Heart magnetic resonance heart function evaluation method based on multi-task learning

Abstract

The invention discloses a cardiac magnetic resonance cardiac function evaluation method based on multi-task learning, and belongs to the technical field of medical image processing. The method comprises the following steps: labeling, enhancing and preprocessing cardiac magnetic resonance image data; training a multi-task learning model by using the preprocessed data, supervising a multi-task training process by introducing regional geometric consistency loss, and improving the accuracy and generalization performance of the model; inputting a to-be-evaluated heart magnetic resonance image into the trained multi-task learning model to obtain left and right ventricular intima segmentation results in a heart anatomical structure, a left ventricular myocardial segmentation result and a right ventricular insertion point and a left ventricular central point in a heart key point position; further calculating the ventricular volume to obtain left and right ventricular ejection fractions; calculating the thickness of each segment of the left ventricular myocardium; and outputting a cardiac function evaluation result. According to the method, the accuracy and generalization performance of the model are improved, and the problems that a traditional method is low in precision and long in analysis time consumption are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image processing, and in particular relates to a cardiac magnetic resonance cardiac function assessment method based on multi-task learning. Background Art

[0002] Cardiac magnetic resonance imaging (CMR) is widely used in the diagnosis and treatment of heart diseases due to its non-invasiveness, high soft tissue contrast, multi-parameter and multi-directional imaging capabilities. CMR can provide detailed information on the morphology, structure, function, blood perfusion and tissue characteristics of the heart, which is crucial for the early diagnosis of primary myocardial diseases, risk assessment and monitoring of the efficacy of heart failure patients. Traditional CMR imaging techniques, such as cardiac cine imaging, can obtain dynamic images of the whole cardiac cycle and evaluate the morphology and function of the left atrium, right atrium, left ventricle and right ventricle. However, these technologies are limited in clinical promotion due to reasons including complex operation, high requirements for technicians, the need for patients to cooperate with multiple breath holding and low success rate for those with poor tolerance. With the continuous development of imaging technology, CMR examination sequences and methods are constantly updated, and CMR-specific cardiac function evaluation indicators are derived, such as ejection fraction, ventricular mass index, strain, septal curvature ratio, right atrioventricular valve ring systolic displacement and vascular compliance.

[0003] Although CMR has unique advantages in evaluating cardiac function, it still faces challenges in practical applications, such as long imaging time, high requirements for technicians, and the need for patients to hold their breath. In addition, the quality of CMR imaging is affected by factors such as the position, size, and motion state of the heart, resulting in image quality that may not be as good as expected in some cases. Therefore, the development of high-quality, low-time CMR imaging technology, combined with advanced image segmentation algorithms to achieve accurate assessment of cardiac structure and function, is of great significance in the diagnosis of heart disease. Summary of the invention

[0004] In view of the above prior art, the purpose of the present invention is to provide a cardiac magnetic resonance cardiac function assessment method based on multi-task learning, aiming to optimize the performance of cardiac anatomical structure segmentation and cardiac key point identification through deep learning technology, and improve the accuracy and efficiency of cardiac function assessment. This method is expected to overcome the problems of low assessment accuracy and long analysis time in the prior art, achieve efficient cardiac anatomical structure segmentation and key point detection, reduce the model's dependence on training data, and provide high-quality cardiac function assessment results.

[0005] The technical solution of the present invention is as follows:

[0006] The present invention proposes a cardiac magnetic resonance cardiac function assessment method based on multi-task learning, comprising the following steps:

[0007] S1. Obtain cardiac magnetic resonance images and annotate cardiac segmentation labels and cardiac key point labels to obtain annotated data sets, and perform data enhancement on the data sets;

[0008] S2, performing a preprocessing operation on the data set constructed in S1, and training a multi-task learning model, wherein the multi-task learning model includes a cardiac anatomical structure segmentation sub-branch and a cardiac key point position recognition sub-branch;

[0009] S3, inputting the cardiac magnetic resonance image to be evaluated into the trained multi-task learning model to obtain the segmentation results of the left and right ventricular endocardium in the cardiac anatomical structure, the segmentation result of the left ventricular myocardium, and the right ventricular insertion point and the left ventricular center point in the cardiac key point position;

[0010] S4, based on the segmentation results of the left and right ventricular endocardium in the cardiac anatomical structure, calculating the ventricular volume to obtain the left and right ventricular ejection fractions;

[0011] S5, dividing the left ventricular myocardium segmentation result based on the right ventricular insertion point and the left ventricular center point in the heart key point position, and calculating the thickness of each segment of the left ventricular myocardium;

[0012] S6. Outputting cardiac function assessment results based on the ejection fraction and the thickness of each segment of the left ventricular myocardium.

[0013] Preferably, the multi-task learning model in step S2 includes a multi-task shared encoder and a decoder customized for tasks corresponding to different sub-branches, and a Transformer module is introduced between the encoder and the decoder, so that the model's ability to capture long-range dependencies and understand complex patterns and representations is enhanced; the model input is a two-dimensional magnetic resonance short-axis movie sequence image of the heart, and the output is the left and right ventricular endocardium segmentation results, the left ventricular myocardium segmentation results, and the right ventricular insertion point and the left ventricular center point in the heart key point position.

[0014] Preferably, during the model training process of step S2, the total loss function L is constructed as follows:

[0015] L=ω seg ·L seg +ω lm ·L lm +ω rgc ·L rgc

[0016] Among them, ω seg is the segmentation task loss L seg Weight, ω lm L is the loss for the key point detection task lm Weight, ω rgc is the regional geometric consistency loss L rgc Weight;

[0017] L seg =λ 1 ·L CE +λ 2 ·L Dice

[0018] Among them, λ 1 is the corresponding cross entropy loss L CE The weight, λ 2 Corresponding to Dice loss L Dice Weight;

[0019]

[0020] Among them, ω is the proportional constraint value, which is a positive number; ε is the curvature constraint value; is a constant;

[0021]

[0022] Among them, p represents the key points of the heart, including the anterior insertion point of the right ventricle Right ventricular posterior insertion point and left ventricular center point P LC ;For any given point q on the myocardial contour, C contains the set of points that define the contour; ‖·‖ 2 represents the L2 norm, which is used to quantify the Euclidean distance between points; |·| represents the Euclidean distance between two key points; is the sigmoid function, which is used to introduce nonlinearity; k is the proportional coefficient, which is used to adjust the influence of distance difference on the sensitivity of the loss function.

[0023] The innovation and advantages of the present invention are:

[0024] (1) The present invention innovatively introduces the concept of multi-task learning into cardiac magnetic resonance cardiac function assessment. By improving the network structure, the cardiac anatomical structure can be efficiently segmented and the key point positions can be identified. The regional geometric consistency loss is introduced to supervise the multi-task training process, thereby improving the accuracy and generalization performance of the model and solving the problems of low accuracy and long analysis time of traditional methods.

[0025] (2) The present invention adopts a rigid deformation method for data enhancement, which effectively expands the data set and improves the generalization ability of the model. At the same time, the Transformer module is introduced between downsampling and upsampling, so that the model's ability to capture long-range dependencies and understand complex patterns and representations is enhanced.

[0026] (3) The present invention provides a comprehensive cardiac function assessment result by comprehensively evaluating the ejection fraction and myocardial wall thickness. This method not only improves the accuracy of diagnosis, but also has high operability and repeatability, and is of great value to clinical medical research. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 The figure is a flow chart of the cardiac function assessment method of the present invention.

[0028] Figure 2 This is a flow chart of data preprocessing in the present invention.

[0029] Figure 3 This is a framework diagram of the heart segmentation and key point detection model based on multi-task learning in the present invention.

[0030] Figure 4 It is a comparison diagram of the left ventricular myocardial segmentation result of an embodiment of the present invention and the two-stage TransUNet method.

[0031] Figure 5 Schematic diagram of the myocardial segment thickness calculation principle in the present invention.

[0032] Figure 6 This is a flowchart of the central function diagnosis report generation and auxiliary diagnosis and treatment of the present invention. DETAILED DESCRIPTION

[0033] The present invention is further described and illustrated below in conjunction with specific embodiments. The embodiments are merely exemplary of the present disclosure and do not define the scope of limitation. The technical features of each embodiment of the present invention may be combined accordingly without conflicting with each other.

[0034] In this embodiment, if Figure 1 As shown, a cardiac magnetic resonance cardiac function assessment method based on multi-task learning is provided, which includes the following steps:

[0035] S1. Obtain cardiac magnetic resonance images and annotate cardiac segmentation labels and cardiac key point labels to obtain annotated data sets, and perform data enhancement on the data sets;

[0036] In this embodiment, S1 is as follows: obtain two-dimensional magnetic resonance film sequence images from different centers and different equipment, collected from the heart base to the heart apex, and carefully annotate the images, including but not limited to heart segmentation labels such as left and right ventricular blood pools, left ventricular myocardium, and heart key point labels such as right ventricular insertion points and left and right ventricular center points. Then, in order to perform model training and performance evaluation, the present invention divides the data set into a training set and a test set in a 6:1 ratio, and introduces a rigid deformation method for data enhancement, including random distance translation, random angle rotation, mirror flipping, etc. to expand the data volume of the training set. This method enhances the model's adaptability to changes in heart morphology by simulating the geometric changes of the heart between different individuals.

[0037] S2, performing a preprocessing operation on the data set constructed in S1, and training a multi-task learning model, wherein the multi-task learning model includes a cardiac anatomical structure segmentation sub-branch and a cardiac key point position recognition sub-branch;

[0038] Reference Figure 2 , a series of measures are taken to preprocess the data set. In order to enhance the contrast of magnetic resonance images, the histogram equalization method is used to redistribute the image pixel values; then, in order to remove irrelevant information, the region of interest (ROI) is cropped from the image, which contains the target research object; in addition, the data sets from different sources are resampled to unify the spatial resolution. The specific operation is to adjust the voxel size and slice spacing of the image, which helps to eliminate the difference in scanner resolution; finally, the min-max normalization method is used to map the image pixel values ​​to the [0,1] interval, which can reduce the numerical error in the calculation process and improve the numerical stability. The calculation formula is:

[0039]

[0040] Where x is the original data, x min and x max are the minimum and maximum values ​​in the data set respectively, and x′ is the standardized data.

[0041] S3, inputting the cardiac magnetic resonance image to be evaluated into the trained multi-task learning model to obtain the segmentation results of the left and right ventricular endocardium in the cardiac anatomical structure, the segmentation result of the left ventricular myocardium, and the right ventricular insertion point and the left ventricular center point in the cardiac key point position;

[0042] S4, based on the segmentation results of the left and right ventricular endocardium in the cardiac anatomical structure, calculating the ventricular volume to obtain the left and right ventricular ejection fractions;

[0043] S5, dividing the left ventricular myocardium segmentation result based on the right ventricular insertion point and the left ventricular center point in the heart key point position, and calculating the thickness of each segment of the left ventricular myocardium;

[0044] S6. Outputting cardiac function assessment results based on the ejection fraction and the thickness of each segment of the left ventricular myocardium.

[0045] In cardiac magnetic resonance imaging analysis, the traditional two-stage model has obvious limitations, such as the independence of cardiac segmentation and cardiac key point detection, which leads to the loss of inter-task dependency information and low computational efficiency. Therefore, in S3 of the cardiac magnetic resonance cardiac function assessment method proposed in the present invention, a multi-task learning network MLTUNet (Multi-task Learning TransUNet) is introduced. Figure 3 As shown in the figure, for the input cardiac 2D MRI short-axis movie sequence images, ResNet50 is first used to downsample the images three times to obtain feature maps; then the Transformer module is input; the image size is adjusted through the convolution layer, BatchNorm normalization layer and ReLU activation function in sequence; then two subtask branches are input, each of which contains three upsampling layers, and each layer uses a skip connection mechanism to fuse the low-level image features extracted by the encoder at each stage with the decoder. During the training process, the network output includes the segmentation prediction value of the cardiac anatomical structure (S pre ) and the predicted value of the heart key point position (L pre ), these predictions will be compared with the actual cardiac anatomical structure labels (S gt ) and the heart key point location label (L gt ) are combined to calculate the loss function, and through the back-propagation algorithm, these losses are used to guide and optimize the network training process to improve the accuracy of prediction. The multi-task learning network can focus on multiple related tasks at the same time, improve the ability to capture cardiac motion and structural changes, and enable the model to achieve better performance on each individual task.

[0046] The proposed network MLTNUet includes a multi-task shared encoder and a decoder customized for different subtasks. The Transformer module is introduced between the encoder and the decoder, so that the model's ability to capture long-range dependencies and understand complex patterns and representations is enhanced to cope with the complexity of left and right ventricular endocardium segmentation in cardiac anatomy. This design allows the model to not only focus on local features but also capture global contextual information when processing cardiac images, which is crucial for accurate cardiac structure segmentation. The Transformer module contains two submodules, namely the multi-head self-attention mechanism (MSA) and the feedforward neural network (FFN). The multi-head self-attention mechanism is a technology that allows the model to simultaneously focus on different position information in different representation subspaces. The input vector is split into multiple heads, each head independently calculates the attention output, and then these outputs are merged to enhance the model's ability to capture information. Let the input sequence be Q, K, V, where Q is the query, K is the key, and V is the value. The calculation of multi-head self-attention can be expressed as:

[0047] MHead(Q,K,V)=Concat(head 1 ,…,head h )W o

[0048] head i =Att(QWi i Q ,KW i K ,VW i V )

[0049]

[0050] Among them, W i Q ,W i K ,W i V is the learnable weight matrix, d k is the dimension of the key (K) vector, Used to scale dot products to prevent the vanishing gradient problem.

[0051] The feedforward neural network (FFN) consists of two linear transformation layers and a ReLU activation function. The first layer of linear transformation is responsible for expanding the input data to a higher-dimensional representation space. This process allows the model to capture richer feature information. Then, by introducing the ReLU activation function, the network can introduce necessary nonlinear characteristics, which is essential for simulating complex function mappings. Finally, the second layer of linear transformation converts the nonlinearly processed data back to the original dimension or target dimension to ensure that the output is compatible with other parts of the model. Let the input be x, then the calculation process can be expressed as:

[0052] FFN(x)=max(0,xW 1 +b 1 )W 2 +b 2

[0053] Among them, W i represents a series of trainable weight matrices, and b i represents the corresponding bias vector.

[0054] Furthermore, during the model training process, Dice loss and cross entropy loss are used to supervise the performance of the segmentation branch, while Wing loss is used to supervise the performance of key point detection. In addition, the regional geometric consistency loss L is introduced. rgc , to measure the common performance of the two tasks, the back-propagation algorithm is used to update the model parameters. The loss functions are introduced as follows.

[0055] Segmentation branch loss L seg :

[0056] L seg =λ 1 ·L CE +λ 2 ·L Dice

[0057] Among them, L seg is the segmentation branch loss, λ 1 is the corresponding cross entropy loss L CE The weight, λ 2 Corresponding to Dice loss L Dice The weight, in this embodiment, λ 1 With λ 2 All were chosen to be 0.5.

[0058] Keypoint detection branch loss L lm :

[0059]

[0060] Where L lmis the key point detection branch loss, ω is the proportional constraint value, which is a positive number, limiting the range of the nonlinear part to [-ω, ω]; ∈ is the curvature constraint value, which is used to constrain the curvature of the nonlinear part; is a constant used to smoothly connect the linear and nonlinear parts of the above segmentation.

[0061] Regional geometric consistency loss L rgc :

[0062]

[0063] Among them, p represents a key cardiac landmark, including the anterior insertion point of the right ventricle Right ventricular posterior insertion point and left ventricular center point P LC . For any given point q on the myocardial contour, C contains the set of points that define the contour; ‖·‖ 2 represents the L2 norm, which is used to quantify the Euclidean distance between points; |·| represents the Euclidean distance between two key points; is the sigmoid function, which is used to introduce nonlinearity; k is the proportional coefficient, which is used to adjust the influence of distance difference on the sensitivity of the loss function.

[0064] By integrating the above multi-faceted loss functions, the final loss function is constructed as follows:

[0065] L=ω seg ·L seg +ω lm ·L lm +ω rgc ·L rgc

[0066] Among them, ω seg is the weight of the segmentation task loss function, ω lm is the weight of the loss function for the key point detection task, ω rgc is the weight of the regional geometric consistency loss function.

[0067] Further, S4 is specifically as follows: based on the segmentation results of the left and right ventricular endocardium in the cardiac anatomical structure, the ventricular contour is identified by an edge tracking algorithm, the number of pixels in the contour is counted, and the single-layer ventricular cavity area is estimated in combination with the imaging resolution; then, the areas of the left and right ventricles in all slices are accumulated and multiplied by the inter-layer resolution of the image to obtain the volumes of the left and right ventricles, and the left and right ventricular ejection fractions are calculated based on the following formula:

[0068]

[0069] Where EF is the ejection fraction, EDV and ESV are the end-diastolic volume and end-systolic volume, respectively.

[0070] The ejection fraction calculation results of the proposed network MLTUNet and the two-stage TransUNet model are shown in Table 1, using mean absolute error (MAE) and root mean square error (RMSE) as evaluation indexes. The results show that the present invention has higher left ventricular ejection fraction calculation accuracy than the existing two-stage model.

[0071] Table 1 Quantitative comparison of ejection fraction calculation accuracy between the present invention and the two-stage TransUNet algorithm

[0072]

[0073] Further, S5 is specifically: based on the position information of the key points of the heart such as the left ventricular center point and the right ventricular insertion point, the left ventricular myocardium is divided into 16 segments, Figure 4 This is a comparison chart of the left ventricular myocardial segmentation results of the embodiment of the present invention and the two-stage TransUNet method. The two-stage TransUNet method has the problem of missed detection at the base, and the segmentation results of each segment are thinner than those of the method of the present invention, and the difference with the annotation label is greater. The results show that MLTUNet has excellent performance in the myocardial segmentation task; then refer to Figure 5 The maximum thickness, minimum thickness and average thickness of the ventricular wall of each myocardial segment were calculated as part of the cardiac function evaluation results. The specific method is to extract the center of gravity of the inner contour of the left ventricular myocardium, and intersect the inner and outer contours of the left ventricular myocardium with the rays emitted from the center of gravity, and calculate the straight-line distance between the two intersections in combination with the imaging resolution as the thickness value at that location.

[0074] The ejection fraction and myocardial wall thickness calculation results in S6 can be directly output as cardiac function assessment results, or can be referred to Figure 6 As shown in the figure, the measurement results of ejection fraction (EF) and myocardial wall thickness are combined with clinical guidelines and expert knowledge graphs to generate a detailed cardiac function assessment report. This report will comprehensively measure the diastolic and systolic functions of the heart, provide a scientific basis for clinical decision-making, and thus achieve an accurate assessment of heart health.

[0075] This embodiment also provides a cardiac magnetic resonance cardiac function assessment system based on multi-task learning, including at least one memory and at least one processor, the memory stores a computer program, when the program is executed by the processor, the processor can execute the above-mentioned cardiac magnetic resonance cardiac function assessment method based on multi-task learning.

[0076] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. For ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A cardiac magnetic resonance cardiac function assessment method based on multi-task learning, characterized in that: The method comprises the following steps: S1. Obtain cardiac magnetic resonance images and annotate cardiac segmentation labels and cardiac key point labels to obtain annotated data sets, and perform data enhancement on the data sets; S2, performing a preprocessing operation on the data set constructed in S1, and training a multi-task learning model, wherein the multi-task learning model includes a cardiac anatomical structure segmentation sub-branch and a cardiac key point position recognition sub-branch; S3, inputting the cardiac magnetic resonance image to be evaluated into the trained multi-task learning model to obtain the segmentation results of the left and right ventricular endocardium in the cardiac anatomical structure, the segmentation result of the left ventricular myocardium, and the right ventricular insertion point and the left ventricular center point in the cardiac key point position; S4, based on the segmentation results of the left and right ventricular endocardium in the cardiac anatomical structure, calculating the ventricular volume to obtain the left and right ventricular ejection fractions; S5, dividing the left ventricular myocardium segmentation result based on the right ventricular insertion point and the left ventricular center point in the heart key point position, and calculating the thickness of each segment of the left ventricular myocardium; S6. Outputting cardiac function assessment results based on the ejection fraction and the thickness of each segment of the left ventricular myocardium.

2. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: In step S1, the cardiac magnetic resonance image includes a two-dimensional magnetic resonance short-axis movie sequence image of the heart; then these images are annotated with cardiac segmentation labels and cardiac key point labels, and the images and their corresponding annotation information are taken as a data set; wherein the cardiac segmentation labels include the left and right ventricular blood pools and the left ventricular myocardium; and the cardiac key point labels include the right ventricular insertion point and the left ventricular center point.

3. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: In step S1, a rigid deformation method is used to perform data enhancement on the data set, and the data enhancement method includes translation, rotation and scaling.

4. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: The preprocessing operation in step S2 includes: a. Use histogram equalization method to redistribute image pixel values; b. Crop the region of interest from the image; c. Resample the datasets from different sources to unify the spatial resolution by adjusting the voxel size and slice spacing of the image; d. Finally, the min-max normalization method is used to map the image pixel values ​​to the interval [0, 1] to reduce the numerical error in the calculation process.

5. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: The multi-task learning model in step S2 includes an encoder shared by multiple tasks and decoders customized for tasks corresponding to different sub-branches. At the same time, a Transformer module is introduced between the encoder and the decoder, so that the model's ability to capture long-range dependencies and understand complex patterns and representations is enhanced; The model input is a two-dimensional magnetic resonance short-axis movie sequence image of the heart, and the output is the segmentation results of the left and right ventricular endocardium, the segmentation results of the left ventricular myocardium, and the right ventricular insertion point and left ventricular center point in the heart key point position.

6. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: In step S2, for the input cardiac 2D MRI short-axis movie sequence images, the multi-task learning model first uses ResNet50 to downsample the images three times to obtain feature maps; then inputs the Transformer module; adjusts the image size through the convolution layer, BatchNorm normalization layer and ReLU activation function in sequence; then inputs two subtask branches, each of which contains three upsampling layers, and each layer uses a skip connection mechanism to fuse the low-level image features extracted by each stage of the encoder with the decoder; During the training process, the output of the multi-task learning model includes the segmentation prediction value of the cardiac anatomical structure and the prediction value of the cardiac key point location. These prediction values ​​will be combined with the actual cardiac anatomical structure label and the cardiac key point location label to calculate the total loss function and optimize the network parameters of the multi-task learning model through the back-propagation algorithm.

7. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: During the model training process of step S2, the total loss function L is constructed as follows: L=ω seg ·L seg +oh lm ·L lm +oh rgc ·L rgc Among them, ω seg is the segmentation task loss L seg Weight, ω lm L is the loss for the key point detection task lm Weight, ω rgc is the regional geometric consistency loss L rgc Weight; L seg =λ1·L CE +λ2·L Dice Among them, λ1 is the corresponding cross entropy loss L CE The weight of λ2 corresponds to the Dice loss L Dice Weight; Among them, ω is the proportional constraint value, which is a positive number; ∈ is the curvature constraint value; is a constant; Among them, p represents the key points of the heart, including the anterior insertion point of the right ventricle Right ventricular posterior insertion point and left ventricular center point P LC ; For any given point q on the myocardial contour, C contains the set of points that define the contour; ||·||2 represents the L2 norm, which is used to quantify the Euclidean distance between points; |·| represents the Euclidean distance between two key points; is the sigmoid function, which is used to introduce nonlinearity; k is the proportional coefficient, which is used to adjust the influence of distance difference on the sensitivity of the loss function.

8. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: In step S4, the ventricular volume is calculated to obtain the left and right ventricular ejection fractions, specifically: Based on the segmentation results of the left and right ventricular endocardium in the cardiac anatomical structure, the ventricular contour is identified by an edge tracking algorithm, the number of pixels in the contour is counted, and the single-layer ventricular cavity area is estimated in combination with the imaging resolution; then the areas of the left and right ventricles in all slices are accumulated and multiplied by the inter-layer resolution of the image to obtain the volumes of the left and right ventricles, and the left and right ventricular ejection fractions are calculated based on the following formula: Where EF is the ejection fraction, EDV and ESV are the end-diastolic volume and end-systolic volume, respectively.

9. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: In step S5, the thickness of each segment of the left ventricular myocardium is calculated, specifically: Based on the position information of the left ventricular center point and the right ventricular insertion point, the left ventricular myocardium was divided into 16 segments, and the maximum thickness, minimum thickness and average thickness of the ventricular wall of each myocardial segment were counted respectively.

10. The cardiac magnetic resonance cardiac function assessment method based on multi-task learning according to claim 1, characterized in that: In step S6, the calculation results of ejection fraction and myocardial wall thickness are directly output as cardiac function assessment results; Alternatively, based on the ejection fraction, myocardial wall thickness, and in combination with clinical guidelines and knowledge graphs, a cardiac function assessment report including cardiac diastolic function and systolic function is output as a cardiac function assessment result.

Images