A myocardial damage detection system based on image characteristics

Abstract

The present invention provides a myocardial damage condition detection system based on image characteristics, the system comprising an image acquisition module, a feature extraction module, a data processing module and a report generation module; the image acquisition module is used to acquire high-resolution cardiac image data information; the feature extraction module is used to extract feature information related to cardiac structure and function from the acquired image data information; the data processing module is used to analyze the extracted feature information to identify related conditions of myocardial damage; the report generation module is used to generate a medical report on related conditions of myocardial damage for doctors; the present invention provides a more comprehensive and accurate assessment of myocardial damage conditions by comprehensively analyzing the patient's cardiac image data information, thereby improving the accuracy and effectiveness of medical diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of medical detection systems, and in particular to a myocardial damage detection system based on image characteristics. Background Art

[0002] With the increasing incidence of cardiovascular diseases, early detection and accurate assessment of myocardial damage have become increasingly important. Traditional myocardial detection methods mainly rely on a single imaging technique or physiological parameter, which is difficult to fully reflect the overall health of the heart; especially in clinical diagnosis, accurate assessment of the type, severity and development trend of myocardial damage is crucial to the formulation of effective treatment plans; in existing technologies, although some medical imaging systems can calculate and display myocardial contractility in real time, these systems often focus on a single functional parameter analysis and lack a comprehensive assessment of myocardial structural and functional characteristics; this limitation makes it difficult for doctors to obtain comprehensive and accurate information during diagnosis and treatment, affecting the scientificity and effectiveness of clinical decision-making.

[0003] After consulting the related disclosed technical solutions, the technology with the publication number CN115462833A proposes a medical imaging system, which is used to calculate and display myocardial contractility in real time, including an input module, a calculation module and an output module; the input module collects the parameter values ​​of the patient's myocardial contraction detected by the medical imaging device; the calculation module calculates the index of the patient's myocardial contractility according to the parameter values; the output module transmits the calculated index of myocardial contractility to the medical imaging device, and displays it on the screen of the medical imaging device. This invention combines physics and mechanical formulas with cardiac imaging measurement results, and can calculate the size of myocardial contractility in real time and display it on the screen of the medical imaging device, which is conducive to the in-depth study of the mechanical properties of the heart's myocardium by medical imaging equipment, opens up new research fields, and improves the scope of clinical and scientific research applications of medical imaging equipment; but although this solution can calculate and display myocardial contractility in real time, it is limited to a single mechanical property analysis, and lacks a comprehensive assessment of the type and severity of myocardial damage. Summary of the invention

[0004] The purpose of the present invention is to propose a myocardial damage detection system based on image characteristics in response to the current deficiencies.

[0005] The present invention adopts the following technical solution:

[0006] A myocardial damage condition detection system based on image characteristics, the system comprising an image acquisition module, a feature extraction module, a data processing module and a report generation module;

[0007] The image acquisition module is used to acquire high-resolution cardiac image data information; the feature extraction module is used to extract feature information related to cardiac structure and function from the acquired image data information; the data processing module is used to analyze the extracted feature information to identify the related conditions of myocardial damage; the report generation module is used to generate a medical report on the related conditions of myocardial damage for the doctor;

[0008] The image acquisition module includes an image acquisition unit and an image preprocessing unit; the image acquisition unit is used to acquire the patient's cardiac image data using a high-resolution medical imaging device, and the cardiac image data includes MRI image data and Doppler imaging data within multiple cardiac activity cycles; the image preprocessing unit is used to preprocess the acquired image data;

[0009] The feature extraction module includes an anatomical feature extraction unit and a functional feature extraction unit; the anatomical feature extraction unit is used to extract structural features related to the patient's heart according to the preprocessed image data; the functional feature extraction unit is used to extract functional features related to the patient's heart according to the preprocessed image data;

[0010] Further, the data processing module includes a myocardial injury analysis unit and a deterioration degree assessment unit; the myocardial injury analysis unit analyzes the type and severity of the patient's myocardial injury based on the structural and functional characteristics of the patient's heart; the deterioration degree assessment unit assesses the deterioration trend of the patient's myocardial injury in combination with the analysis data of the patient's myocardial injury in the historical data;

[0011] Furthermore, the anatomical feature extraction unit extracts structural related features of the patient's heart in the following manner:

[0012] S11: Acquire MRI image data from the preprocessed image data; the MRI image data includes image data of each section of the heart at multiple time points in multiple cardiac activity cycles;

[0013] S12: For all the slice image data, obtain the heart edge and internal contour information corresponding to each slice image by using a threshold segmentation method;

[0014] S13: fusing the images at multiple time points on each section according to the heart edge and internal contour information corresponding to each image to obtain a standard fused image on each section;

[0015] S14: Input the standard fusion images of all sections into the pre-trained CNN feature recognition model to obtain the structural features of the patient's heart;

[0016] Furthermore, in step S13, the standard fusion image on each section is obtained specifically in the following manner:

[0017] S131: For each slice, calculate the edge contour similarity between each image in the slice and other images on the slice:

[0018] ;

[0019] in, For an image on this slice With an image The edge contour similarity between them; is an image on this slice The heart edge and internal contour point set; is an image on this slice The heart edge and internal contour point set; For collection a point within; For collection a point within; Representative Points With point The Euclidean distance between is the infimum operator, which means finding the smallest value among all possible values. In all possible Find the The smallest value; is the supremum operator, which means finding the largest value among all possible values. In all possible Find the The largest value;

[0020] S132: Setting similarity threshold , all images whose edge contour similarity is less than the similarity threshold are placed in the same group, and the edge contour similarity between the image in each group and the rest of the images is less than the similarity threshold ; Assume a total of Groups;

[0021] S133: Merge the images in each group:

[0022] ;

[0023] For the The fused images in the groups; For the The total number of images in each group; For the In the group images;

[0024] S134: Comprehensively fuse the images fused in each group to obtain a standard fused image of the section:

[0025] ;

[0026] For this section The corresponding standard fusion image; is a magnification factor with a value greater than 1; is the total number of images on this slice;

[0027] Furthermore, the functional feature extraction unit combines the cardiac MRI image data and the Doppler imaging data to perform imaging analysis to obtain functional related features of the patient's heart;

[0028] Furthermore, the myocardial injury analysis unit integrates and splices the structural and functional characteristics of the patient's heart into a pre-trained myocardial injury neural network recognition model to complete a quantitative assessment of the type and severity of myocardial injury.

[0029] The beneficial effects achieved by the present invention are:

[0030] The present invention makes comprehensive use of high-resolution cardiac imaging data and Doppler imaging data to accurately extract structural and functional related features of the patient's heart; obtains standard fused images by preprocessing and fusing imaging data at multiple time points, thereby improving the quality and consistency of imaging data and ensuring the accurate generation of structural related features; inputs the extracted structural and functional features into a pre-trained myocardial damage neural network recognition model to complete a quantitative assessment of the type and severity of myocardial damage, and obtains the deterioration trend of the patient's myocardial damage through multiple historical quantitative assessment results, thereby providing doctors with a more comprehensive and accurate diagnostic basis, effectively improving the accuracy of myocardial damage detection, and thereby improving the scientific nature of medical decision-making and treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0032] Figure 1 It is a schematic diagram of the overall module of the present invention.

[0033] Figure 2 Schematic diagram of the workflow of the anatomical feature extraction unit of the present invention.

[0034] Figure 3 It is a schematic diagram of the working process of the deterioration trend assessment unit of the present invention. DETAILED DESCRIPTION

[0035] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention; for those skilled in the art, other systems, methods and / or features of the present embodiment will become apparent after reviewing the following detailed description; it is intended that all such additional systems, methods, features and advantages are included in this specification; included within the scope of the present invention and protected by the appended claims; additional features of the disclosed embodiments are described in the following detailed description, and these features will be apparent from the following detailed description.

[0036] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0037] Embodiment 1: Figure 1 As shown, this embodiment provides a myocardial damage condition detection system based on image characteristics, the system includes an image acquisition module, a feature extraction module, a data processing module and a report generation module;

[0038] The image acquisition module is used to acquire high-resolution cardiac image data information; the feature extraction module is used to extract feature information related to cardiac structure and function from the acquired image data information; the data processing module is used to analyze the extracted feature information to identify the related conditions of myocardial damage; the report generation module is used to generate a medical report on the related conditions of myocardial damage for the doctor;

[0039] The image acquisition module includes an image acquisition unit and an image preprocessing unit; the image acquisition unit is used to acquire the patient's cardiac image data using a high-resolution medical imaging device, and the cardiac image data includes MRI image data and Doppler imaging data within multiple cardiac activity cycles; the image preprocessing unit is used to preprocess the acquired image data;

[0040] The feature extraction module includes an anatomical feature extraction unit and a functional feature extraction unit; the anatomical feature extraction unit is used to extract structural features related to the patient's heart according to the preprocessed image data; the functional feature extraction unit is used to extract functional features related to the patient's heart according to the preprocessed image data;

[0041] The data processing module includes a myocardial injury analysis unit and a deterioration degree assessment unit; the myocardial injury analysis unit analyzes the type and severity of the patient's myocardial injury based on the structural and functional characteristics of the patient's heart; the deterioration degree assessment unit assesses the deterioration trend of the patient's myocardial injury in combination with the analysis data of the patient's myocardial injury in the historical data;

[0042] Further, such as Figure 2 As shown, the anatomical feature extraction unit completes the extraction of structural related features of the patient's heart in the following manner:

[0043] S11: Acquire MRI image data from the preprocessed image data; the MRI image data includes image data of each section of the heart at multiple time points in multiple cardiac activity cycles;

[0044] S12: For all the slice image data, obtain the heart edge and internal contour information corresponding to each slice image by using a threshold segmentation method;

[0045] S13: fusing the images at multiple time points on each section according to the heart edge and internal contour information corresponding to each image to obtain a standard fused image on each section;

[0046] S14: Input the standard fusion images of all sections into the pre-trained CNN feature recognition model to obtain the structural features of the patient's heart;

[0047] Furthermore, in step S13, the standard fusion image on each section is obtained specifically in the following manner:

[0048] S131: For each slice, calculate the edge contour similarity between each image in the slice and other images on the slice:

[0049] ;

[0050] in, For an image on this slice With an image The edge contour similarity between them; is an image on this slice The heart edge and internal contour point set; is an image on this slice The heart edge and internal contour point set; For collection a point within; For collection a point within; Representative Points With point The Euclidean distance between is the infimum operator, which means finding the smallest value among all possible values. In all possible Find the The smallest value; is the supremum operator, which means finding the largest value among all possible values. In all possible Find the The largest value;

[0051] S132: Setting similarity threshold , all images whose edge contour similarity is less than the similarity threshold are placed in the same group, and the edge contour similarity between the image in each group and the rest of the images is less than the similarity threshold ; Assume a total of Groups;

[0052] S133: Merge the images in each group:

[0053] ;

[0054] For the The fused images in the groups; For the The total number of images in each group; For the In the group images;

[0055] S134: Comprehensively fuse the images fused in each group to obtain a standard fused image of the section:

[0056] ;

[0057] For this section The corresponding standard fusion image; is a magnification factor with a value greater than 1; is the total number of images on this slice;

[0058] Specifically, the structural characteristics of the patient's heart include, but are not limited to, myocardial thickness, heart chamber size, and heart morphology;

[0059] Comprehensive information is obtained through image data of each section of the heart at multiple time points, thereby improving the integrity and reliability of image data; the heart edge and internal contour are extracted through the threshold segmentation method, thus laying the foundation for subsequent image similarity calculation and fusion; image grouping is achieved by calculating edge contour similarity, thereby ensuring that images in the same group have high similarity, thereby enhancing the quality of the fused image; high-quality standard fused images are obtained by weighted fusion based on the number of images in each group, thereby ensuring that the images input into the CNN feature recognition model have higher accuracy and clarity, thereby providing a reliable basis for subsequent diagnosis and treatment;

[0060] Furthermore, the functional feature extraction unit combines cardiac MRI image data and Doppler imaging data to perform imaging analysis to obtain functional-related features of the patient's heart; the functional-related features of the patient's heart include but are not limited to cardiac contraction and relaxation characteristics, myocardial movement velocity and blood flow velocity.

[0061] Embodiment 2: This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;

[0062] This embodiment provides a myocardial damage condition detection system based on image characteristics, the system includes an image acquisition module, a feature extraction module, a data processing module and a report generation module;

[0063] The image acquisition module is used to acquire high-resolution cardiac image data information; the feature extraction module is used to extract feature information related to cardiac structure and function from the acquired image data information; the data processing module is used to analyze the extracted feature information to identify the related conditions of myocardial damage; the report generation module is used to generate a medical report on the related conditions of myocardial damage for the doctor;

[0064] The data processing module includes a myocardial injury analysis unit and a deterioration degree assessment unit; the myocardial injury analysis unit analyzes the type and severity of the patient's myocardial injury based on the structural and functional characteristics of the patient's heart; the deterioration degree assessment unit assesses the deterioration trend of the patient's myocardial injury in combination with the analysis data of the patient's myocardial injury in the historical data;

[0065] Furthermore, the myocardial injury analysis unit integrates and splices the structural and functional characteristics of the patient's heart into a pre-trained myocardial injury neural network recognition model to complete a quantitative assessment of the type and severity of myocardial injury;

[0066] Further, such as Figure 3 As shown, the deterioration degree assessment unit completes the assessment of the deterioration trend of the patient's myocardial damage in the following manner:

[0067] S21: Get the continuous data in the historical data with the current time as the deadline The severity of myocardial damage in this patient, as well as the patient's Information on living habits during the collection period;

[0068] S22: Will be continuous Among the historical data on the severity of myocardial damage of patients, the one closest to the current time is marked as times, the one farthest from the current time is marked as the first time;

[0069] S23: Calculate the second to third The coefficient of variation of myocardial damage:

[0070] ;

[0071] in, For the The coefficient of variation of myocardial damage, For the A quantitative assessment of the severity of myocardial damage in patients in historical data; ;

[0072] S24: Calculate the patient's deterioration trend parameters:

[0073] ;

[0074] in, is the patient's deterioration trend parameter. The larger the deterioration trend parameter is, the more obvious the deterioration trend of the patient's myocardial damage is. For the To The bad habit assessment parameters of the patient during the collection period can be set by the doctor based on the patient's living habit information and rich clinical experience. The value range is ; is the preset magnification factor, the value range is ;

[0075] By comprehensively considering multiple historical data and the patient's living habits information, the deterioration trend assessment unit can more comprehensively understand the changes in the patient's myocardial damage, thereby providing more accurate assessment results; by obtaining multiple myocardial damage change coefficients in historical data, the deterioration trend of the patient's myocardial damage at different stages of the disease can be identified in a timely manner; by combining the timeline and the patient's living habits information to provide assessment weights for the deterioration trend parameters, and analyzing the patient's myocardial damage deterioration trend based on the deterioration trend parameters, the doctor is reminded to intervene in potential risks, thereby improving the patient's overall health status;

[0076] Furthermore, the medical report information generated by the report generation module includes the analysis result of the myocardial injury analysis unit and the evaluation result of the deterioration degree evaluation unit.

[0077] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. A myocardial damage detection system based on image characteristics, characterized in that: The system includes an image acquisition module, a feature extraction module, a data processing module and a report generation module; The image acquisition module is used to acquire high-resolution cardiac image data information; the feature extraction module is used to extract feature information related to cardiac structure and function from the acquired image data information; the data processing module is used to analyze the extracted feature information to identify the related conditions of myocardial damage; the report generation module is used to generate a medical report on the related conditions of myocardial damage for the doctor; The image acquisition module includes an image acquisition unit and an image preprocessing unit; the image acquisition unit is used to acquire the patient's cardiac image data using a high-resolution medical imaging device, and the cardiac image data includes MRI image data and Doppler imaging data within multiple cardiac activity cycles; the image preprocessing unit is used to preprocess the acquired image data; The feature extraction module includes an anatomical feature extraction unit and a functional feature extraction unit; the anatomical feature extraction unit is used to extract structural features related to the patient's heart according to the preprocessed image data; the functional feature extraction unit is used to extract functional features related to the patient's heart according to the preprocessed image data; The data processing module includes a myocardial injury analysis unit and a deterioration degree assessment unit; the myocardial injury analysis unit analyzes the type and severity of the patient's myocardial injury based on the structural and functional characteristics of the patient's heart; the deterioration degree assessment unit assesses the deterioration trend of the patient's myocardial injury in combination with the analysis data of the patient's myocardial injury in the historical data; The anatomical feature extraction unit extracts structural related features of the patient's heart in the following manner: S11: Acquire MRI image data from the preprocessed image data; the MRI image data includes image data of each section of the heart at multiple time points in multiple cardiac activity cycles; S12: For all the slice image data, obtain the heart edge and internal contour information corresponding to each slice image by using a threshold segmentation method; S13: fusing the images at multiple time points on each section according to the heart edge and internal contour information corresponding to each image to obtain a standard fused image on each section; S14: Input the standard fusion images of all sections into the pre-trained CNN feature recognition model to obtain the structural features of the patient's heart; In step S13, the standard fusion image on each section is obtained specifically in the following manner: S131: For each slice, calculate the edge contour similarity between each image in the slice and other images on the slice: ； in, For an image on this slice With an image The edge contour similarity between them; is an image on this slice The heart edge and internal contour point set; is an image on this slice The heart edge and internal contour point set; For collection a point within; For collection a point within; Representative Points With point The Euclidean distance between is the infimum operator, which means finding the smallest value among all possible values. Indicates that in all possible Find the The smallest value; is the supremum operator, which means finding the largest value among all possible values. Indicates that in all possible Find the The largest value; S132: Setting similarity threshold , all images whose edge contour similarity is less than the similarity threshold are placed in the same group, and the edge contour similarity between the image in each group and the rest of the images is less than the similarity threshold ; Assume a total of Groups; S133: Merge the images in each group: ； For the The fused images in the groups; For the The total number of images in each group; For the In the group images; S134: Comprehensively fuse the images fused in each group to obtain a standard fused image of the section: ； For this section The corresponding standard fusion image; is a magnification factor with a value greater than 1; is the total number of images on this slice; The myocardial injury analysis unit integrates and splices the structural and functional characteristics of the patient's heart and inputs them into a pre-trained myocardial injury neural network recognition model to complete a quantitative assessment of the type and severity of myocardial injury.

2. A myocardial damage detection system based on image characteristics according to claim 1, characterized in that: The functional feature extraction unit combines the cardiac MRI image data and the Doppler imaging data to perform imaging analysis to obtain functional-related features of the patient's heart.

Images