Coronary artery low-calcification integral plaque prediction method, device, equipment and medium

Abstract

The invention discloses a coronary artery low-calcification integral plaque prediction method, device and equipment and a medium, and relates to the technical field of medical image processing, and the method comprises the steps: obtaining clinical laboratory data and a scanning image set of a plurality of low-calcification integral patients; wherein each scanning image set comprises a heart CT plain scanning image and a coronary artery CTA image; image omics features are extracted from all the scanning image sets; constructing a prediction model according to clinical laboratory data and radiomics characteristics; and predicting a coronary artery soft plaque prediction result of the corresponding low-calcification integral patient according to the radiomics characteristics by using the prediction model. More information except for CT attenuation of coronary peripheral fat can be provided according to the radiomics characteristics, so that a real prediction model can be constructed by combining clinical laboratory data, and whether soft plaques exist in coronary arteries of low-calcification integral patients or not can be accurately predicted according to the radiomics characteristics by utilizing the prediction model.

Description

Technical Field

[0001] The present application relates to the field of medical image processing technology, and in particular to a method, device, equipment and medium for predicting coronary artery hypocalcified integrated plaque. Background Art

[0002] In recent years, the fat attenuation index (FAI) of the right coronary artery pericoronary adipose tissue (PCAT) measured based on coronary computed tomography angiography (CTA) images has been shown to be a new sensitive marker for the degree of coronary artery inflammation and can be used as an imaging marker for predicting coronary artery sclerosis. However, the occurrence of coronary artery inflammation can change the composition of PCAT through various processes, causing some irreversible morphological changes, such as fibrosis and microvascular remodeling. Since the CT attenuation of PCAT is only based on the voxel intensity value, the complex spatial relationship between voxels is not considered. Patients with low calcium score have fewer soft plaques in the coronary arteries, which are more difficult to detect in cardiac CT plain scan images. Therefore, the relevant technology is still not accurate enough for the detection of coronary artery sclerosis in patients with low calcium score. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose a method, device, equipment and medium for predicting coronary artery low calcification score plaques to accurately predict whether there are soft plaques in the coronary arteries of patients with low calcification scores.

[0004] To achieve the above-mentioned purpose, a method for predicting coronary artery hypocalcified integrated plaque is provided in one aspect of an embodiment of the present application. The method comprises the following steps:

[0005] Acquire clinical laboratory data and scan image sets of multiple patients with low calcium scores; wherein each of the scan image sets includes a cardiac CT plain scan image and a coronary artery CTA image;

[0006] Extracting radiomics features from each of the scanned image sets;

[0007] constructing a prediction model based on the clinical laboratory data and the radiomics features;

[0008] The prediction model is used to predict the coronary soft plaque prediction result corresponding to the patient with low calcification score according to the imaging omics characteristics.

[0009] In some embodiments, the step of obtaining clinical laboratory data and scan image sets of multiple patients with low calcium scores comprises the following steps:

[0010] Acquire the clinical laboratory data and the scan image set of a group of patients suspected of having coronary heart disease; wherein each of the scan image sets includes the cardiac CT plain scan image and the coronary artery CTA image;

[0011] Screening a plurality of patients with low calcification scores from each of the suspected coronary heart disease patients according to the cardiac CT plain scan images;

[0012] Acquiring the coronary artery CTA image of each of the patients with low calcium scores;

[0013] Detecting whether there is a plaque in each of the coronary artery CTA images;

[0014] The coronary artery CTA image in which plaque is detected and the corresponding cardiac CT plain scan image are determined as the scan image set.

[0015] In some embodiments, the step of screening a plurality of patients with low calcium scores from each of the suspected coronary heart disease patients according to the cardiac CT plain scan images comprises the following steps:

[0016] Calculating the calcification score of each blood vessel according to the cardiac CT plain scan image using a heartbeat detection workstation;

[0017] Accumulating the calcification scores of all blood vessels in each of the cardiac CT plain scan images to obtain a corresponding total calcification score;

[0018] The suspected coronary heart disease patients whose total calcification scores are lower than a preset threshold are selected as the low calcification score patients.

[0019] In some embodiments, the detecting whether there is a plaque in each of the coronary artery CTA images comprises the following steps:

[0020] Using the Digital Plaque Identification Software to detect whether plaques exist in each of the coronary artery CTA images;

[0021] The digital plaque recognition software is used to annotate the type and CT attenuation value of the plaque in the coronary artery CTA image with plaque.

[0022] In some embodiments, the step of extracting radiomics features from each of the scanned image sets comprises the following steps:

[0023] Delineating a region of interest on the cardiac CT plain scan image;

[0024] Using 3D Slicer software to segment the cardiac CT plain scan image to obtain the region of interest;

[0025] The radiomics package was used to extract the radiomics features of the region of interest on the pyhon platform.

[0026] In some embodiments, delineating a region of interest on the cardiac CT plain scan image comprises the following steps:

[0027] Determining voxels having CT attenuation values ​​within an attenuation value threshold range in the cardiac CT plain scan image;

[0028] Coronary artery fat whose distance from the right coronary artery ostium is within a distance threshold range and whose thickness is equal to the vessel diameter is selected from the voxels as the region of interest.

[0029] In some embodiments, constructing a prediction model based on the clinical laboratory data and the radiomics features comprises the following steps:

[0030] A T test is performed on the radiomics features that conform to the normal distribution, and a Mann-Whitney U test is performed on the radiomics features that do not conform to the normal distribution, and each radiomics feature whose probability value is less than or equal to the probability threshold is retained as the first feature;

[0031] Calculating the Spearman correlation coefficient between each of the imaging features and the coronary artery plaque, and retaining each of the imaging features whose absolute value of the Spearman correlation coefficient is greater than a coefficient threshold as the second feature;

[0032] The random forest method is used to select the first several radiomics features with the highest importance scores as the third feature;

[0033] Taking the intersection of each of the first features, each of the second features, and each of the third features to obtain a target feature set;

[0034] The prediction model is constructed based on the clinical laboratory data and the target feature set using the LASSO method.

[0035] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application provides a coronary artery hypocalcified integrated plaque prediction device, the device comprising:

[0036] An image acquisition unit, used to acquire clinical laboratory data and scan image sets of multiple patients with low calcium scores; wherein each of the scan image sets includes a cardiac CT plain scan image and a coronary artery CTA image;

[0037] A feature extraction unit, used for extracting radiomics features from each of the scanned image sets;

[0038] A model building unit, used for building a prediction model based on the clinical laboratory data and the radiomics features;

[0039] A plaque prediction unit is used to predict the coronary soft plaque prediction result of the patient with low calcification score by using the prediction model according to the imaging genomics characteristics.

[0040] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above method when executing the computer program.

[0041] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0042] The embodiments of the present application include at least the following beneficial effects:

[0043] This application can obtain clinical laboratory data and scan image sets of multiple patients with low calcification scores; wherein each scan image set includes cardiac CT plain scan images and coronary artery CTA images; extract radiomic features from each scan image set; construct a prediction model based on clinical laboratory data and radiomic features; and use the prediction model to predict the prediction results of coronary soft plaques in patients with low calcification scores based on radiomic features. Radiomic features can provide more information than pericoronary fat CT attenuation, so a more realistic prediction model can be constructed in combination with clinical laboratory data, and the prediction model can be used to accurately predict whether there are soft plaques in the coronary arteries of patients with low calcification scores based on radiomic features. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A schematic diagram of a flow chart of a method for predicting coronary artery hypocalcified integrated plaques provided in an embodiment of the present application;

[0046] Figure 2 ROC curve diagram of the prediction model provided in the embodiment of the present application on the training set and the validation set;

[0047] Figure 3 A calibration curve diagram of the training set prediction model provided in the embodiment of the present application;

[0048] Figure 4A calibration curve diagram of the validation set prediction model provided in the embodiment of the present application;

[0049] Figure 5 A schematic diagram of the structure of a coronary artery hypocalcified integrated plaque prediction device provided in an embodiment of the present application;

[0050] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0052] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0053] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0055] The embodiment of the present application provides a method for predicting coronary hypocalcification integrated plaques, which relates to the field of medical image processing technology. The method for predicting coronary hypocalcification integrated plaques provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the method for predicting coronary hypocalcification integrated plaques, etc., but is not limited to the above forms.

[0056] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0057] Reference Figure 1 The present application embodiment provides a method for predicting coronary artery hypocalcified integrated plaques. The method may include but is not limited to S100 to S130, which are as follows:

[0058] S100: Acquire clinical laboratory data and scan image sets of multiple patients with low calcium scores; wherein each of the scan image sets includes a cardiac CT plain scan image and a coronary artery CTA image.

[0059] First of all, it should be noted that coronary artery plaques are divided into soft plaques and hard plaques, among which hard plaques can be directly found in both cardiac CT plain scan images and coronary artery CTA images without the need for prediction; soft plaques cannot be directly found in cardiac CT plain scan images, but the embodiments of the present application can predict whether there are soft plaques in the coronary arteries of patients with low calcification scores based on cardiac CT plain scan images.

[0060] Specifically, each patient with a low calcium score has their own corresponding clinical laboratory data and scan image set, that is, this embodiment can obtain multiple clinical laboratory data and multiple scan image sets, among which cardiac CT plain scan examination and coronary artery CTA examination can be performed simultaneously, and corresponding cardiac CT plain scan images and coronary artery CTA images can be obtained.

[0061] Illustratively, the clinical laboratory data of this embodiment may include: gender, age, body mass index (BMI), hemoglobin, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, triglycerides, hypertension, diabetes, and dyslipidemia.

[0062] In this embodiment, patients with low calcification scores can be screened according to the coronary artery calcification scores. For example, patients whose coronary artery calcification scores are within a set range are classified as patients with low calcification scores.

[0063] Furthermore, S100 may include S101 to S105:

[0064] S101: Acquire the clinical laboratory data and the scan image set of a group of patients suspected of having coronary heart disease; wherein each of the scan image sets includes the cardiac CT plain scan image and the coronary artery CTA image;

[0065] S102: Screening a plurality of patients with low calcification scores from each of the suspected coronary heart disease patients according to the cardiac CT plain scan image;

[0066] S103: Acquire the coronary artery CTA image of each patient with low calcification score;

[0067] S104: Detecting whether there is a plaque in each of the coronary artery CTA images;

[0068] S105: The coronary artery CTA image in which plaques are detected and the corresponding cardiac CT plain scan image are determined as the scan image set.

[0069] Specifically, since cardiac CT plain scan images cannot show whether the coronary arteries have soft plaques, this embodiment can determine whether the patient's coronary arteries have plaques through coronary artery CTA images (cardiac CT plain scan examination and CTA examination are performed simultaneously) to determine positive samples for the presence of plaques in the coronary arteries.

[0070] Furthermore, S102 may include:

[0071] Calculating the calcification score of each blood vessel according to the cardiac CT plain scan image using a heartbeat detection workstation;

[0072] Accumulating the calcification scores of all blood vessels in each of the cardiac CT plain scan images to obtain a corresponding total calcification score;

[0073] The suspected coronary heart disease patients whose total calcification scores are lower than a preset threshold are selected as the low calcification score patients.

[0074] Exemplarily, this embodiment can use the heartbeat detection workstation (Philips Heartbeat-CS) to calculate the Agatston score (i.e., calcification score) of each blood vessel for the cardiac CT plain scan image; according to the Agatston scoring method, the sum of the scores of each coronary artery is the total calcification score. Calcification degree grading method: a total calcification score of 0 means no calcification, a total calcification score of 1-99 means mild calcification, a total calcification score of 100-399 means moderate calcification, and a total calcification score greater than or equal to 400 means severe calcification; this embodiment can set the preset threshold to 100, that is, patients with a total calcification score lower than 100 are regarded as patients with low calcification scores.

[0075] Furthermore, S104 may include:

[0076] Using the Digital Plaque Identification Software to detect whether plaques exist in each of the coronary artery CTA images;

[0077] The digital plaque recognition software is used to annotate the type and CT attenuation value of the plaque in the coronary artery CTA image with plaque.

[0078] Exemplarily, the coronary artery CTA image is sent to the Shukun plaque recognition software, which automatically identifies whether the coronary artery has plaques and provides information such as the type of plaque and CT attenuation value, such as calcified plaque (≥350HU), fibrous plaque (130-349HU), lipid fibrous plaque (30-129HU), and lipid plaque (<30HU). If necessary, the coronary artery CTA image of a certain patient can also be manually selected as the coronary artery CTA image with plaques.

[0079] S110: Extracting radiomics features from each of the scanned image sets.

[0080] Specifically, this embodiment can extract corresponding radiomics features from the scan image set of each patient with low calcification score.

[0081] Furthermore, S110 may include S111 to S113:

[0082] S111: outlining a region of interest on the cardiac CT plain scan image;

[0083] S112: Segmenting the region of interest from the cardiac CT plain scan image using 3D Slicer software;

[0084] S113: extracting the radiomics features of the region of interest on the pyhon platform using the radiomics package.

[0085] Exemplarily, a cardiac CT plain scan image is exported in a digital imaging and communications in medicine (DICOM) format, and then the 3DSlicer software is used to segment the cardiac CT plain scan image to obtain a region of interest, and then the radiomics package is used to extract features of the segmented region of interest on the pyhon platform. The features may include 7 major categories and sub-category features under each major category, namely: firstorder (360 sub-categories), glcm (440 sub-categories), dldm (280 sub-categories), glrllm (320 sub-categories), glszm (320 sub-categories), ngtdm (100 sub-categories), shape (14 sub-categories), a total of 1834 features; among which, firstorder is a first-order feature, glcm (gray level co-occurrence matrix) is a gray level co-occurrence matrix, dldm (gray level dependence matrix) is a gray level dependence matrix, grllm (gray level run length matrix) is a gray level run length matrix, glszm (gray level size zone matrix) is a gray level area size matrix, ngtdm (neighbouring graytone difference matrix) is the adjacent grayscale difference matrix, and shape is the shape feature.

[0086] Furthermore, S111 may include:

[0087] Determining voxels having CT attenuation values ​​within an attenuation value threshold range in the cardiac CT plain scan image;

[0088] Coronary artery fat whose distance from the right coronary artery ostium is within a distance threshold range and whose thickness is equal to the vessel diameter is selected from the voxels as the region of interest.

[0089] Exemplarily, the attenuation value threshold range may be between -190 and -30 HU, where HU is a unit of CT attenuation value, and the distance threshold range may be between 10 and 50 mm.

[0090] S120: Constructing a prediction model based on the clinical laboratory data and the imaging genomics features.

[0091] Specifically, this embodiment can build a prediction model by combining the clinical laboratory data and radiomics features of each patient with low calcification score.

[0092] Furthermore, S120 may include S121 to S125:

[0093] S121: performing a T test on the radiomics features that conform to the normal distribution, performing a Mann-Whitney U test on the radiomics features that do not conform to the normal distribution, and retaining each radiomics feature whose probability value is less than or equal to the probability threshold as the first feature;

[0094] S122: calculating the Spearman correlation coefficient between each of the imaging omics features and the coronary artery plaque, and retaining each of the imaging omics features whose absolute value of the Spearman correlation coefficient is greater than a coefficient threshold as a second feature;

[0095] S123: using a random forest method to select the first several radiomics features with the highest importance scores as the third feature;

[0096] S124: Taking the intersection of each of the first features, each of the second features, and each of the third features to obtain a target feature set;

[0097] S125: Using the LASSO method to construct the prediction model according to the clinical laboratory data and the target feature set.

[0098] For example, the probability threshold may be 0.05, the coefficient threshold may be 0.1, and the third feature may be the top 50 radiomics features with the highest importance scores.

[0099] The LASSO method is a regression analysis method that can perform variable selection and complexity adjustment. It selects and shrinks features through the absolute value of the penalty coefficient, which helps reduce overfitting of the prediction model and improves prediction accuracy. Cross-validation (such as K-fold cross-validation) is usually used to determine the regularization parameter (λ) in the LASSO method, which is used to control the intensity of the penalty, thereby affecting the sparsity of the prediction model. For example, assuming there are 100 features to be processed, 20 features may be obtained after processing by the LASSO method.

[0100] S130: Using the prediction model to predict the coronary soft plaque prediction result corresponding to the patient with low calcification score according to the radiomics features.

[0101] Specifically, the prediction model can output the prediction probability value corresponding to each patient with low calcification score based on the imaging genomics characteristics. When the prediction probability value reaches a preset threshold, it can be considered that the patient with low calcification score has soft plaque in the coronary artery.

[0102] The embodiment of the present application may also include the following steps:

[0103] The target feature set was divided into training set and validation set in a ratio of 7:3. Sensitivity, specificity and receiver operating characteristic (ROC) curve were used to evaluate the predictive ability of the prediction model in the training set and validation set respectively. The Hosmer-Lemeshow test and calibration curve were used to analyze the consistency between the predicted risk and the actual observation.

[0104] Next, the solution of the embodiment of the present application will be described in detail and explained in conjunction with specific application examples:

[0105] Specifically, this embodiment includes the following steps:

[0106] S1: Collect clinical laboratory data, cardiac CT plain scan images, and coronary artery CTA images of patients with low calcium scores;

[0107] S2: delineate the region of interest on the cardiac CT plain scan image and extract radiomics features;

[0108] S3: The patient data (including clinical laboratory information, cardiac CT plain scan images, and coronary artery CTA images) were randomly divided into a training set and a validation set in a ratio of 7:3, and the imaging features were screened on the training set;

[0109] S4: All clinical laboratory data and radiomics features are integrated to build a prediction model on the training set;

[0110] S5: Use the prediction model to output the prediction results of coronary artery soft plaque in patients with low calcium scores.

[0111] Wherein, S1 includes the following steps:

[0112] S11: Obtain clinical laboratory data including: sex, age, body mass index (BMI), hemoglobin, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, triglycerides, hypertension, diabetes, and dyslipidemia;

[0113] S12: Perform cardiac CT scan and coronary artery CTA examinations simultaneously in patients suspected of coronary heart disease;

[0114] S13: The heartbeat detection workstation (Philips Heartbeat-CS) was used to calculate the Agatston score of each blood vessel for the cardiac CT plain scan images; according to the Agatston scoring method, the sum of the scores of each coronary artery was the total calcification score. Calcification degree grading method: CACS score 0 means no calcification, 1-99 means mild calcification, 100-399 means moderate calcification, and ≥400 means severe calcification;

[0115] S14: Send the coronary artery CTA image to the Shukun plaque recognition software, which automatically identifies whether the coronary artery has plaques and provides information such as the type of plaque and CT attenuation value, such as calcified plaque (≥350HU), fibrous plaque (130-349HU), lipid fibrous plaque (30-129HU), and lipid plaque (<30HU). If necessary, the coronary artery CTA image of a certain patient can also be manually selected as the coronary artery CTA image with plaques.

[0116] Wherein, S2 includes the following steps:

[0117] S21: Cardiac CT plain scan images were exported in Digital Imaging and Communications in Medicine (DICOM) format, and 3D Slicer software was used to perform pericoronary artery fat (PCAT) segmentation;

[0118] S22: The radiomics package was used on the pyhon platform to extract radiomics features from the segmented images of pericoronary artery fat (PCAT), and 7 major categories and sub-category features under each major category were proposed, namely: firstorder (360 sub-categories), glcm (440 sub-categories), gldm (280 sub-categories), glrlm (320 sub-categories), glszm (320 sub-categories), ngtdm (100 sub-categories), shape (14 sub-categories), a total of 1834 features.

[0119] Wherein, S21 includes the following steps:

[0120] S211: PCAT is defined as all voxels with CT attenuation values ​​between −190 and −30 HU;

[0121] S212: The PCAT around the proximal segment of the right coronary artery (RCA) (10-50 mm from the RCA ostium) and with a thickness equal to the vessel diameter is selected as the region of interest (ROI).

[0122] Among them, S3 includes the following steps:

[0123] S31: Perform T test on the combined image features that obey normal distribution, perform Mann-Whitney U test on the combined image features that do not obey normal distribution, and retain the combined image features with probability values ​​less than or equal to 0.05;

[0124] S32: Calculate the Spearman correlation coefficient between the combined image features and the coronary artery plaques, and retain the combined image features with an absolute value of the correlation coefficient greater than 0.1;

[0125] S33: The top 50 combined image features with the highest importance scores were selected using the random forest method;

[0126] S34: Take the intersection of the features extracted from S31-S33 as the target feature set;

[0127] Exemplarily, the target feature set may include 35 radiomics features:

[0128] "exponential_firstorder_Kurtosis";

[0129] "lbp_3D_m1_glszm_SizeZoneNonUniformity";

[0130] "lbp_3D_m2_glcm_Imc2""lbp_3D_m2_glszm_SizeZoneNonUniformity";

[0131] "log_sigma_3_0_mm_3D_firstorder_MeanAbsoluteDeviation";

[0132] "log_sigma_3_0_mm_3D_firstorder_RootMeanSquared";

[0133] "log_sigma_3_0_mm_3D_glcm_Id";

[0134] "log_sigma_3_0_mm_3D_glcm_Idmn";

[0135] "log_sigma_3_0_mm_3D_glcm_Idn";

[0136] "log_sigma_3_0_mm_3D_glcm_InverseVariance";

[0137] "log_sigma_3_0_mm_3D_glszm_GrayLevelVariance";

[0138] "log_sigma_3_0_mm_3D_ngtdm_Contrast";

[0139] "logarithm_firstorder_Kurtosis";

[0140] "original_firstorder_Kurtosis";

[0141] "original_glcm_Idmn""original_shape_Elongation";

[0142] "original_shape_Maximum2DDiameterRow";

[0143] "original_shape_MinorAxisLength";

[0144] "square_firstorder_Kurtosis";

[0145] "square_glcm_Idmn";

[0146] "square_glcm_Idn";

[0147] "squareroot_firstorder_Kurtosis";

[0148] "wavelet_HHH_firstorder_Minimum";

[0149] "wavelet_HHH_glcm_Autocorrelation";

[0150] "wavelet_HHH_glcm_JointAverage";

[0151] "wavelet_HHH_gldm_LargeDependenceHighGrayLevelEmphasis";

[0152] "wavelet_HHH_glrlm_GrayLevelVariance";

[0153] "wavelet_HHH_glrlm_HighGrayLevelRunEmphasis";

[0154] "wavelet_HHH_glrlm_LongRunHighGrayLevelEmphasis";

[0155] "wavelet_HHH_glrlm_ShortRunHighGrayLevelEmphasis";

[0156] "wavelet_HHH_glszm_HighGrayLevelZoneEmphasis";

[0157] "wavelet_HHH_glszm_LargeAreaHighGrayLevelEmphasis";

[0158] "wavelet_HHH_glszm_SmallAreaHighGrayLevelEmphasis";

[0159] "wavelet_HHL_gldm_SmallDependenceHighGrayLevelEmphasis";

[0160] "wavelet_HHL_ngtdm_Complexity".

[0161] Wherein, S4 includes the following steps:

[0162] In the training set, all clinical laboratory data + imaging omics features were used to construct a prediction model for coronary artery plaques using the LASSO method;

[0163] The prediction model construction formula is:

[0164]

[0165] Wherein, S5 comprises the following steps:

[0166] In the training set and validation set, the sensitivity, specificity and receiver operating characteristic (ROC) curve were used to evaluate the predictive ability of the model; the Hosmer-Lemeshow test and calibration curve were used to analyze the consistency between the predicted risk and the actual observation.

[0167] Example results are as follows Figure 2As shown in the figure, the AUC area, sensitivity and specificity values ​​of the training set were 0.821 (95% CI: 0.774-0.868), 0.574 and 0.896, respectively. The AUC area, sensitivity and specificity values ​​of the validation set were 0.719 (95% CI: 0.632-0.806), 0.844 and 0.425, respectively. This indicates that the coronary artery plaque prediction model for patients with low calcium score based on radiomics has good accuracy.

[0168] like Figure 3 , Figure 4 As shown in the figure, the Hosmer-Lemeshow test found that the predicted probability and the true probability in the training set and the validation set had a good fit (P>0.05). The P values ​​in the training set and the validation set were 0.923 and 0.809, respectively.

[0169] Compared with the prior art, the beneficial effects of this embodiment include:

[0170] This embodiment provides a method for predicting coronary artery low calcification score plaques, which is based on cardiac CT plain scan images, coronary artery CTA images, and integrates clinical laboratory data-radiomic features to predict coronary artery plaques in patients with low calcification scores. This embodiment can achieve accurate prediction of coronary soft plaques in patients with low calcification scores by establishing a radiomic feature prediction model of fat around the right coronary artery on the basis of a relatively low dose of cardiac CT plain scan.

[0171] Reference Figure 5 The embodiment of the present application further provides a coronary artery hypocalcification integrated plaque prediction device, which can implement the above-mentioned coronary artery plaque soft prediction method, and the device includes:

[0172] An image acquisition unit, used to acquire clinical laboratory data and scan image sets of multiple patients with low calcium scores; wherein each of the scan image sets includes a cardiac CT plain scan image and a coronary artery CTA image;

[0173] A feature extraction unit, used for extracting radiomics features from each of the scanned image sets;

[0174] A model building unit, used for building a prediction model based on the clinical laboratory data and the radiomics features;

[0175] A plaque prediction unit is used to predict the coronary soft plaque prediction result of the patient with low calcification score by using the prediction model according to the imaging genomics characteristics.

[0176] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0177] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above coronary artery hypocalcified integrated plaque prediction method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0178] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0179] See also Figure 6 , Figure 6 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0180] The processor 601 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0181] The memory 602 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 602, and the processor 601 calls and executes the method for predicting coronary artery hypocalcified integrated plaques in the embodiment of this application;

[0182] Input / output interface 603, used to implement information input and output;

[0183] Communication interface 604, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0184] Bus 605 , which transmits information between various components of the device (e.g., processor 601 , memory 602 , input / output interface 603 , and communication interface 604 );

[0185] The processor 601 , the memory 602 , the input / output interface 603 and the communication interface 604 are connected to each other in communication within the device via a bus 605 .

[0186] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned coronary artery hypocalcified integrated plaque prediction method is implemented.

[0187] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0188] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0189] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0190] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0191] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0192] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0193] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0194] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0195] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0196] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0197] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0198] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0199] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for predicting coronary artery hypocalcified integrated plaques, characterized in that: The method comprises the following steps: Acquire clinical laboratory data and scan image sets of multiple patients with low calcium scores; wherein each of the scan image sets includes a cardiac CT plain scan image and a coronary artery CTA image; Extracting radiomics features from each of the scanned image sets; constructing a prediction model based on the clinical laboratory data and the radiomics features; The prediction model is used to predict the coronary soft plaque prediction result corresponding to the patient with low calcification score according to the imaging omics characteristics.

2. A method for predicting coronary artery hypocalcified integrated plaque according to claim 1, characterized in that: The method of obtaining clinical laboratory data and scan image sets of multiple patients with low calcium scores includes the following steps: Acquire the clinical laboratory data and the scan image set of a group of patients suspected of having coronary heart disease; wherein each of the scan image sets includes the cardiac CT plain scan image and the coronary artery CTA image; Screening a plurality of patients with low calcification scores from each of the suspected coronary heart disease patients according to the cardiac CT plain scan images; Acquiring the coronary artery CTA image of each of the patients with low calcium scores; Detecting whether there is a plaque in each of the coronary artery CTA images; The coronary artery CTA image in which plaque is detected and the corresponding cardiac CT plain scan image are determined as the scan image set.

3. A method for predicting coronary artery hypocalcified integrated plaque according to claim 2, characterized in that: The method of obtaining a plurality of patients with low calcification scores from each of the suspected coronary heart disease patients according to the cardiac CT plain scan images comprises the following steps: Calculating the calcification score of each blood vessel according to the cardiac CT plain scan image using a heartbeat detection workstation; Accumulating the calcification scores of all blood vessels in each of the cardiac CT plain scan images to obtain a corresponding total calcification score; The suspected coronary heart disease patients whose total calcification scores are lower than a preset threshold are selected as the low calcification score patients.

4. A method for predicting coronary artery hypocalcified integrated plaque according to claim 2, characterized in that: The detecting whether there is a plaque in each of the coronary artery CTA images comprises the following steps: Using the Digital Plaque Identification Software to detect whether plaques exist in each of the coronary artery CTA images; The digital plaque recognition software is used to annotate the type and CT attenuation value of the plaque in the coronary artery CTA image with plaque.

5. A method for predicting coronary artery hypocalcified integrated plaque according to claim 1, characterized in that: The step of extracting radiomics features from each of the scanned image sets comprises the following steps: Delineating a region of interest on the cardiac CT plain scan image; Using 3D Slicer software to segment the cardiac CT plain scan image to obtain the region of interest; The radiomics package was used to extract the radiomics features of the region of interest on the pyhon platform.

6. A method for predicting coronary artery hypocalcified integrated plaque according to claim 5, characterized in that: Delineating a region of interest on the cardiac CT plain scan image comprises the following steps: Determining voxels having CT attenuation values ​​within an attenuation value threshold range in the cardiac CT plain scan image; Coronary artery fat whose distance from the right coronary artery ostium is within a distance threshold range and whose thickness is equal to the vessel diameter is selected from the voxels as the region of interest.

7. A method for predicting coronary artery hypocalcified integrated plaque according to any one of claims 1 to 6, characterized in that: The method of constructing a prediction model based on the clinical laboratory data and the radiomics features comprises the following steps: A T test is performed on the radiomics features that conform to the normal distribution, and a Mann-Whitney U test is performed on the radiomics features that do not conform to the normal distribution, and each radiomics feature whose probability value is less than or equal to the probability threshold is retained as the first feature; Calculating the Spearman correlation coefficient between each of the imaging features and the coronary artery plaque, and retaining each of the imaging features whose absolute value of the Spearman correlation coefficient is greater than a coefficient threshold as the second feature; The random forest method is used to select the first several radiomics features with the highest importance scores as the third feature; Taking the intersection of each of the first features, each of the second features, and each of the third features to obtain a target feature set; The prediction model is constructed based on the clinical laboratory data and the target feature set using the LASSO method.

8. A coronary artery hypocalcified integrated plaque prediction device, characterized in that: The device comprises: An image acquisition unit, used to acquire clinical laboratory data and scan image sets of multiple patients with low calcium scores; wherein each of the scan image sets includes a cardiac CT plain scan image and a coronary artery CTA image; A feature extraction unit, used for extracting radiomics features from each of the scanned image sets; A model building unit, used for building a prediction model based on the clinical laboratory data and the radiomics features; A plaque prediction unit is used to predict the coronary soft plaque prediction result of the patient with low calcification score by using the prediction model according to the imaging genomics characteristics.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images