquisition and reconstruction.
操作者指导扫描对象摆位旨在获得更加有效的重建数据，例如对身体全方位扫描和病变位置更精准的定位等，但是目前医院对摆位指导参考的标准一般仅限于视频影像指导或者AI智能定位，个体差异影响因素无法消除。The operator guides the positioning of the scanned object to obtain more effective reconstruction data, such as omnidirectional scanning of the body and more accurate positioning of the lesion position. Positioning, the influencing factors of individual differences cannot be eliminated.
发明内容SUMMARY OF THE INVENTION
有鉴于此，有必要提供一种医学扫描成像方法、装置及系统，用以解决目前医学扫描无法准确定位扫描对象的目标扫描位置，依赖于扫描对象的准确摆位，无法消除个体差异影响的问题。In view of this, it is necessary to provide a medical scanning imaging method, device and system to solve the problem that the current medical scanning cannot accurately locate the target scanning position of the scanning object, and cannot eliminate the influence of individual differences depending on the accurate positioning of the scanning object. .
本发明一个实施例提供一种医学扫描成像方法，包括：An embodiment of the present invention provides a medical scanning imaging method, including:
基于初始扫描框获取扫描对象的初始医学影像；Obtain the initial medical image of the scanned object based on the initial scan frame;
获取扫描对象的可见光图像；Obtain a visible light image of the scanned object;
对所述可见光图像以及所述初始医学影像进行融合，得到定位指导图；Fusion of the visible light image and the initial medical image to obtain a positioning guide map;
基于所述定位指导图对所述初始扫描框进行调整，得到成像扫描框；Adjusting the initial scan frame based on the positioning guide map to obtain an imaging scan frame;
基于所述成像扫描框对扫描对象进行医学影像扫描。A medical image scan is performed on the scanned object based on the imaging scan frame.
本方法另一实施例中，所述方法还包括：设置初始扫描框；In another embodiment of the method, the method further includes: setting an initial scan frame;
所述设置扫描框包括：The setting scan frame includes:
设置不同种类动物的扫描框样本，建立扫描框数据库；Set up scan frame samples of different types of animals and establish a scan frame database;
获取扫描对象的种类，从所述扫描框数据库中选择与扫描对象相应的扫描框样本，得到所述初始扫描框。The type of the scanning object is acquired, and a scanning frame sample corresponding to the scanning object is selected from the scanning frame database to obtain the initial scanning frame.
本方法另一实施例中，所述设置不同种类动物的扫描框样本包括：In another embodiment of the method, the setting of scan frame samples of different types of animals includes:
根据动物种类设置扫描框的中心点以及扫描框的尺寸；Set the center point of the scan frame and the size of the scan frame according to the animal species;
在所述扫描框内针对多个扫描目标划分多个子框，并设置多个子框之间的相对位置关系，得到所述扫描框样本。In the scanning frame, a plurality of subframes are divided for a plurality of scanning targets, and relative positional relationships between the plurality of subframes are set to obtain the scanning frame samples.
本方法另一实施例中，所述获取扫描对象的种类包括：In another embodiment of the method, the acquiring the type of the scanned object includes:
根据可见光图像识别所述扫描对象的种类。Identify the type of the scanned object according to the visible light image.
本方法另一实施例中，所述获取扫描对象的可见光图像包括：In another embodiment of the method, the acquiring the visible light image of the scanned object includes:
获取扫描对象的视频流，获取所述视频流中与所述初始医学影像的扫描时刻相对应的帧作为所述可见光图像。A video stream of the scanned object is acquired, and a frame corresponding to the scanning moment of the initial medical image in the video stream is acquired as the visible light image.
本方法另一实施例中，所述对所述可见光图像以及所述初始医学影像进行融合，得到定位指导图包括：In another embodiment of the method, the fusion of the visible light image and the initial medical image to obtain a positioning guide map includes:
分别获取所述可见光图像和所述初始医学影像的特征点；respectively acquiring the feature points of the visible light image and the initial medical image;
基于所述特征点对所述可见光图像和所述初始医学影像进行点云配准，得到所述可见光图像与所述初始医学影像之间的旋转角和平移量；Perform point cloud registration on the visible light image and the initial medical image based on the feature points to obtain the rotation angle and translation between the visible light image and the initial medical image;
基于所述旋转角和平移量对所述可见光图像和初始医学影像的相对位置进行调整；adjusting the relative position of the visible light image and the initial medical image based on the rotation angle and the translation amount;
对所述可见光图像和初始医学影像进行像素叠加，得到所述定位指导图。Pixels are superimposed on the visible light image and the initial medical image to obtain the positioning guide map.
本方法另一实施例中，所述基于所述定位指导图对所述初始扫描框进行调整，得到成像扫描框包括：In another embodiment of the method, the adjusting the initial scan frame based on the positioning guide map to obtain the imaging scan frame includes:
根据所述定位指导图中初始医学影像部分设置目标扫描框；Set the target scan frame according to the initial medical image part in the positioning guide;
计算所述目标扫描框与所述初始扫描框的偏差值；Calculate the deviation value of the target scan frame and the initial scan frame;
基于所述偏差值对所述初始扫描框进行调整，得到所述目标扫描框。The initial scan frame is adjusted based on the deviation value to obtain the target scan frame.
本方法另一实施例中，基于所述成像扫描框对扫描对象进行医学影像扫描之前，还包括：In another embodiment of the method, before performing medical image scanning on the scanning object based on the imaging scanning frame, the method further includes:
在所述扫描对象上标记所述成像扫描框，获取包含成像扫描框标记的可见光标记图像；marking the imaging scan frame on the scanning object, and obtaining a visible light marked image containing the imaging scan frame mark;
通过对比所述可见光标记图像与所述定位指导图判断扫描对象是否发生移动，如果发生移动，则重新进行成像扫描框的确定，否则以当前成像扫描框对扫描对象进行医学影像的扫描。Determine whether the scanning object moves by comparing the visible light marker image with the positioning guide map. If there is movement, the imaging scan frame is re-determined. Otherwise, the scan object is scanned for medical images with the current imaging scan frame.
本发明另一实施例还提供一种医学扫描成像装置，包括处理器以及存储器，所述存储器上存储有计算机程序，所述计算机程序被所述处理器执行时，实现所述医学扫描成像方法。Another embodiment of the present invention further provides a medical scanning and imaging apparatus, including a processor and a memory, where a computer program is stored in the memory, and when the computer program is executed by the processor, the medical scanning and imaging method is implemented.
本发明另一实施例还提供一种医学扫描成像系统，包括所述医学扫描成像装置，还包括医学影像装置以及可见光图像获取装置；Another embodiment of the present invention further provides a medical scanning imaging system, including the medical scanning imaging device, a medical imaging device and a visible light image acquiring device;
所述医学影像装置用于基于初始扫描框对扫描对象进行扫描得到初始医学影像，并将所述初始医学影像发送至所述医学扫描成像装置；The medical imaging device is configured to scan the scanning object based on the initial scanning frame to obtain an initial medical image, and send the initial medical image to the medical scanning imaging device;
所述可见光图像获取装置用于采集扫描对象的可见光图像，并将所述可见光图像发送至所述医学扫描成像装置；The visible light image acquisition device is configured to collect a visible light image of the scanned object, and send the visible light image to the medical scanning imaging device;
所述医学扫描成像装置用于基于所述初始医学影像以及所述可见光图像，采用所述医学扫描成像方法，获取所述成像扫描框，并将所述成像扫描框发送至所述医学影像装置；The medical scanning and imaging device is configured to, based on the initial medical image and the visible light image, adopt the medical scanning and imaging method to acquire the imaging scan frame, and send the imaging scan frame to the medical imaging device;
所述医学影像装置用于基于所述成像扫描框对扫描对象进行医学影像扫描。The medical imaging device is configured to perform medical image scanning on the scanning object based on the imaging scanning frame.
有益效果：本发明首先基于初始扫描框获取扫描对象的初始医学影像，与此同时获取扫描对象的可见光图像，这两张图像分别描述了扫描对象的内部生理结构和可视化的外部身体结构。为了在扫描对象的外部身体上准确标注包括扫描目标的临床扫描范围，将能够描述内部生理结构的医学影像融合至可见光图像中，从而实现了扫描对象内部生理结构与外部身体结构相对位置关系的可视化，在内部生理结构可视化的前提下，进行初始扫描框的调整，得到成像扫描框，从而保证了成像扫描框中可以准确包含扫描目标。最后基于成像扫描框进行医学影像的扫描，即可保证扫描的精准度。本发明实现了成像扫描框的自动调整定位，避免了扫描过程中凭借经验对扫描对象进行摆位的过程，解除了扫描效果对与人为摆位准确性的依赖。同时，扫描范围可以自动调整，消除了凭借经验进行摆位扫描时存在的个体差异，针对特定的扫描对象设置相应的成像扫描框，得到最为适合和准确的扫描效果。Beneficial effects: the present invention first obtains the initial medical image of the scanning object based on the initial scanning frame, and simultaneously obtains the visible light image of the scanning object. The two images describe the internal physiological structure and the visualized external body structure of the scanning object respectively. In order to accurately mark the clinical scanning range including the scanning target on the external body of the scanned object, medical images that can describe the internal physiological structure are fused into the visible light image, thereby realizing the visualization of the relative positional relationship between the internal physiological structure and the external body structure of the scanned object , Under the premise of visualizing the internal physiological structure, the initial scan frame is adjusted to obtain the imaging scan frame, thereby ensuring that the imaging scan frame can accurately contain the scanning target. Finally, scan the medical image based on the imaging scan frame to ensure the accuracy of the scan. The invention realizes the automatic adjustment and positioning of the imaging scanning frame, avoids the process of arranging the scanning object by experience in the scanning process, and relieves the dependence of the scanning effect on the accuracy of artificial positioning. At the same time, the scanning range can be automatically adjusted, which eliminates the individual differences in position scanning based on experience, and sets the corresponding imaging scanning frame for specific scanning objects to obtain the most suitable and accurate scanning effect.
附图说明Description of drawings
图1为本发明提供的医学扫描成像方法第一实施例的方法流程图；FIG. 1 is a method flowchart of a first embodiment of a medical scanning imaging method provided by the present invention;
图2为本发明提供的医学扫描成像系统第一实施例的系统架构图。FIG. 2 is a system architecture diagram of a first embodiment of a medical scanning imaging system provided by the present invention.
具体实施方式Detailed ways
下面结合附图来具体描述本发明的优选实施例，其中，附图构成本申请一部分，并与本发明的实施例一起用于阐释本发明的原理，并非用于限定本发明的范围。The preferred embodiments of the present invention are specifically described below with reference to the accompanying drawings, wherein the accompanying drawings constitute a part of the present application, and together with the embodiments of the present invention, are used to explain the principles of the present invention, but are not used to limit the scope of the present invention.
如图1所示，本发明的一实施例提供了医学扫描成像方法，以下简称本方法，包括：As shown in FIG. 1, an embodiment of the present invention provides a medical scanning imaging method, hereinafter referred to as the method, including:
S1、基于初始扫描框获取扫描对象的初始医学影像；S1. Obtain an initial medical image of the scanned object based on the initial scan frame;
S2、获取扫描对象的可见光图像；S2. Obtain a visible light image of the scanned object;
S3、对所述可见光图像以及所述初始医学影像进行融合，得到定位指导图；S3, fuse the visible light image and the initial medical image to obtain a positioning guide map;
S4、基于所述定位指导图对所述初始扫描框进行调整，得到成像扫描框；S4, adjusting the initial scan frame based on the positioning guide map to obtain an imaging scan frame;
S5、基于所述成像扫描框对扫描对象进行医学影像扫描。S5. Perform medical image scanning on the scanning object based on the imaging scanning frame.
目前，在进行医学影像扫描时，扫描对象在扫描中的位置难以确定，在现有的应用中，因为没有实时的内部生理结构定位图通过可视化的方式协助操作者确定扫描位置，更多的是依靠操作者的肉眼和直觉确定位置，这就会导致最终成像出现偏差，无法获得清晰有效的医学影像。本方法提出了一种有效的方式，来可视化地帮助操作者确定所关注的扫描目标的生理位置，同时，根据融合得到的定位指导图划定更加精确可靠的成像扫描框。At present, when scanning medical images, it is difficult to determine the position of the scanned object in the scan. In existing applications, because there is no real-time internal physiological structure localization map to assist the operator in determining the scanning position through visualization, more Relying on the operator's naked eyes and intuition to determine the position can lead to deviations in the final image, and it is impossible to obtain a clear and effective medical image. This method proposes an effective way to visually help the operator to determine the physiological position of the scanning target concerned, and at the same time, delineate a more accurate and reliable imaging scan frame according to the fusion positioning guide map.
具体的，首先基于初始扫描框获取扫描对象的初始医学影像，医学影像可以是扫描对象的CT scout图像，与此同时获取扫描对象的可见光图像，这两幅图像分别描述了扫描对象不可视的内部生理结构和可视化的外部身体结构。为了在扫描对象的外部身体上准确定位扫描目标所在的临床扫描范围，将能够描述内部生理结构的初始医学影像融合至可见光图像中，从而实现了扫描对象内部生理结构与外部身体结构相对位置关系的可视化，得到定位指导图。基于定位指导图，在内部生理结构可视化的前提下，进行初始扫描框的调整，得到成像扫描框，从而保证了成像扫描框中可以准确包含扫描目标(扫描的目标生理结构)。同时所定义的成像扫描框是在定位指导图中定义的，其相对于可见光图像的位置信息可基于与初始扫描框的偏差间接获取到，从而使得获取到的成像扫描框可以准确描述扫描范围相对于扫描对象的外部身体结构的位置信息。最后基于成像扫描框进行医学扫描得到医学影像，可保证扫描成像的精准度，不需刻意进行扫描对象的摆位。Specifically, an initial medical image of the scanned object is obtained based on the initial scan frame. The medical image may be a CT scout image of the scanned object, and at the same time, a visible light image of the scanned object is obtained. The two images respectively describe the invisible interior of the scanned object. Physiological structures and visualization of external body structures. In order to accurately locate the clinical scanning range where the scanning target is located on the external body of the scanning object, the initial medical image that can describe the internal physiological structure is fused into the visible light image, thereby realizing the relative positional relationship between the internal physiological structure and the external body structure of the scanning object. Visualization, get the positioning guide map. Based on the positioning guide map, on the premise of visualizing the internal physiological structure, the initial scan frame is adjusted to obtain the imaging scan frame, thereby ensuring that the imaging scan frame can accurately contain the scanning target (the scanned target physiological structure). At the same time, the defined imaging scan frame is defined in the positioning guide map, and its position information relative to the visible light image can be obtained indirectly based on the deviation from the initial scan frame, so that the acquired imaging scan frame can accurately describe the relative scanning range. The position information of the external body structure of the scanned object. Finally, medical scanning is performed based on the imaging scanning frame to obtain a medical image, which can ensure the accuracy of scanning and imaging, and does not need to deliberately position the scanning object.
本方法实现了成像扫描框的自动调整定位，避免了扫描过程中凭借经验对扫描对象进行摆位的过程，解除了扫描效果对于人为摆位准确性的依赖。同时，扫描范围可以自动调整，消除了凭借经验进行摆位扫描时存在的个体差异，针对特定的扫描对象设置相应的成像扫描框，在保证了成像扫描框中准确包含扫描目标的前提下，获取了成像扫描框相对于扫描对象外部身体结构的位置信息，最终得到最为适合和准确的扫描效果。The method realizes the automatic adjustment and positioning of the imaging scanning frame, avoids the process of arranging the scanning object by experience in the scanning process, and relieves the dependence of the scanning effect on the accuracy of artificial positioning. At the same time, the scanning range can be automatically adjusted, eliminating the individual differences in position scanning based on experience, setting the corresponding imaging scanning frame for specific scanning objects, and ensuring that the imaging scanning frame accurately contains the scanning target. The position information of the imaging scanning frame relative to the external body structure of the scanning object is obtained, and the most suitable and accurate scanning effect is finally obtained.
本方法的另一实施例中，所述方法还包括：设置初始扫描框。In another embodiment of the method, the method further includes: setting an initial scan frame.
所述设置初始扫描框包括：The setting initial scan frame includes:
所述扫描对象为动物，设置不同种类动物的扫描框样本，建立扫描框数据库。The scanning object is an animal, and scanning frame samples of different types of animals are set to establish a scanning frame database.
获取扫描对象的种类，从所述扫描框数据库中选择与扫描对象相应的扫描框样本，得到所述初始扫描框。The type of the scanning object is acquired, and a scanning frame sample corresponding to the scanning object is selected from the scanning frame database to obtain the initial scanning frame.
对于人来说，尤其是成年人，其体型大小、各脏器的分布以及在身体上的相对位置是大致相同的，而且是公知的医学常识，因此针对人设置初始的扫描框可以根据经验进行设置。但是对于动物来说，其种类繁多，不同种类的动物因其体型大小、脏器分布、脏器位置均有不同，如果仅仅凭借经验和常识进行设置很容易出现错误或偏差。本发明实施例在设置初始扫描框之前先建立扫描框数据库，该扫描框数据库中存储了不同种类动物的扫描框样本，在设置初始扫描框时，只需要根据动物种类在扫描数据库中选择相应的扫描框样本，再根据扫描框样本进行扫描即可，从而使得初始扫描框的设置不再依赖于经验常识，提高了初始扫描框设置的效率和精确性。For people, especially adults, their body size, the distribution of various organs and their relative positions on the body are roughly the same, and it is a well-known medical common sense, so setting the initial scan frame for people can be done based on experience. set up. But for animals, there are many kinds of them. Different kinds of animals have different body sizes, organ distribution, and organ locations. If you only rely on experience and common sense to set up, it is easy to make mistakes or deviations. In this embodiment of the present invention, before setting the initial scan frame, a scan frame database is established. The scan frame database stores the scan frame samples of different types of animals. When setting the initial scan frame, it is only necessary to select the corresponding animal type in the scan database according to the animal type. Scan the frame samples, and then scan according to the scan frame samples, so that the setting of the initial scan frame no longer depends on experience and common sense, and the efficiency and accuracy of the initial scan frame setting are improved.
本方法的另一实施例中，所述设置不同种类动物的扫描框样本包括：In another embodiment of the method, the setting of scan frame samples of different types of animals includes:
根据动物种类设置扫描框的中心点以及扫描框的尺寸；Set the center point of the scan frame and the size of the scan frame according to the animal species;
在所述扫描框内针对多个扫描目标划分多个子框，并设置多个子框之间的相对位置关系，得到所述扫描框样本。In the scanning frame, a plurality of subframes are divided for a plurality of scanning targets, and relative positional relationships between the plurality of subframes are set to obtain the scanning frame samples.
不同种类动物的体型大小、脏器位置分布、脏器大小都是不同的。通过扫描框的中心点和尺寸这两项参数来实现扫描框样本的确定，可以对不同种类动物的不同扫描目标进行准确描述。具体的，设置扫描框样本时先确定中心点，然后确定尺寸。例如，需要对兔子的心脏进行扫描时，需要确定兔子心脏的中心点作为扫描框样本的中心点，然后根据兔子心脏的大小设置扫描框样本的尺寸。扫描框样本的形状根据扫描目标进行设置，可以为矩形、圆形、椭圆形等，不同形状的扫描框样本的尺寸采用不同的参数进行描述，例如矩形采用长和宽，圆形采用半径或直径，椭圆形采用长轴和短轴。Different species of animals have different body sizes, organ locations, and organ sizes. Through the two parameters of the center point and size of the scanning frame, the sample of the scanning frame can be determined, and different scanning targets of different kinds of animals can be accurately described. Specifically, when setting the scan frame sample, first determine the center point, and then determine the size. For example, when the heart of a rabbit needs to be scanned, the center point of the rabbit heart needs to be determined as the center point of the scan frame sample, and then the size of the scan frame sample is set according to the size of the rabbit heart. The shape of the scan frame sample is set according to the scanning target, which can be rectangle, circle, ellipse, etc. The size of the scan frame sample of different shapes is described by different parameters, for example, the rectangle adopts the length and width, and the circle adopts the radius or diameter , the ellipse adopts a major axis and a minor axis.
扫描框样本的中心点和尺寸的设置依赖于坐标系的建立，设置扫描框样本时，其坐标系的建立可以基于动物身体上的特征点实现，例如基于两只眼睛、两个耳朵、鼻子等，用于建立坐标系的特征点可以根据动物自身的特点进行选择，可以选择动物身上较为突出的特征点。例如对兔子进行扫描时，可以选择它的两个耳朵为基准建立坐标系，以两个耳朵尖角的连线作为X轴，两个耳朵尖角连线的中垂线作为Y轴，建立坐标系。需要扫描兔子的心脏，则获取心脏中心点在所建立的坐标系中的位置坐标，然后根据其心脏大小设置扫描框样本的尺寸，得到兔子的扫描框样本。The setting of the center point and size of the scan frame sample depends on the establishment of the coordinate system. When setting the scan frame sample, the establishment of the coordinate system can be realized based on the feature points on the animal body, such as two eyes, two ears, nose, etc. , the feature points used to establish the coordinate system can be selected according to the characteristics of the animal itself, and the more prominent feature points on the animal can be selected. For example, when scanning a rabbit, you can choose its two ears as a reference to establish a coordinate system, use the line connecting the two ears as the X axis, and the vertical line connecting the two ears as the Y axis to establish the coordinates. Tie. To scan the rabbit's heart, obtain the position coordinates of the center point of the heart in the established coordinate system, and then set the size of the scan frame sample according to the size of the heart to obtain the rabbit's scan frame sample.
另外，如果针对扫描对象的扫描目标只有一种，例如只有心脏，那么在设置扫描框样本时，只需要设置扫描框的中心点位置和大小(即尺寸)即可。但是，在很多场景下，存在对扫描对象的多个脏器，即多个扫描目标进行同时扫描的需求，此时，仅仅设置一个扫描框的大小和位置则无法对各个脏器的位置进行精确标注。针对这一问题，在设置扫描框样本时，首先设置扫描框将所有需要扫描的扫描目标包括在内，然后在扫描框中设置各个扫描目标对应的子框，子框的设置同样包括中心点和大小两部分，参考前述扫描框的设置方式进行设置即可；同时标注多个子框之间的相对位置关系，即多个脏器(即多个扫描目标)之间的相对位置关系，便于后续扫描时对各个脏器进行精确定位，并分别针对每个脏器进行扫描。In addition, if there is only one scanning target for the scanning object, for example, only the heart, then when setting the scan frame sample, only the position and size (ie, size) of the center point of the scan frame need to be set. However, in many scenarios, there is a need to scan multiple organs of the scanning object, that is, multiple scanning targets at the same time. At this time, only setting the size and position of one scanning frame cannot accurately determine the position of each organ. callout. In response to this problem, when setting the scan frame sample, first set the scan frame to include all the scan targets to be scanned, and then set the sub-frames corresponding to each scan target in the scan frame. The settings of the sub-frames also include the center point and The size of the two parts can be set by referring to the setting method of the aforementioned scan frame; at the same time, the relative positional relationship between multiple subframes is marked, that is, the relative positional relationship between multiple organs (ie multiple scanning targets), which is convenient for subsequent scanning. At the same time, each organ is accurately positioned, and each organ is scanned separately.
具体的，针对同种类动物设置扫描框样本时，虽然同种类动物的脏器分布、脏器位置是相同的，但是同种类不同年龄阶段动物的体型大小仍有区别，其各脏器在身体上的相对位置也是不同的。针对某一种动物设置扫描框样本时，优先选择体型大小在同一设定范围内的动物样本，根据多个动物样本设置多个扫描框并取其平均值(包括中心点坐标的平均值以及大小的平均值)作为最终的扫描框样本。同时将所选取的动物样本的体型大小设定范围的中位值标注于所述扫描框样本上，在根据动物种类选择设置了相应的扫描框样本后，根据所述可见光图像获取动物的体型大小数据，根据所述体型大小数据与所述中位值的比值，对所述扫描框样本进行缩小或放大，得到最终的初始扫描框，从而使得初始扫描框能够适应于同种类不同体型大小的动物。体型大小数据可以采用头围、身长、手长、腿长、身宽等进行描述，同样是根据不同种类的动物进行选择即可，优先选取能够明显区分同种类动物不同体型大小的数据。Specifically, when setting scan frame samples for the same type of animals, although the organ distribution and organ locations of the same type of animals are the same, there are still differences in the size and size of the same type of animals at different ages, and their organs are on the body. The relative positions are also different. When setting a scan frame sample for a certain animal, the animal sample whose body size is within the same set range is preferentially selected, and multiple scan frames are set according to multiple animal samples and the average value (including the average value and size of the center point coordinates) is taken. ) as the final scan frame sample. At the same time, the median value of the body size setting range of the selected animal sample is marked on the scan frame sample. After selecting and setting the corresponding scan frame sample according to the animal type, the body size of the animal is obtained according to the visible light image. According to the ratio of the body size data to the median value, the scan frame sample is reduced or enlarged to obtain the final initial scan frame, so that the initial scan frame can be adapted to animals of the same type and different body sizes . Body size data can be described by head circumference, body length, hand length, leg length, body width, etc. It is also necessary to select according to different types of animals, and it is preferred to select data that can clearly distinguish different body sizes of animals of the same type.
本方法的另一实施例中，所述获取扫描对象的种类包括：In another embodiment of the method, the acquiring the type of the scanned object includes:
根据可见光图像识别所述扫描对象的种类。Identify the type of the scanned object according to the visible light image.
通过可见光图像实现对扫描对象的种类的自动识别，从而进一步解除了扫描过程对于人的依赖，实现扫描过程更高程度上的自动化。在一个实施例中，用于识别扫描对象的种类的可见光图像不同于用于与初始医学影像进行融合的可见光图像。在一个实施例中，用于识别扫描对象的种类的可见光图像为第一可见光图像，用于与初始医学影像进行融合的可见光图像为第二可见光图像。第一可见光图像和第二可见光图像为同一类型图像，但图像获取的时间不同。第一可见光图像在对动物种类进行识别时获得，可以为多角度拍摄的多幅照片。第二可见光图像为与初始医学影像的扫描时刻相对应的视频流的帧或者同一时刻拍摄的照片。The automatic identification of the type of the scanned object is realized through the visible light image, thereby further releasing the dependence of the scanning process on people and realizing a higher degree of automation of the scanning process. In one embodiment, the visible light image used to identify the type of object scanned is different from the visible light image used to fuse with the original medical image. In one embodiment, the visible light image used for identifying the type of the scanned object is the first visible light image, and the visible light image used for fusion with the original medical image is the second visible light image. The first visible light image and the second visible light image are images of the same type, but the images are acquired at different times. The first visible light image is obtained when the animal species is identified, and may be multiple photos taken at multiple angles. The second visible light image is a frame of the video stream corresponding to the scanning moment of the initial medical image or a photo taken at the same moment.
具体的，根据可见光图像对扫描对象的动物种类进行识别，可以采用神经网络训练的方式实现。首先，采集各类动物的样本图像，对样本图像进行特征点提取，得到特征点向量。应该注意的是，这里的样本图像应该是动物在扫描体位时的图像，与扫描体位差别较大的体位的图像可以无需获取，以减小训练难度，同时提高模型识别精度。对每一样本图像进行种类标签标注，以特征点向量作为输入，以种类标签作为输出，对神经网络进行训练，得到动物种类识别模型，通过动物种类识别模型即可实现基于可见光图像的动物种类识别。Specifically, the recognition of the animal species of the scanned object according to the visible light image can be realized by means of neural network training. First, sample images of various animals are collected, and feature points are extracted from the sample images to obtain feature point vectors. It should be noted that the sample image here should be the image of the animal when scanning the body position, and the image of the body position with a large difference from the scanned body position can be obtained without needing to obtain, so as to reduce the difficulty of training and improve the recognition accuracy of the model. Label each sample image with a species label, take the feature point vector as input, and take the species label as output, train the neural network to obtain an animal species recognition model, and realize animal species recognition based on visible light images through the animal species recognition model. .
样本图像特征点的提取可以采用LLE(Locally Linear Embedding)算法，即局部线性嵌入算法实现，其包括：The extraction of the feature points of the sample image can be realized by the LLE (Locally Linear Embedding) algorithm, that is, the local linear embedding algorithm, which includes:
根据样本图像构造k邻近图，并计算任意两个样本图像之间的相似度，结合每两个样本图像之间的相似度构造相似度矩阵，对相似度矩阵进行特征分解，取分解得到的前m个特征向量作为特征提取的结果。Construct k-proximity map according to the sample image, calculate the similarity between any two sample images, construct a similarity matrix by combining the similarity between each two sample images, perform feature decomposition on the similarity matrix, and take the decomposed front m feature vectors as the result of feature extraction.
神经网络的隐层节点为聚类算法得到的聚类中心。The hidden layer node of the neural network is the cluster center obtained by the clustering algorithm.
在一个实施例中，聚类算法选择K-means算法，包括：In one embodiment, the clustering algorithm selects the K-means algorithm, including:
以各样本图像的特征点向量作为数据点；Take the feature point vector of each sample image as the data point;
设置与动物种类数量相同的个数的初始的聚类中心；Set the initial cluster center of the same number as the number of animal species;
对于任意一张样本图像，分别计算其对应的数据点到各聚类中心的距离，并将相应的样本图像归入距离最近的聚类中心所在的类；For any sample image, calculate the distance between its corresponding data point and each cluster center, and classify the corresponding sample image into the class where the nearest cluster center is located;
计算每一类中所有数据点的平均值作为该类更新后的聚类中心，判断每一类当前的聚类中心与上一次的聚类中心之间的差值是否均小于设定阈值，如果是，则输出当前聚类结果，否则返回上一步进行下一次聚类，直到当前所有类的聚类中心与上一次的聚类中心的差值小于设定阈值为止。Calculate the average value of all data points in each class as the updated cluster center of that class, and judge whether the difference between the current cluster center of each class and the last cluster center is less than the set threshold, if If yes, output the current clustering result, otherwise return to the previous step to perform the next clustering until the difference between the cluster centers of all current classes and the previous cluster centers is less than the set threshold.
本方法的另一实施例中，所述获取扫描对象的可见光图像包括：In another embodiment of the method, the acquiring a visible light image of the scanned object includes:
获取扫描对象的视频流，获取所述视频流中与所述初始医学影像的扫描时刻相对应的帧作为所述可见光图像。A video stream of the scanned object is acquired, and a frame corresponding to the scanning moment of the initial medical image in the video stream is acquired as the visible light image.
为了保证可见光图像与初始医学影像是同一时刻的图像，首先获取扫描对象的视频流，然后从视频流中选取相应的帧，得到同一时刻的可见光图像与初始医学影像，以便提高后续图像融合的精度。在获取视频帧时，需要在扫描对象保持稳定状态时进行拍摄，以便后续抓取视频流中相应的帧，获取完整清晰的一张图片。对于动物等一些扫描对象来说，在获取视频流和初始医学影像时，其状态可能不受控制，很难保持稳定，一般需要先对动物进行用药使其状态稳定后再进行体位的固定，最后再获取视频帧和初始医学影像。In order to ensure that the visible light image and the initial medical image are images at the same time, first obtain the video stream of the scanned object, and then select the corresponding frame from the video stream to obtain the visible light image and the initial medical image at the same time, so as to improve the accuracy of subsequent image fusion. . When acquiring a video frame, it is necessary to shoot when the scanned object is in a stable state, so that the corresponding frame in the video stream can be subsequently captured to obtain a complete and clear picture. For some scanning objects such as animals, their state may be out of control when acquiring video streams and initial medical images, and it is difficult to maintain stability. Generally, it is necessary to administer medicine to the animal to stabilize its state, and then fix the body position. Video frames and initial medical images are then acquired.
在另一实施例中，所述同时获取扫描对象的可见光图像包括：采用高分辨率多目摄像头对扫描对象全方位拍照，然后对不同方位的照片进行融合处理得到可见光图像。In another embodiment, the simultaneous acquisition of the visible light images of the scanning object includes: using a high-resolution multi-eye camera to take photos of the scanning object in all directions, and then merging the photos in different directions to obtain the visible light images.
本方法的另一实施例中，所述对所述可见光图像以及所述初始医学影像进行融合，得到定位指导图包括：In another embodiment of the method, the obtaining a positioning guide map by fusing the visible light image and the initial medical image includes:
分别获取所述可见光图像和所述初始医学影像的特征点；respectively acquiring the feature points of the visible light image and the initial medical image;
基于所述特征点对所述可见光图像和所述初始医学影像进行点云配准，得到所述可见光图像与所述初始医学影像之间的旋转角和平移量；Perform point cloud registration on the visible light image and the initial medical image based on the feature points to obtain the rotation angle and translation between the visible light image and the initial medical image;
基于所述旋转角和平移量对所述可见光图像和初始医学影像的相对位置进行调整，然后对所述可见光图像和初始医学影像进行像素叠加，得到所述定位指导图。The relative positions of the visible light image and the initial medical image are adjusted based on the rotation angle and the translation amount, and then pixels are superimposed on the visible light image and the initial medical image to obtain the positioning guide map.
对可见光图像和初始医学影像进行融合，得到定位指导图，以便后续基于定位指导图进行初始扫描框的调整，确定最终的扫描范围。The visible light image and the initial medical image are fused to obtain a positioning guide map, so that the initial scan frame can be adjusted based on the positioning guide map and the final scan range can be determined.
具体的，通过HRNet获取两张图的特征点，通过ICP(Iterative Closest Point，迭代最近点)点云配准获得可见光图像和初始医学影像之间的平移量和旋转角，并进行相应的平移和旋转。Specifically, the feature points of the two images are obtained through HRNet, the translation amount and rotation angle between the visible light image and the initial medical image are obtained through ICP (Iterative Closest Point, iterative closest point) point cloud registration, and the corresponding translation and rotate.
具体的，HRNet即High Resolution NET，它能够在特征提取过程中保持图像高分辨率表示，以高分辨率子网开始作为第一阶段，按高分辨率到低分辨率的顺序逐个添加子网以形成更多阶段，并且并行连接多分辨率子网。在特征提取过程中反复交换并行多分辨率子网中信息来进行重复的多尺度融合。Specifically, HRNet is High Resolution NET, which can maintain the high-resolution representation of the image during the feature extraction process, starting with the high-resolution subnet as the first stage, and adding subnets one by one in the order of high resolution to low resolution. More stages are formed and multi-resolution subnetworks are connected in parallel. Repeated multi-scale fusion is performed by repeatedly exchanging information in parallel multi-resolution subnetworks during feature extraction.
具体的，在一个实施例中对所述可见光图像和所述初始医学影像进行ICP点云配准包括：Specifically, in one embodiment, performing ICP point cloud registration on the visible light image and the initial medical image includes:
将所述可见光图像和所述初始医学影像分别划分为目标区域和背景区域两个区域；Dividing the visible light image and the initial medical image into two areas, a target area and a background area, respectively;
分别针对目标区域和背景区域进行ICP点云配准，得到目标区域的旋转角和平移量以及背景区域的旋转角以及平移量；ICP算法是一种迭代计算方法，通过迭代，最小化源数据(可见光图像)与目标数据(初始医学影像)的对应点来实现精确地拼合；The ICP point cloud registration is performed for the target area and the background area respectively, and the rotation angle and translation of the target area and the rotation angle and translation of the background area are obtained; the ICP algorithm is an iterative calculation method, which minimizes the source data ( Visible light image) and the corresponding point of the target data (initial medical image) to achieve accurate stitching;
分别设置目标区域的配准权重和背景区域的配准权重；Set the registration weight of the target area and the registration weight of the background area respectively;
计算目标区域与背景区域的旋转角加权和，计算目标区域与背景区域的平移量加权和，得到最终的可见光图像与初始医学影像之间的旋转角和平移量。Calculate the weighted sum of the rotation angle of the target area and the background area, calculate the weighted sum of the translation amount of the target area and the background area, and obtain the rotation angle and translation amount between the final visible light image and the initial medical image.
目标区域的配准权重和背景区域的配准权重，可以根据目标区域的配准误差和背景区域的配准误差进行设置，目标区域的配准权重与背景区域的配准权重之和为1。The registration weight of the target area and the registration weight of the background area can be set according to the registration error of the target area and the registration error of the background area. The sum of the registration weight of the target area and the registration weight of the background area is 1.
背景区域和目标区域的划分基于区域生长法实现：设置阈值上限和阈值下限，区域点数在阈值上限和阈值下限之间的范围为目标区域，区域点数小于阈值下限或大于阈值上限的范围为背景区域。The division of the background area and the target area is realized based on the area growing method: the upper threshold and the lower threshold are set, the range of the area points between the upper threshold and the lower threshold is the target area, and the range of the area points less than the lower threshold or greater than the upper threshold is the background area .
完成点云配准得到可见光图像与初始医学影像之间的平移量和旋转角后，即可融合得到定位指导图。具体的，先根据平移量和旋转角对可见光图像或初始医学影像进行旋转及平移，使得可见光图像与初始医学影像的方向一致。然后根据扫描对象的大小设置图片裁剪大小，对可见光图像和初始医学影像进行裁剪到同一大小，例如256*256。将以上生成的裁剪后的可见光图像和初始医学影像进行像素级融合，即将可见光图像和初始医学影像中相应像素点的像素值分别乘以0.5后相加，得到定位指导图。After completing the point cloud registration to obtain the translation amount and rotation angle between the visible light image and the initial medical image, the positioning guide map can be obtained by fusion. Specifically, the visible light image or the initial medical image is first rotated and translated according to the translation amount and the rotation angle, so that the direction of the visible light image and the initial medical image is consistent. Then set the image cropping size according to the size of the scanned object, and crop the visible light image and the initial medical image to the same size, for example, 256*256. Pixel-level fusion is performed on the cropped visible light image generated above and the initial medical image, that is, the pixel values of the corresponding pixels in the visible light image and the initial medical image are multiplied by 0.5 and added together to obtain a positioning guide map.
本方法的另一实施例中，所述基于所述定位指导图对所述初始扫描框进行调整，得到成像扫描框包括：In another embodiment of the method, the adjusting the initial scan frame based on the positioning guide map to obtain the imaging scan frame includes:
根据所述定位指导图中初始医学影像部分设置目标扫描框；Set the target scan frame according to the initial medical image part in the positioning guide;
计算所述目标扫描框与所述初始扫描框的偏差值；Calculate the deviation value of the target scan frame and the initial scan frame;
基于所述偏差值对所述初始扫描框进行调整，得到所述目标扫描框。The initial scan frame is adjusted based on the deviation value to obtain the target scan frame.
对初始扫描框进行调整，得到成像扫描框，具体的，在通过上述步骤获取到定位指导图后，定位指导图中可以观察到扫描对象的内部生理结构，以及内部生理结构与外部身体结构的相对关系，通过观察定位指导图中扫描对象的内部生理结构准确选择扫描目标的位置及范围，设置目标扫描框。目标扫描框可以采用滑动框的方式来设置，即通过移动滑动框来设置目标扫描框的位置，通过拖拉滑动框的方式来设置目标扫描框的大小。由于初始扫描框的位置已知，因此根据初始扫描框的位置和目标扫描框(移动、拖拉好后的最终滑动框)的位置，即可确定初始扫描框与扫描目标之间的位置偏差值以及大小偏差值，从而最终确定成像扫描框的位置和大小。应该理解的，成像扫描框的位置为相对位置，即相对于初始扫描框的位置，该相对位置用于指导用户对初始扫描框进行调整以获取最佳的扫描效果。记录初始扫描框的起始位置和起始位置的偏差值作为成像扫描框的起始位置，记录初始扫描框的大小和大小偏差值作为成像扫描框的大小，从而准确定义临床扫描范围。Adjust the initial scan frame to obtain the imaging scan frame. Specifically, after the positioning guide map is obtained through the above steps, the internal physiological structure of the scanned object and the relative relationship between the internal physiological structure and the external body structure can be observed in the positioning guide map. By observing the internal physiological structure of the scanning object in the positioning guidance map, the position and range of the scanning target are accurately selected, and the target scanning frame is set. The target scan frame can be set by sliding the frame, that is, the position of the target scan frame is set by moving the slide frame, and the size of the target scan frame is set by dragging the slide frame. Since the position of the initial scan frame is known, the position deviation value between the initial scan frame and the scan target can be determined according to the position of the initial scan frame and the position of the target scan frame (the final sliding frame after moving and dragging). The size deviation value, which ultimately determines the position and size of the imaging scan frame. It should be understood that the position of the imaging scan frame is a relative position, that is, relative to the position of the initial scan frame, and the relative position is used to guide the user to adjust the initial scan frame to obtain the best scanning effect. The initial position of the initial scanning frame and the deviation value of the initial position are recorded as the initial position of the imaging scanning frame, and the size and size deviation of the initial scanning frame are recorded as the size of the imaging scanning frame, thereby accurately defining the clinical scanning range.
具体的，当有多个扫描目标，即需要对多个脏器同时进行扫描时，由于初始扫描框中已经包含了各个子框的分布以及各个子框的相对位置关系，因此进行成像扫描框确定时，只需要确定初始扫描框，即最大范围框的偏差值，则初始扫描框内所包含的多个子框的大小偏差值和位置偏差值即可同时得到，在此也就不再过多赘述。Specifically, when there are multiple scanning targets, that is, multiple organs need to be scanned at the same time, since the initial scan frame already contains the distribution of each subframe and the relative positional relationship of each subframe, the imaging scan frame is determined. When it is necessary to determine the initial scan frame, that is, the deviation value of the maximum range frame, the size deviation value and position deviation value of the multiple subframes contained in the initial scanning frame can be obtained at the same time, which will not be repeated here. .
本方法的另一实施例中，基于所述成像扫描框对扫描对象进行医学影像扫描之前，还包括：In another embodiment of the method, before performing medical image scanning on the scanning object based on the imaging scanning frame, the method further includes:
在所述扫描对象上标记所述成像扫描框，获取包含成像扫描框标记的可见光标记图像；marking the imaging scan frame on the scanning object, and obtaining a visible light marked image containing the imaging scan frame mark;
通过对比所述可见光标记图像与所述定位指导图判断扫描对象是否发生移动，如果发生移动，则重新进行成像扫描框的确定，否则以当前成像扫描框对扫描对象进行医学影像的扫描。Determine whether the scanning object moves by comparing the visible light marker image with the positioning guide map. If there is movement, the imaging scan frame is re-determined. Otherwise, the scan object is scanned for medical images with the current imaging scan frame.
在扫描过程中，即从基于初始扫描框进行初始医学影像扫描成像到基于成像扫描框进行医学影像扫描成像之间的这段时间里，应该尽量保持扫描对象的体位状态稳定，这样才能保证后续扫描结果的准确。如果扫描对象在扫描过程中发生较大的体位移动，则调整得到的成像扫描框显然就不再适应。在一些特殊情况下，例如对儿童或动物进行扫描时，保持状态的稳定显然不是特别的容易，很多时候扫描对象已经发生了体位移动，但是这种体位移动无法通过肉眼准确快速识别，从而导致后续扫描工作变成了无用功，降低了扫描的效率和精度。有鉴于此，在成像扫描框调整确认之后，在扫描医学影像之前，还进行了扫描对象的体位移动确认步骤。具体实现为：将成像扫描框标记到扫描对象身上，标记的方式有很多种，只要能够在扫描对象上体现可见的成像扫描框标记即可。本实施例采用向扫描对象投射可见光束形成可见光标记的方式实现。成像扫描框标记设置好后重新采集扫描对象的可见光图像，得到可见光标记图像，该图像准确描述了当前时刻扫描对象与成像扫描框之间的相对位置关系。对比定位指导图中的成像扫描框与可见光图像中扫描对象的相对位置关系，判断当前相对位置关系是否发生较大变化，即两张可见光图像中成像扫描框的旋转角和平移量是否均大于设定阈值，如果是，则说明扫描对象的体位发生了较大的变化，当前的成像扫描框已经不再适用，需要重新调整，否则说明扫描对象的体位没有发生较大变化，当前的成像扫描框仍然使适用，以当前的成像扫描框直接扫描获取医学影像即可。During the scanning process, that is, during the period from the initial medical image scanning and imaging based on the initial scanning frame to the medical image scanning and imaging based on the imaging scanning frame, the body position of the scanned object should be kept as stable as possible, so as to ensure subsequent scanning. accurate results. If the scanning object undergoes a large body position movement during the scanning process, the adjusted imaging scan frame obviously no longer fits. In some special cases, such as scanning children or animals, it is obviously not easy to keep the state stable. In many cases, the scanning object has already moved, but this movement cannot be accurately and quickly identified by the naked eye, resulting in subsequent follow-up. Scanning work becomes useless, reducing the efficiency and accuracy of scanning. In view of this, after the adjustment and confirmation of the imaging scan frame, before scanning the medical image, a step of confirming the body position movement of the scanning object is also performed. The specific implementation is as follows: marking the imaging scan frame on the scanning object. There are many ways of marking, as long as the visible imaging scanning frame mark can be reflected on the scanning object. This embodiment is implemented by projecting a visible light beam to a scanning object to form a visible light mark. After the imaging scan frame mark is set, the visible light image of the scanning object is re-collected to obtain a visible light mark image, which accurately describes the relative positional relationship between the scanning object and the imaging scan frame at the current moment. Compare the relative positional relationship between the imaging scan frame in the positioning guide and the scanned object in the visible light image, and determine whether the current relative positional relationship has changed greatly, that is, whether the rotation angle and translation of the imaging scan frame in the two visible light images are greater than the set value. Set the threshold value, if yes, it means that the body position of the scanned object has changed greatly, the current imaging scan frame is no longer applicable and needs to be re-adjusted, otherwise it means that the body position of the scanned object has not changed greatly, and the current imaging scan frame Still applicable, the current imaging scan frame can be used to directly scan to obtain medical images.
当然，应该理解的是，由于可见光图像的获取、初始医学影像的获取、可见光图像与初始医学影像之间的融合、基于定位指导图的成像扫描框确定，这些步骤均是通过计算机程序自动化完成的，因此完成此过程的时间其实是非常短的，只需要扫描对象在这段非常短的时间内保持相对稳定的体位，成像扫描框的确定和扫描均可一次性完成，不需要重复，即体位校验步骤为优选可选步骤。Of course, it should be understood that, due to the acquisition of the visible light image, the acquisition of the initial medical image, the fusion between the visible light image and the initial medical image, and the determination of the imaging scan frame based on the positioning guide map, these steps are all automated through computer programs. , so the time to complete this process is actually very short, only need to scan the object to maintain a relatively stable body position during this very short period of time, the determination of the imaging scan frame and scanning can be completed at one time, no need to repeat, that is, the body position The verification step is a preferred optional step.
本发明的另一实施例提供了医学扫描成像装置，包括处理器以及存储器，所述存储器上存储有计算机程序，所述计算机程序被所述处理器执行时，实现实施例1提供的医学扫描成像方法。Another embodiment of the present invention provides a medical scanning imaging apparatus, including a processor and a memory, where a computer program is stored in the memory, and when the computer program is executed by the processor, the medical scanning imaging provided in Embodiment 1 is implemented method.
本发明实施例提供的医学扫描成像装置，用于实现医学扫描成像方法，因此，医学扫描成像方法所具备的技术效果，医学扫描成像装置同样具备，在此不再赘述。The medical scanning and imaging apparatus provided by the embodiment of the present invention is used to realize the medical scanning and imaging method. Therefore, the technical effects of the medical scanning and imaging method are also provided by the medical scanning and imaging apparatus, which will not be repeated here.
如图2所示，本发明另一实施例还提供医学扫描成像系统，包括医学扫描成像装置1，还包括医学影像装置2以及可见光图像获取装置3；在一个实施例中，医学影像装置2包括CT扫描设备,可见光图像获取装置3包括光学摄像头。As shown in FIG. 2 , another embodiment of the present invention further provides a medical scanning imaging system, including a medical scanning imaging device 1, a medical imaging device 2 and a visible light image acquiring device 3; in one embodiment, the medical imaging device 2 includes CT scanning equipment, visible light image acquisition device 3 includes an optical camera.
所述医学影像装置2用于基于初始扫描框对扫描对象进行扫描得到初始医学影像，并将所述初始医学影像发送至所述医学扫描成像装置1。The medical imaging device 2 is configured to scan the scanning object based on the initial scanning frame to obtain an initial medical image, and send the initial medical image to the medical scanning and imaging device 1 .
所述可见光图像获取装置3用于采集扫描对象的可见光图像，并将所述可见光图像发送至所述医学扫描成像装置1。The visible light image acquisition device 3 is used for collecting a visible light image of the scanning object, and sending the visible light image to the medical scanning imaging device 1 .
所述医学扫描成像装置1用于基于所述初始医学影像以及所述可见光图像，采用所述医学扫描成像方法，获取所述成像扫描框，并将所述成像扫描框发送至所述医学影像装置2。The medical scanning and imaging device 1 is configured to, based on the initial medical image and the visible light image, adopt the medical scanning and imaging method to acquire the imaging scan frame, and send the imaging scan frame to the medical imaging device 2.
所述医学影像装置2用于基于所述成像扫描框对扫描对象进行医学影像扫描。The medical imaging device 2 is configured to perform medical image scanning on the scanning object based on the imaging scanning frame.
医学扫描成像装置1可以集成于医学影像装置2中，也可以是单独设置的终端。The medical scanning and imaging device 1 may be integrated into the medical imaging device 2, or may be a separately set terminal.
本发明实施例提供的医学扫描成像系统，包括医学扫描成像装置1，因此，医学扫描成像装置1所具备的技术效果，医学扫描成像系统同样具备，在此不再赘述。The medical scanning and imaging system provided by the embodiment of the present invention includes the medical scanning and imaging apparatus 1 . Therefore, the technical effects of the medical scanning and imaging apparatus 1 are also provided by the medical scanning and imaging system, which will not be repeated here.
以上所述，仅为本发明较佳的具体实施方式，但本发明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发明揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本发明的保护范围之内。The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited to this. Substitutions should be covered within the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011636907.9ACN114693571B (en) | 2020-12-31 | 2020-12-31 | Medical scanning imaging method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011636907.9ACN114693571B (en) | 2020-12-31 | 2020-12-31 | Medical scanning imaging method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114693571Atrue CN114693571A (en) | 2022-07-01 |
| CN114693571B CN114693571B (en) | 2025-01-03 |
Family
ID=82133906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011636907.9AActiveCN114693571B (en) | 2020-12-31 | 2020-12-31 | Medical scanning imaging method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114693571B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07116161A (en)* | 1993-10-22 | 1995-05-09 | Hitachi Medical Corp | Ultrasonograph |
| US5740802A (en)* | 1993-04-20 | 1998-04-21 | General Electric Company | Computer graphic and live video system for enhancing visualization of body structures during surgery |
| CN205633443U (en)* | 2016-05-16 | 2016-10-12 | 新疆维吾尔自治区人民医院 | Two -dimensional code magnetism is frozen and is deposited device suitable for deposit medical sample |
| CN109242893A (en)* | 2018-08-23 | 2019-01-18 | 深圳市斯尔顿科技有限公司 | Imaging method, method for registering images and device |
| CN109727223A (en)* | 2018-12-27 | 2019-05-07 | 上海联影医疗科技有限公司 | A kind of automatic fusion method of medical image and system |
| CN110299199A (en)* | 2019-06-28 | 2019-10-01 | 上海联影医疗科技有限公司 | Medical image scan method, device, computer equipment and storage medium |
| CN110942493A (en)* | 2019-11-28 | 2020-03-31 | 南京安科医疗科技有限公司 | Method for automatically generating scanning area in CT system |
| CN111012371A (en)* | 2019-12-17 | 2020-04-17 | 东软医疗系统股份有限公司 | CT scanning image building method and CT scanning image building device |
- 2020
- 2020-12-31CNCN202011636907.9Apatent/CN114693571B/enactiveActive
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5740802A (en)* | 1993-04-20 | 1998-04-21 | General Electric Company | Computer graphic and live video system for enhancing visualization of body structures during surgery |
| JPH07116161A (en)* | 1993-10-22 | 1995-05-09 | Hitachi Medical Corp | Ultrasonograph |
| CN205633443U (en)* | 2016-05-16 | 2016-10-12 | 新疆维吾尔自治区人民医院 | Two -dimensional code magnetism is frozen and is deposited device suitable for deposit medical sample |
| CN109242893A (en)* | 2018-08-23 | 2019-01-18 | 深圳市斯尔顿科技有限公司 | Imaging method, method for registering images and device |
| CN109727223A (en)* | 2018-12-27 | 2019-05-07 | 上海联影医疗科技有限公司 | A kind of automatic fusion method of medical image and system |
| CN110299199A (en)* | 2019-06-28 | 2019-10-01 | 上海联影医疗科技有限公司 | Medical image scan method, device, computer equipment and storage medium |
| CN110942493A (en)* | 2019-11-28 | 2020-03-31 | 南京安科医疗科技有限公司 | Method for automatically generating scanning area in CT system |
| CN111012371A (en)* | 2019-12-17 | 2020-04-17 | 东软医疗系统股份有限公司 | CT scanning image building method and CT scanning image building device |
Non-Patent Citations (1)
| Title |
|---|
| 李晓春, 陈鲸: "一种基于小波变换的图像融合新方法", 空军工程大学学报(自然科学版), vol. 4, no. 2, 25 April 2003 (2003-04-25), pages 55 - 58* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114693571B (en) | 2025-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11576578B2 (en) | Systems and methods for scanning a patient in an imaging system | |
| CN107789001B (en) | A positioning method and system for imaging scanning | |
| US9895131B2 (en) | Method and system of scanner automation for X-ray tube with 3D camera | |
| EP3406196A1 (en) | X-ray system and method for standing subject | |
| CN110956633B (en) | Rapid CT scanning method and system based on virtual stereotactic image | |
| CN110956635A (en) | Lung segment segmentation method, device, equipment and storage medium | |
| CN102106758B (en) | Automatic visual location device and automatic visual location method for head marks of patient in stereotactic neurosurgery | |
| JP2018522622A (en) | Method and system for simultaneous scene analysis and model fusion for endoscopic and laparoscopic navigation | |
| US10078906B2 (en) | Device and method for image registration, and non-transitory recording medium | |
| CN108294772A (en) | A kind of CT scan vision positioning method and CT system | |
| EP2727082A2 (en) | Method and device for displaying an object | |
| WO2021104153A1 (en) | Systems and methods for automated calibration | |
| EP4184433A2 (en) | System and methods for medical image quality assessment using deep neural networks | |
| US11847730B2 (en) | Orientation detection in fluoroscopic images | |
| CN106344152A (en) | Abdominal surgery navigation registering method and system | |
| CN109166177A (en) | Air navigation aid in a kind of art of craniomaxillofacial surgery | |
| JP2024504867A (en) | Image-based planning of tomography scans | |
| US12272082B2 (en) | Method and system for constructing bone model, medium and device | |
| CN109934798A (en) | Internal object information labeling method and device, electronic equipment, storage medium | |
| Singh et al. | Estimating a patient surface model for optimizing the medical scanning workflow | |
| CN114693571A (en) | Medical scanning imaging method, device and system | |
| US10049480B2 (en) | Image alignment device, method, and program | |
| CN115887002A (en) | Operation space registration method and operation navigation system | |
| KR102534981B1 (en) | System for alignmenting patient position and monitoring with surface image guidance | |
| EP3968215A1 (en) | Determining target object type and position |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |