CN115910379B - A method, system, device and storage medium for evaluating curative effect after renal calculus surgery - Google Patents
A method, system, device and storage medium for evaluating curative effect after renal calculus surgeryDownload PDFInfo
- Publication number
- CN115910379B CN115910379BCN202310052949.5ACN202310052949ACN115910379BCN 115910379 BCN115910379 BCN 115910379BCN 202310052949 ACN202310052949 ACN 202310052949ACN 115910379 BCN115910379 BCN 115910379B
- Authority
- CN
- China
- Prior art keywords
- data
- patient
- target
- determining
- feature
- 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.)
- Active
Links
Images
Classifications
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本申请涉及疗效评估的技术领域，尤其是涉及一种肾结石术后疗效评估方法、系统、设备及存储介质。The present application relates to the technical field of curative effect evaluation, in particular to a method, system, device and storage medium for evaluating curative effect after renal calculus surgery.
背景技术Background technique
体外冲击波碎石（ESWL）治疗是肾结石常见的治疗方法之一，针对肾结石的病人，如果结石体积不是很大，没有形成严重的梗阻，是可以通过体外冲击波碎石进行治疗的。大部分病人可能将结石粉碎成比较小的颗粒，然后自身排出体外。但是，临床实践证明并不是所有的结石都适合采用体外冲击波碎石（ESWL）治疗，有些结石无法击碎，有些结石击碎后病人无法自行排出。Extracorporeal shock wave lithotripsy (ESWL) is one of the common treatment methods for kidney stones. For patients with kidney stones, if the stones are not very large and do not form serious obstruction, they can be treated by extracorporeal shock wave lithotripsy. Most patients may crush the stones into relatively small particles, and then pass them out of the body by themselves. However, clinical practice has proved that not all stones are suitable for extracorporeal shock wave lithotripsy (ESWL). Some stones cannot be crushed, and some stones cannot be crushed by the patient.
对于计划实施体外冲击波碎石的患者，现有的疗效预测方法主要是从CT影像数据中测量结石与体表之间距离、CT值等参数，从而预测体外冲击波碎石（ESWL）的成功率，也有相关研究采取建立人工智能模型来预测疗效。一方面患者的CT值等相关数据需要人工进行测量，在一定程度上会导致疗效的预测结果不准确，另一方面，目前疗效预测参考的因素过少，在疗效预测时考虑的因素不全面，也会导致疗效预测不准确。For patients who plan to implement extracorporeal shock wave lithotripsy, the existing curative effect prediction method is mainly to measure the distance between the stone and the body surface, CT value and other parameters from CT image data, so as to predict the success rate of extracorporeal shock wave lithotripsy (ESWL). There are also related studies that use the establishment of artificial intelligence models to predict the curative effect. On the one hand, relevant data such as CT values of patients need to be measured manually, which will lead to inaccurate prediction results of curative effect to a certain extent; It can also lead to inaccurate prediction of efficacy.
上述中的现有技术方案存在以下缺陷：存在体外冲击波碎石（ESWL）疗效预测不准确的问题。The above existing technical solutions have the following defects: there is the problem of inaccurate prediction of the curative effect of extracorporeal shock wave lithotripsy (ESWL).
发明内容Contents of the invention
为了改善体外冲击波碎石疗效预测不准确的问题，本申请提供了一种肾结石术后疗效评估方法、系统、设备及存储介质。In order to improve the inaccurate prediction of curative effect of extracorporeal shock wave lithotripsy, the present application provides a method, system, device and storage medium for evaluating curative effect after renal calculus surgery.
在本申请的第一方面，提供了一种肾结石术后疗效评估方法。该方法包括：In the first aspect of the present application, a method for evaluating curative effect after renal calculus surgery is provided. The method includes:
获取患者数据和第一特征；Obtain patient data and first characteristics;
根据预设的数据归一规则和所述患者数据，确定患者目标数据；Determine patient target data according to preset data normalization rules and the patient data;
根据预设的特征确定规则和所述患者目标数据，确定第二特征；determining a second feature according to a preset feature determination rule and the patient target data;
根据预设的训练模型、所述第一特征、所述第二特征和所述患者目标数据，确定目标预测模型；determining a target prediction model according to a preset training model, the first feature, the second feature, and the patient target data;
获取待预测患者数据，并根据所述待预测患者数据和所述目标预测模型，确定患者术后疗效。Obtain the data of the patient to be predicted, and determine the postoperative curative effect of the patient according to the data of the patient to be predicted and the target prediction model.
由以上技术方案可知，获取患者数据和第一特征，根据数据归一规则对患者数据做处理并确定患者目标数据，进而根据特征确定规则对患者目标数据做筛选，确定第二特征，然后根据预设的训练模型、第一特征、第二特征和患者目标数据，确定目标预测模型，获取待预测患者的患者数据，并将待预测患者的患者数据输入至目标预测模型中可以得到患者术后疗效，通过训练目标预测模型，可以改善体外冲击波碎石疗效预测不准确的问题，在一定程度上可以提高体外冲击波碎石疗效预测的准确率。It can be seen from the above technical solutions that the patient data and the first feature are obtained, the patient data is processed according to the data normalization rule and the patient target data is determined, and then the patient target data is screened according to the feature determination rule to determine the second feature, and then according to the predicted Set the training model, first feature, second feature and patient target data, determine the target prediction model, obtain the patient data of the patient to be predicted, and input the patient data of the patient to be predicted into the target prediction model to obtain the postoperative curative effect of the patient , by training the target prediction model, the problem of inaccurate prediction of the curative effect of extracorporeal shock wave lithotripsy can be improved, and the accuracy rate of curative effect prediction of extracorporeal shock wave lithotripsy can be improved to a certain extent.
在一种可能的实现方式中，所述获取第一特征，包括：In a possible implementation manner, the acquiring the first feature includes:
获取肾脏分割模型；Obtain the kidney segmentation model;
根据预设的训练规则、所述患者数据和所述肾脏分割模型，确定第一特征。A first feature is determined according to preset training rules, the patient data and the kidney segmentation model.
在一种可能的实现方式中，所述获取患者数据，包括：所述患者数据包括结石发生图像；In a possible implementation manner, the acquiring patient data includes: the patient data includes an image of stone occurrence;
获取图像数据和标注指令，所述图像数据包括患者的平扫CT图像和增强CT图像；Acquiring image data and labeling instructions, the image data including plain scan CT images and enhanced CT images of the patient;
根据所述标注指令和所述图像数据，对所述图像数据进行标注，确定结石发生图像。According to the labeling instruction and the image data, the image data is marked to determine the calculus occurrence image.
在一种可能的实现方式中，根据预设的数据归一规则和所述患者数据，确定患者目标数据；In a possible implementation manner, the patient target data is determined according to a preset data normalization rule and the patient data;
所述患者数据还包括数值数据；The patient data also includes numerical data;
所述患者目标数据包括目标数值数据和目标影像数据；The patient target data includes target numerical data and target image data;
根据标准分数规则和所述数值数据，确定目标数值数据；Determining target numerical data according to standard score rules and said numerical data;
根据重采样规则和所述结石发生图像，确定目标影像数据。Target image data is determined according to the resampling rule and the calculus occurrence image.
在一种可能的实现方式中，所述根据预设的特征确定规则和所述患者目标数据，确定第二特征，包括：In a possible implementation manner, the determining the second feature according to the preset feature determination rule and the patient target data includes:
根据特征提取规则和所述患者目标数据，确定目标特征；determining target features according to feature extraction rules and the patient target data;
根据特征筛选规则和所述目标特征，确定第二特征。The second feature is determined according to the feature screening rule and the target feature.
在一种可能的实现方式中，该方法还包括：In a possible implementation, the method further includes:
获取测试数据集；Get the test data set;
根据所述测试数据集和所述目标预测模型，确定结果数据集；determining a result data set according to the test data set and the target prediction model;
根据正确率计算规则、所述测试数据集和所述结果数据集，确定预测正确率。Determine the prediction accuracy rate according to the accuracy rate calculation rule, the test data set and the result data set.
在一种可能的实现方式中，所述训练规则为支持向量机。In a possible implementation manner, the training rule is a support vector machine.
在本申请的第二方面，提供了一种肾结石术后疗效评估系统。该系统包括：In the second aspect of the present application, a system for evaluating curative effect after kidney stone surgery is provided. The system includes:
数据获取模块，用于获取患者数据、第一特征和待预测患者数据；A data acquisition module, configured to acquire patient data, first features and patient data to be predicted;
数据处理模块，用于根据预设的数据归一规则和所述患者数据，确定患者目标数据；A data processing module, configured to determine patient target data according to preset data normalization rules and the patient data;
特征提取模块，用于根据预设的特征确定规则和所述患者目标数据，确定第二特征；A feature extraction module, configured to determine a second feature according to preset feature determination rules and the patient target data;
模型训练模块，用于根据预设的训练模型、所述第一特征、所述第二特征和所述患者目标数据，确定目标预测模型；A model training module, configured to determine a target prediction model according to a preset training model, the first feature, the second feature, and the patient target data;
疗效预测模块，用于根据正确率计算规则、所述待预测患者数据和所述目标预测模型，确定患者术后疗效。The curative effect prediction module is used to determine the postoperative curative effect of the patient according to the accuracy rate calculation rule, the patient data to be predicted and the target prediction model.
在本申请的第三方面，提供了一种电子设备。该电子设备包括：存储器和处理器，所述存储器上存储有计算机程序，所述处理器执行所述程序时实现如以上所述的肾结石术后疗效评估方法。In a third aspect of the present application, an electronic device is provided. The electronic device includes: a memory and a processor, where a computer program is stored on the memory, and when the processor executes the program, the above-mentioned method for evaluating curative effect after kidney stone operation is realized.
在本申请的第四方面，提供了一种计算机可读存储介质，其上存储有计算机程序，所述程序被处理器执行时实现如根据本申请的第一方面的方法。In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method according to the first aspect of the present application is implemented.
综上所述，本申请包括以下至少一种有益技术效果：In summary, the present application includes at least one of the following beneficial technical effects:
1.获取患者数据和第一特征，根据数据归一规则对患者数据做处理并确定患者目标数据，进而根据特征确定规则对患者目标数据做筛选，确定第二特征，然后根据预设的训练模型、第一特征、第二特征和患者目标数据，确定目标预测模型，获取待预测患者的患者数据，并将待预测患者的患者数据输入至目标预测模型中可以得到患者术后疗效，通过训练目标预测模型，可以改善体外冲击波碎石疗效预测不准确的问题，在一定程度上可以提高体外冲击波碎石疗效预测的准确率；1. Obtain the patient data and the first feature, process the patient data according to the data normalization rules and determine the patient target data, and then filter the patient target data according to the feature determination rules, determine the second feature, and then use the preset training model , the first feature, the second feature, and the patient target data, determine the target prediction model, obtain the patient data of the patient to be predicted, and input the patient data of the patient to be predicted into the target prediction model to obtain the postoperative curative effect of the patient. By training the target The prediction model can improve the problem of inaccurate prediction of the curative effect of extracorporeal shock wave lithotripsy, and to a certain extent, can improve the accuracy of predicting the curative effect of extracorporeal shock wave lithotripsy;
2.通过获取测试数据集，对目标预测模型做测试得到结果数据集，并根据正确率计算规则和结果数据集计算目标预测模型对应的预测正确率。通过对目标预测模型做测试，进一步验证模型的可靠性。2. By obtaining the test data set, test the target prediction model to obtain the result data set, and calculate the prediction accuracy corresponding to the target prediction model according to the accuracy rate calculation rules and the result data set. By testing the target prediction model, the reliability of the model is further verified.
附图说明Description of drawings
图1是本申请提供的肾结石术后疗效评估方法的流程示意图。Fig. 1 is a schematic flow chart of the method for evaluating curative effect after renal calculus surgery provided by the present application.
图2是本申请提供的肾结石术后疗效评估系统的结构示意图。Fig. 2 is a schematic structural diagram of the curative effect evaluation system after renal calculus surgery provided by the present application.
图3是本申请提供的电子设备的结构示意图。FIG. 3 is a schematic structural diagram of an electronic device provided by the present application.
图中，200、肾结石术后疗效评估系统；201、数据获取模块；202、数据处理模块；203、特征提取模块；204、模型训练模块；205、疗效预测模块；301、CPU；302、ROM；303、RAM；304、I/O接口；305、输入部分；306、输出部分；307、存储部分；308、通信部分；309、驱动器；310、可拆卸介质。In the figure, 200, curative effect evaluation system after kidney stone surgery; 201, data acquisition module; 202, data processing module; 203, feature extraction module; 204, model training module; 205, curative effect prediction module; 301, CPU; 302,
具体实施方式Detailed ways
为使本申请实施例的目的、技术方案和优点更加清楚，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作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。In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.
另外，本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，如无特殊说明，一般表示前后关联对象是一种“或”的关系。In addition, the term "and/or" in this article is only an association relationship describing associated objects, which means that there may be three relationships, for example, A and/or B may mean: A exists alone, A and B exist at the same time, There are three cases of B alone. In addition, the character "/" in this article, unless otherwise specified, generally indicates that the contextual objects are an "or" relationship.
下面结合说明书附图对本申请实施例作进一步详细描述。The embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings.
本申请实施例提供一种肾结石术后疗效评估方法，上述方法的主要流程描述如下。The embodiment of the present application provides a method for evaluating curative effect after kidney stone surgery, and the main process of the above method is described as follows.
如图1所示：As shown in Figure 1:
步骤S101：获取患者数据和第一特征。Step S101: Obtain patient data and first features.
具体的，首先要获取患者的平扫CT影像数据、增强CT影像数据、临床统计学资料、CT人工测量指标以及对应患者的术后疗效情况。临床医生根据患者的平扫CT影像数据和增强CT影像数据，对上述平扫CT影像数据和增强CT影像数据做标注，在平扫CT影像数据和增强CT影像数据上对产生肾结石的位置做标注，记为结石发生图像。上述临床统计学资料表示对某个患者用定量的方法测定某项指标量的大小，上述临床统计学资料包括但不限于患者的身高(cm)、体重(kg)、脉搏(次/分)、血压(KPa)。上述CT人工测量指标包括结石的位置、形态和大小。上述对应患者的术后疗效情况表示患者完成体外冲击波碎石治疗之后，体内结石大小，医生会根据结石的大小对患者数据做疗效标识，上述疗效标识包括疗效显著和无疗效。患者数据包括结石发生图像、临床统计学资料、CT人工测量指标和疗效标识。根据上述描述可以得知临床统计学资料和CT人工测量指标为数值型数据，故临床统计学资料和CT人工测量指标组成数值数据。Specifically, the patient’s plain scan CT image data, enhanced CT image data, clinical statistical data, CT manual measurement indicators, and postoperative curative effect of the corresponding patient must be obtained first. According to the plain scan CT image data and enhanced CT image data of the patient, the clinician marks the above plain scan CT image data and enhanced CT image data, and makes the location of the kidney stone on the plain scan CT image data and enhanced CT image data. Annotated, recorded as the image of calculus occurrence. The above-mentioned clinical statistical data means that the quantitative method is used to determine the size of a certain index for a certain patient. The above-mentioned clinical statistical data include but are not limited to the patient's height (cm), weight (kg), pulse (times/minute), Blood pressure (KPa). The aforementioned CT manual measurement indicators include the location, shape and size of the stones. The postoperative curative effect of the above corresponding patients means that after the extracorporeal shock wave lithotripsy, the doctor will mark the curative effect of the patient data according to the size of the stone in the body. The above curative effect mark includes significant curative effect and no curative effect. Patient data include images of calculi occurrence, clinical statistics, CT manual measurement indicators and curative effect indicators. According to the above description, it can be known that the clinical statistical data and the manual CT measurement indicators are numerical data, so the clinical statistical data and the manual CT measurement indicators form numerical data.
上述第一特征的获取包括：首先基于KiTS19数据集的nn-Unet肾脏分割模型。基于KiTS19数据集的nn-Unet肾脏分割模型是开源的，将上述患者数据中的结石发生图像输入至上述nn-Unet肾脏分割模型并进行预设值次数的断点续训，确定目标肾脏分割模型。当需要对某一患者的疗效进行预测时，将需要预测的患者的结石发生图像输入至上述目标肾脏分割模型，上述目标肾脏分割模型输出与上述患者对应的一组矩阵数据。上述矩阵数据为第一特征。在本实施例中，预设值为50，即对nn-Unet肾脏分割模型进行50次的断点续训。The acquisition of the above-mentioned first feature includes: first, based on the nn-Unet kidney segmentation model of the KiTS19 data set. The nn-Unet kidney segmentation model based on the KiTS19 data set is open source. Input the images of calculus occurrence in the above patient data to the above nn-Unet kidney segmentation model and carry out breakpoint continuous training for the number of preset values to determine the target kidney segmentation model. . When the curative effect of a certain patient needs to be predicted, the calculus occurrence image of the patient to be predicted is input to the above-mentioned target kidney segmentation model, and the above-mentioned target kidney segmentation model outputs a set of matrix data corresponding to the above-mentioned patient. The aforementioned matrix data is the first feature. In this embodiment, the preset value is 50, that is, the nn-Unet kidney segmentation model is continued for 50 breakpoint trainings.
步骤S102：根据预设的数据归一规则和患者数据，确定患者目标数据。Step S102: Determine patient target data according to preset data normalization rules and patient data.
具体的，上述患者目标数据包括目标数值数据和目标影像数据。上述患者数据包括结石发生图像和数值数据。对上述结石发生图像做重采样处理，得到目标影像数据，根据标准分数规则和上述数值数据，确定目标数值数据。获取上述数值数据的平均数和标准差，目标数值数据=(数值数据-平均数)/标准差。例如，数值数据为某一患者的身高，则计算所有患者身高的平均值和标准差，该身高对应的目标数值数据=(身高-平均数)/标准差。Specifically, the patient target data includes target numerical data and target image data. The above-mentioned patient data includes stone occurrence images and numerical data. Resampling is performed on the above calculus occurrence image to obtain the target image data, and the target numerical data is determined according to the standard score rule and the above numerical data. Obtain the mean and standard deviation of the above numerical data, target numerical data = (numerical data - mean)/standard deviation. For example, if the numerical data is the height of a certain patient, the mean and standard deviation of the heights of all patients are calculated, and the target numerical data corresponding to the height = (height-average)/standard deviation.
步骤S103：根据预设的特征确定规则和患者目标数据，确定第二特征。Step S103: Determine the second feature according to preset feature determination rules and patient target data.
具体的，上述第二特征包括无效目标特征和有效目标特征。根据上述疗效标识对所有的患者目标数据进行分类，疗效标识为疗效显著的患者目标数据组成疗效显著数据集，疗效标识为无疗效的患者目标数据组成无疗效数据集。分别将上述疗效显著数据集和无疗效数据集中目标影像数据做影像组学特征提取，提取1688种影像组学特征，上述影像组学特征分为一阶统计学、形状、纹理以及滤波四个类别。上述四个分类的影像组学特征一共包括1688个特征，这是本领域技术人员公知的内容，在此不做赘述。上述疗效显著数据集获取的影像组学特征组成有效特征，上述无疗效数据集获取的影像组学特征组成无效特征。上述目标特征包括上述有效特征和上述无效特征。根据特征筛选规则、上述有效特征和上述无效特征，确定无效目标特征和有效目标特征。上述特征筛选规则包括方差阈值法、spearman相关性分析法和LASSO回归模型。在本实施例中，对有效特征依次通过方差阈值法、spearman相关性分析法和LASSO回归模型进行特征选择，确定有效目标特征；对无效特征依次通过方差阈值法、spearman相关性分析法和LASSO回归模型进行特征选择，确定无效目标特征。上述筛选出来的无效目标特征和有效目标特征为相同的特征，将无效目标特征或有效目标特征作为最优特征即第二特征。上述影像组学特征提取、方差阈值法、spearman相关性分析法和LASSO回归模型均为本领域技术人员公知的技术，在此不做赘述。上述最优特征指所有影像组学特征中对预测疗效影响较大的特征。Specifically, the above-mentioned second feature includes an invalid target feature and a valid target feature. Classify all patient target data according to the above curative effect markers. The curative effect markers are the patient target data with significant curative effect to form a significant curative effect data set, and the curative effect markers are non-curative target data to form the non-curative effect data set. The target image data in the above-mentioned significant curative effect data set and the non-curative effect data set were extracted for radiomics features, and 1688 kinds of radiomics features were extracted. The above-mentioned radiomics features were divided into four categories: first-order statistics, shape, texture and filtering . The radiomics features of the above four categories include a total of 1688 features, which are well known to those skilled in the art, and will not be repeated here. The radiomics features obtained from the above-mentioned significant curative effect data set constitute the effective features, and the above-mentioned radiomics features obtained from the non-curative effect data set constitute the invalid features. The above-mentioned target features include the above-mentioned effective features and the above-mentioned invalid features. According to the feature screening rules, the above-mentioned valid features and the above-mentioned invalid features, the invalid target features and the valid target features are determined. The above feature selection rules include variance threshold method, spearman correlation analysis method and LASSO regression model. In this embodiment, the effective features are sequentially selected through the variance threshold method, the spearman correlation analysis method and the LASSO regression model to determine the effective target features; the invalid features are sequentially selected through the variance threshold method, the spearman correlation analysis method and the LASSO regression model The model performs feature selection to identify invalid target features. The invalid target features and valid target features screened out above are the same features, and the invalid target features or valid target features are used as the optimal features, that is, the second features. The aforementioned radiomics feature extraction, variance threshold method, spearman correlation analysis method and LASSO regression model are all technologies well known to those skilled in the art, and will not be repeated here. The above optimal features refer to the features that have a greater impact on the prediction of curative effect among all radiomics features.
步骤S104：根据预设的训练模型、第一特征、第二特征和患者目标数据，确定目标预测模型。Step S104: Determine the target prediction model according to the preset training model, the first feature, the second feature and the patient target data.
具体的，将上述第一特征、第二特征和患者目标数据输入至预设的训练模型中，训练得到目标预测模型，上述训练模型为支持向量机。Specifically, the above-mentioned first feature, second feature and patient target data are input into a preset training model, and a target prediction model is obtained through training, and the above-mentioned training model is a support vector machine.
步骤S105：获取测试数据集并根据正确率计算规则和测试数据集，确定预测正确率。Step S105: Obtain the test data set and determine the prediction accuracy rate according to the accuracy rate calculation rules and the test data set.
具体的，获取测试数据集，测试数据集与患者数据的数据类型相同，测试数据集与患者数据的不同之处在于患者的患病时间不同，以某一时间节点为分界线，时间节点之前的患者的患病数据为上述训练目标预测模型用到的患者数据，时间节点之后的患者的患病数据为上述测试目标预测模型用到的测试数据集。上述时间节点为人为设定。根据上述测试数据集和上述目标预测模型，确定结果数据集。将上述测试数据集输入至上述目标预测模型，可以得到每个患者的治疗效果，上述治疗效果组成结果数据集。根据正确率计算规则、上述测试数据集和上述结果数据集，确定预测正确率。将结果数据集和测试数据集做对比，获取预测正确的患者数量，预测正确率=预测正确的患者数量/测试数据集的患者数量。例如，测试数据集中有10个患者数据，其中5个患者为无效治疗，5个患者为有效治疗，将测试数据集输入至目标预测模型，得到结果数据集，结果数据集中有8个患者为有效治疗，2个患者为无效治疗，其中8个患者中有5个为有效治疗即5个患者预测正确，2个患者为无效治疗均预测正确，则预测正确的患者数量为7个，则预测正确率为7/10=0.7。Specifically, the test data set is obtained. The data type of the test data set is the same as that of the patient data. The difference between the test data set and the patient data is that the patient's illness time is different. With a certain time node as the dividing line, the data before the time node The patient's disease data is the patient data used in the training target prediction model, and the patient's disease data after the time point is the test data set used in the test target prediction model. The above time nodes are artificially set. According to the above test data set and the above target prediction model, determine the result data set. The above-mentioned test data set is input into the above-mentioned target prediction model, and the treatment effect of each patient can be obtained, and the above-mentioned treatment effect forms the result data set. Determine the prediction accuracy rate according to the accuracy rate calculation rules, the above test data set and the above result data set. Compare the result data set with the test data set to obtain the number of correctly predicted patients, and the predicted correct rate = the number of correctly predicted patients/the number of patients in the test data set. For example, there are 10 patient data in the test data set, 5 patients are ineffective treatment, 5 patients are effective treatment, input the test data set into the target prediction model to get the result data set, 8 patients in the result data set are effective Treatment, 2 patients are ineffective treatment, 5 of the 8 patients are effective treatment, that is, 5 patients are predicted correctly, and 2 patients are ineffective treatment, and the prediction is correct, then the number of patients with correct prediction is 7, and the prediction is correct The rate is 7/10=0.7.
在使用目标预测模型对某一患者进行术后疗效预测时，获取待预测患者数据，待预测患者数据和上述患者数据类型相同，将待预测患者数据中的结石发生图像输入至上述目标肾脏分割模型，得到与患者对应的第一特征，然后根据特征确定规则和结石发生图像，确定与患者对应的第二特征。然后将待预测患者数据、对应的第一特征和第二特征输入至目标预测模型时，目标预测模型会输出预测的疗效，包括疗效显著和无疗效两种预测结果。When using the target prediction model to predict the postoperative curative effect of a certain patient, obtain the data of the patient to be predicted, the data of the patient to be predicted is of the same type as the above patient data, and input the stone occurrence image in the data of the patient to be predicted to the above target kidney segmentation model , to obtain the first feature corresponding to the patient, and then determine the second feature corresponding to the patient according to the feature determination rule and the calculus occurrence image. Then, when the patient data to be predicted, the corresponding first feature and the second feature are input into the target prediction model, the target prediction model will output the predicted therapeutic effect, including two prediction results of significant curative effect and no curative effect.
本申请实施例提供一种肾结石术后疗效评估系统200，参照图2，肾结石术后疗效评估系统200包括：The embodiment of the present application provides a curative
数据获取模块201，用于获取患者数据、第一特征和待预测患者数据；A
数据处理模块202，用于根据预设的数据归一规则和所述患者数据，确定患者目标数据；A
特征提取模块203，用于根据预设的特征确定规则和所述患者目标数据，确定第二特征；A
模型训练模块204，用于根据预设的训练模型、所述第一特征、所述第二特征和所述患者目标数据，确定目标预测模型；A
疗效预测模块205，用于根据正确率计算规则、所述待预测患者数据和所述目标预测模型，确定患者术后疗效。The curative
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，所描述的模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the described modules can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.
本申请实施例公开一种电子设备。参照图3，电子设备包括，包括中央处理单元(CPU)301，其可以根据存储在只读存储器(ROM)302中的程序或者从存储部分307加载到随机访问存储器(RAM)303中的程序而执行各种适当的动作和处理。在RAM 303中，还存储有系统操作所需的各种程序和数据。CPU 301、ROM 302以及RAM 303通过总线彼此相连。输入/输出(I/O)接口304也连接至总线。The embodiment of the present application discloses an electronic device. Referring to FIG. 3 , the electronic device includes, including a central processing unit (CPU) 301, which can operate according to a program stored in a read-only memory (ROM) 302 or a program loaded from a
以下部件连接至I/O接口304：包括键盘、鼠标等的输入部分305；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分306；包括硬盘等的存储部分307；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分308。通信部分308经由诸如因特网的网络执行通信处理。驱动器309也根据需要连接至I/O接口304。可拆卸介质310，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器309上，以便于从其上读出的计算机程序根据需要被安装入存储部分307。The following components are connected to the I/O interface 304: an
特别地，根据本申请的实施例，上文参考流程图图1描述的过程可以被实现为计算机软件程序。例如，本申请的实施例包括一种计算机程序产品，其包括承载在机器可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分308从网络上被下载和安装，和/或从可拆卸介质310被安装。在该计算机程序被中央处理单元(CPU)301执行时，执行本申请的装置中限定的上述功能。In particular, according to an embodiment of the present application, the process described above with reference to the flowchart FIG. 1 may be implemented as a computer software program. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a machine-readable medium, where the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via
需要说明的是，本申请所示的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。It should be noted that the computer-readable medium shown in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program codes are carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的申请范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离前述申请构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中申请的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。The above description is only a preferred embodiment of the present application and an illustration of the applied technical principle. Those skilled in the art should understand that the application scope involved in this application is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover the technical solutions made by the above-mentioned technical features or Other technical solutions formed by any combination of equivalent features. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions in this application.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310052949.5ACN115910379B (en) | 2023-02-03 | 2023-02-03 | A method, system, device and storage medium for evaluating curative effect after renal calculus surgery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310052949.5ACN115910379B (en) | 2023-02-03 | 2023-02-03 | A method, system, device and storage medium for evaluating curative effect after renal calculus surgery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115910379A CN115910379A (en) | 2023-04-04 |
| CN115910379Btrue CN115910379B (en) | 2023-06-02 |
Family
ID=86481092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310052949.5AActiveCN115910379B (en) | 2023-02-03 | 2023-02-03 | A method, system, device and storage medium for evaluating curative effect after renal calculus surgery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115910379B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116205915B (en)* | 2023-04-28 | 2023-07-14 | 北京航空航天大学 | A mask-based brain age assessment method, system and electronic equipment |
| CN118762005B (en)* | 2024-09-05 | 2024-11-12 | 华中科技大学同济医学院附属同济医院 | Coordinate positioning method and system for kidney stones based on preoperative CT and intraoperative ultrasound images |
| CN118969194B (en)* | 2024-10-18 | 2024-12-31 | 佛山复星禅诚医院有限公司 | Safety analysis method for upper urinary tract calculus postoperative pipeless |
| CN119092154B (en)* | 2024-11-05 | 2025-01-28 | 西安医学院第一附属医院 | Intelligent uropoiesis surgery postoperative rehabilitation effect monitoring system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112951406A (en)* | 2021-01-27 | 2021-06-11 | 安徽理工大学 | Lung cancer prognosis auxiliary evaluation method and system based on CT (computed tomography) image omics |
| CN115526824A (en)* | 2022-01-27 | 2022-12-27 | 深圳惟德精准医疗科技有限公司 | Image processing method and related device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8315812B2 (en)* | 2010-08-12 | 2012-11-20 | Heartflow, Inc. | Method and system for patient-specific modeling of blood flow |
| WO2016141449A1 (en)* | 2015-03-09 | 2016-09-15 | Her Majesty The Queen In Right Of Canada, As Represented By The Minister Of The Department Of National Defence | Computer-assisted focused assessment with sonography in trauma |
| EP4348678A1 (en)* | 2021-05-28 | 2024-04-10 | University of Southern California | A radiomic-based machine learning algorithm to reliably differentiate benign renal masses from renal cell carcinoma |
- 2023
- 2023-02-03CNCN202310052949.5Apatent/CN115910379B/enactiveActive
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112951406A (en)* | 2021-01-27 | 2021-06-11 | 安徽理工大学 | Lung cancer prognosis auxiliary evaluation method and system based on CT (computed tomography) image omics |
| CN115526824A (en)* | 2022-01-27 | 2022-12-27 | 深圳惟德精准医疗科技有限公司 | Image processing method and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115910379A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115910379B (en) | A method, system, device and storage medium for evaluating curative effect after renal calculus surgery | |
| US11488306B2 (en) | Immediate workup | |
| CN107895367B (en) | Bone age identification method and system and electronic equipment | |
| CN112184656B (en) | Method and device for determining fetal section based on ultrasonic dynamic image | |
| JP6023235B2 (en) | Medical imaging method and apparatus for disease diagnosis and monitoring and uses thereof | |
| CN111415321B (en) | Aneurysm rupture risk detection device and equipment | |
| CN105653858A (en) | Image omics based lesion tissue auxiliary prognosis system and method | |
| JP3928978B1 (en) | Medical image processing apparatus, medical image processing method, and program | |
| CN112183572B (en) | Method and device for generating prediction model for predicting severity of pneumonia | |
| CN111027548B (en) | Brain glioma molecular marker nondestructive prediction method and system based on image histology | |
| CN115222674A (en) | Detection device for rupture risk of intracranial aneurysm based on multidimensional feature fusion | |
| CN119048440B (en) | Bone fracture image auxiliary detection system based on data analysis | |
| CN212853503U (en) | Intelligent liver tumor analysis device | |
| CN114881976B (en) | Method, device and computer equipment for determining standard cross-section images of femur and humerus | |
| CN110648318A (en) | Auxiliary analysis method and device for skin diseases, electronic equipment and storage medium | |
| JP2019508146A (en) | Method and apparatus for identifying and quantifying anomalies | |
| CN116934743B (en) | Medical image tumor malignancy risk assessment method, system, equipment and storage medium | |
| US20240225588A1 (en) | Method and Apparatus of Intelligent Analysis for Liver Tumor | |
| CN118762849A (en) | An intelligent processing method and system for urology diagnosis and treatment data | |
| CN114708971A (en) | Risk assessment method and device, storage medium and electronic equipment | |
| Nakamae et al. | AI prediction of extracorporeal shock wave lithotripsy outcomes for ureteral stones by machine learning-based analysis with a variety of stone and patient characteristics | |
| CN115089112B (en) | Post-stroke cognitive impairment risk assessment model building method and device and electronic equipment | |
| CN115620861A (en) | Evaluation method and system for the treatment of thyroid cancer in the elderly based on multimodal omics | |
| WO2020199692A1 (en) | Method and apparatus for screening predictive image features for cancer metastasis, and storage medium | |
| Duryea et al. | Neural network based automated algorithm to identify joint locations on hand/wrist radiographs for arthritis assessment |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | Denomination of invention:A method, system, equipment, and storage medium for evaluating the postoperative efficacy of kidney stones Granted publication date:20230602 Pledgee:Haidian Beijing science and technology enterprise financing Company limited by guarantee Pledgor:Huiying medical technology (Beijing) Co.,Ltd. Registration number:Y2024110000065 | |
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right | Granted publication date:20230602 Pledgee:Haidian Beijing science and technology enterprise financing Company limited by guarantee Pledgor:Huiying medical technology (Beijing) Co.,Ltd. Registration number:Y2024110000065 | |
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | Denomination of invention:A method, system, equipment, and storage medium for evaluating the postoperative efficacy of kidney stones Granted publication date:20230602 Pledgee:Haidian Beijing science and technology enterprise financing Company limited by guarantee Pledgor:Huiying medical technology (Beijing) Co.,Ltd. Registration number:Y2025110000181 | |
| PE01 | Entry into force of the registration of the contract for pledge of patent right |