Aortic valve regurgitation degree evaluation method and device based on deep learning and medium

Abstract

The invention discloses an aortic valve regurgitation degree evaluation method and device based on deep learning and a medium, and is suitable for semi-quantitative evaluation of the aortic valve regurgitation degree of echocardiography. The method comprises the steps of preprocessing and labeling a long-axis two-dimensional image beside the sternum and a color Doppler image, and training a key point prediction model and an aortic valve prediction model. The positions of upper and lower key points of the left ventricular outflow tract are obtained through a long-axis two-dimensional image beside the sternum, and aortic valve position information is obtained through a color Doppler image. Calculating the width of a left ventricular outflow channel according to the Euclidean distance of the key points, cutting a reflux region to extract an abnormal contour, obtaining the width of a reflux beam and the width of a reduced flow neck, and finally deducing the reflux degree according to a reflux degree grading standard. According to the method, semi-automatic evaluation of the aortic valve regurgitation degree is achieved, and the diagnosis efficiency, accuracy and repeatability are improved.

Description

Technical Field

[0001] The present application relates to the field of medical image processing technology, and in particular to a method, device and medium for evaluating the degree of aortic valve regurgitation based on deep learning. Background Art

[0002] Aortic regurgitation (AR) is a common heart valve disease characterized by the failure of the aortic valve to close completely during diastole, resulting in blood flowing back from the aorta to the left ventricle. This pathological condition can increase the burden on the left ventricle, leading to heart failure and other cardiovascular complications. Effective assessment of the degree of aortic regurgitation is crucial for clinical decision-making, disease monitoring, and treatment planning.

[0003] Traditional methods for assessing aortic regurgitation mainly rely on cardiac ultrasound (such as two-dimensional ultrasound and Doppler ultrasound), magnetic resonance imaging (MRI), and cardiac catheterization. Although these methods can provide certain quantitative assessments, they usually require professional physicians to interpret them, and may be affected by a variety of factors during the operation, such as patient position, physician experience, and equipment performance. In addition, traditional imaging methods are often subjective when assessing the degree of regurgitation, and the assessment results may vary among different operators, leading to inconsistent clinical decisions. Summary of the invention

[0004] The present application provides a method, device and medium for evaluating the degree of aortic regurgitation based on deep learning to solve the problems of strong subjectivity, low efficiency and high misdiagnosis rate in the current diagnosis of aortic regurgitation. By extracting key points and valve features through an automated deep learning model, the influence of human factors on the evaluation results is reduced, thereby improving the accuracy of diagnosis. At the same time, the method can quickly process ultrasound images and automatically calculate regurgitation-related parameters, significantly shortening the diagnosis time and improving clinical work efficiency. In addition, clear quantitative indicators (such as left ventricular outflow tract width, contraction neck width and regurgitation jet width) are provided to provide clinicians with a more intuitive evaluation basis and promote more effective treatment decisions. Through early and accurate assessment of the degree of regurgitation, doctors can take timely intervention measures to improve patient prognosis and reduce the incidence of serious complications.

[0005] The technical solution of this application is as follows:

[0006] On the one hand, the present application provides a method for evaluating the degree of aortic valve regurgitation based on deep learning, comprising the following steps:

[0007] Step 1: Perform image preprocessing and image annotation on the parasternal long axis two-dimensional image to obtain the parasternal long axis two-dimensional data set PLAX-2D; perform image preprocessing and image annotation on the parasternal long axis color Doppler image to obtain the parasternal long axis color Doppler data set PLAX-CDFI;

[0008] Step 2: Use the dataset PLAX-2D to train the YOLOv11 model, and use the trained model to extract key point features from the target patient's parasternal long axis two-dimensional image to obtain the positions of the upper and lower key points of the left ventricular outflow tract; calculate the Euclidean distance between the upper and lower key points of the left ventricular outflow tract, calculate the distance on the map based on the Euclidean distance, and obtain the left ventricular outflow tract width;

[0009] Step 3: Use the dataset PLAX-CDFI to train the Unet++ model, and use the trained model to extract the aortic valve features from the target patient's parasternal long-axis color Doppler image to output the aortic valve position information; process the regurgitant area of ​​the aortic valve position information, extract the contour of the abnormal regurgitant area, and then extract the upper and lower contour points of the contraction neck width to calculate the contraction neck width and the regurgitant jet width;

[0010] Step 4: Determine the severity of the target patient's heart valve regurgitation based on the target patient's left ventricular outflow tract width, contraction neck width, and regurgitation jet width.

[0011] Furthermore, the step 1 comprises:

[0012] Step 1.1: Acquire clear parasternal long-axis 2D images and parasternal long-axis color Doppler images of patients aged over 18 years old, and save the patient information to a document, including image ID, left ventricular outflow tract width, contraction neck width, and regurgitant jet width; preprocess the image and hide all text information in the image, including the patient's name, gender, hospital, and number;

[0013] Step 1.2: Label the parasternal long axis 2D image, use LabelImg as the labeling tool, label the upper and lower key points corresponding to the left ventricular outflow tract width, and mark the left ventricular outflow tract range with a rectangular frame to obtain the parasternal long axis 2D data set PLAX-2D;

[0014] Step 1.3: Label the parasternal long-axis color Doppler image, use LabelImg as the labeling tool, label the visible aortic valve area, and obtain the parasternal long-axis color Doppler data set PLAX-CDFI;

[0015] Step 1.4: Divide the datasets PLAX-2D and PLAX-CDFI into training sets, test sets, and validation sets in proportion.

[0016] Furthermore, the step 2 comprises:

[0017] Step 2.1: Use the training set and validation set of the PLAX-2D dataset to train the YOLOv11 deep learning model to obtain an automatic inference model of the upper and lower key points of the left ventricular outflow tract;

[0018] Step 2.2: Calculate the left ventricular outflow tract image ratio;

[0019] Step 2.2.1: The coordinates of the key points on each image are saved in the PLAX-2D dataset (X 1 ,Y 1 ), the coordinates of the next key point (X 2 ,Y 2 ), find the Euclidean distance of each image

[0020] Step 2.2.2: Obtain the actual left ventricular outflow tract width from the document, and divide the left ventricular outflow tract width data into m types of data with different depths, where m is the set depth for measuring the left ventricular outflow tract width, m∈{11cm, 12cm, 13cm, 14cm};

[0021] Step 2.2.3: Find the image ratio corresponding to each depth Where m is the image depth, D i The LVOT width was actually measured for the parasternal long-axis 2D images;

[0022] Step 2.3: Use the automatic inference model of the upper and lower key points of the left ventricular outflow tract to infer the parasternal long axis two-dimensional image and obtain the coordinates of the upper key point (x 1 ,y 1 ), the coordinates of the next key point (x 2 ,y 2 ), calculate the Euclidean distance between the upper and lower key points

[0023] Step 2.4: Find the actual distance using Euclidean distance and graph ratio Where m is the depth corresponding to the input parasternal long axis 2D image.

[0024] Furthermore, the step 3 comprises:

[0025] Step 3.1: Use the training set and validation set of the PLAX-CDFI dataset to train the Unet++ deep learning model to obtain an automatic aortic valve segmentation model;

[0026] Step 3.2: Use the aortic valve automatic segmentation model to infer the parasternal long-axis color Doppler image and obtain the coordinate points of the aortic valve region (x i ,y i );

[0027] Step 3.3: Expand the aortic valve area;

[0028] Step 3.3.1: Get the horizontal coordinate x of the leftmost point in the aortic valve area 1 , the vertical coordinate y of the top point 1 , establish the upper left coordinate point of the rectangular box (x 1 ,y 1 ), the abscissa x of the rightmost point in the aortic valve region 2 , the ordinate of the lowest point is y 2 , establish the lower right coordinate point of the rectangular box (x 2 ,y 2 ), establish the minimum rectangular frame;

[0029] Step 3.3.2: h = x 2 -x 1 , w=y 2 -y 1 ;

[0030] Step 3.3.3: If h>2cm, jump to step 3.3.4, otherwise jump to step 3.3.5;

[0031] Step 3.3.4: If w>2cm, jump to step 3.4, otherwise jump to step 3.3.6;

[0032] Step 3.3.5: Expand the width of the rectangle to 2cm;

[0033] Step 3.3.6: Expand the height of the rectangular frame to 2cm;

[0034] Step 3.4: Extract the abnormal area rectangle L(x,y,w,h);

[0035] Step 3.5: Use traditional image processing methods to obtain the abnormal area, the width of the contraction neck and the width of the regurgitant jet;

[0036] Step 3.5.1: Convert the read image from BGR color space to HSV color space using color space conversion technology;

[0037] Step 3.5.2: Create the first color mask: define the lower and upper bounds of the HSV color value, and use threshold-based image processing techniques to generate a binary mask; the pixel values ​​in the mask indicate which pixels are within the specified color range and are marked as the target color, and extract the first specified color area;

[0038] Step 3.5.3: Create a second color mask: define the lower and upper bounds of the HSV color value, and use threshold-based image processing technology to generate a binary mask; the pixel values ​​in the mask indicate which pixels are within the specified color range and are marked as the target color, and the second specified color area is extracted.

[0039] Step 3.5.4: Use bitwise operation techniques to combine the two masks mask1 and mask2 into a combined mask to extract all target color areas;

[0040] Step 3.5.5: Perform an erosion operation on the combined mask to remove small noise;

[0041] Step 3.5.6: Perform a dilation operation on the eroded mask to restore the size of the target area;

[0042] Step 3.5.7: extracting the mask of the aortic valve region L;

[0043] Step 3.5.8: Convert the processed image into a grayscale image and generate a binary image through threshold processing; then, extract the contour points in the image;

[0044] Step 3.5.9: Divide the contour into n regions according to its width;

[0045] Step 3.5.10: For each divided area, filter out the upper and lower contour points and calculate the distance between them to find the closest point pair;

[0046] Step 3.5.11: The rightmost point pair is the upper and lower contour points corresponding to the width of the contraction neck. Calculate the Euclidean distance between the two contour points. Calculate the actual distance according to steps 2.2 to 2.3, which is the width of the contraction neck.

[0047] Step 3.5.12: The length of the line segment corresponding to the straight line with a distance of 1 cm between the line segments corresponding to the width of the contraction neck is the width of the reverse flow beam.

[0048] Further, the step 4 comprises:

[0049] Step 4.1: Calculate RJW_ratio = contraction neck width / left ventricular outflow tract width;

[0050] Step 4.2: If RJW_ratio is less than 25% and the width of the contraction neck is less than 0.3 cm, the degree of reflux is judged to be mild; if RJW_ratio is 25% to 64% and the width of the contraction neck is 0.3 cm to 0.6 cm, the degree of reflux is judged to be moderate; if RJW_ratio is greater than 64% and the width of the contraction neck is greater than 0.6 cm, the degree of reflux is judged to be severe.

[0051] In another aspect, the present application provides a device for assessing the degree of aortic valve regurgitation based on deep learning, comprising:

[0052] The data set acquisition unit is used to perform image preprocessing and image annotation on the parasternal long axis two-dimensional image to obtain the parasternal long axis two-dimensional data set PLAX-2D; perform image preprocessing and image annotation on the parasternal long axis color Doppler image to obtain the parasternal long axis color Doppler data set PLAX-CDFI;

[0053] The first model training and detection unit is used to train the YOLOv11 model using the data set PLAX-2D, and use the trained model to extract key point features from the parasternal long axis two-dimensional image of the target patient to obtain the positions of the upper and lower key points of the left ventricular outflow tract; calculate the Euclidean distance between the upper and lower key points of the left ventricular outflow tract, calculate the distance on the map based on the Euclidean distance, and obtain the left ventricular outflow tract width;

[0054] The first model training and detection unit is used to train the Unet++ model using the data set PLAX-CDFI, and use the trained model to extract the aortic valve features from the parasternal long-axis color Doppler image of the target patient to output the aortic valve position information; the regurgitation area of ​​the aortic valve position information is processed to extract the contour of the regurgitation abnormal area, and then the upper and lower contour points of the contraction neck width are extracted to calculate the contraction neck width and the regurgitation jet width;

[0055] The heart valve regurgitation severity judging unit is used to judge the heart valve regurgitation severity of the target patient according to the left ventricular outflow tract width, contraction neck width and regurgitation jet width of the target patient.

[0056] On the other hand, the present application provides a cardiac image data processing terminal, including a processor and a memory, wherein the memory stores a computer-readable program, and when the computer-readable program is called and executed by the processor, the method described above is implemented.

[0057] On the other hand, the present application provides a computer-readable medium, wherein the computer-readable medium stores a computer-readable program, and when the computer-readable program is called and executed by a computer, the method described above is implemented.

[0058] In summary, the beneficial effects of the present application are: First, the use of deep learning models (such as YOLOv11 and Unet++) significantly improves the accuracy of reflux assessment and reduces errors caused by human factors. Secondly, the rapid processing of ultrasound images and automatic calculation of reflux parameters greatly improve the diagnostic efficiency and reduce the time investment of doctors in image analysis. In addition, the quantitative indicators provided (such as left ventricular outflow tract width, contraction neck width, and regurgitation jet width) enable clinicians to more intuitively assess the patient's condition and support the formulation of scientific treatment plans. Finally, by identifying potential heart problems early and reducing the misdiagnosis rate, patient safety and overall treatment effects are enhanced. Therefore, the present invention provides significant gains for the diagnosis and management of aortic valve regurgitation and has important clinical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Overall flow chart of the semi-quantitative assessment method for aortic regurgitation

[0060] Figure 2 Flow chart for prediction of contraction neck width and reverse flow jet width

[0061] Figure 3 Prediction results of upper and lower key points of left ventricular outflow tract

[0062] Figure 4 Aortic valve segmentation results DETAILED DESCRIPTION

[0063] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0064] A specific embodiment of the present application provides a method for evaluating the degree of aortic valve regurgitation based on deep learning, such as Figure 1 , including the following steps:

[0065] Step 1: Perform image preprocessing and image annotation on the parasternal long axis two-dimensional image to obtain the parasternal long axis two-dimensional data set PLAX-2D; perform image preprocessing and image annotation on the parasternal long axis color Doppler image to obtain the parasternal long axis color Doppler data set PLAX-CDFI;

[0066] Step 2: Use the dataset PLAX-2D to train the YOLOv11 model, and use the trained model to extract key point features from the target patient's parasternal long axis two-dimensional image to obtain the positions of the upper and lower key points of the left ventricular outflow tract; calculate the Euclidean distance between the upper and lower key points of the left ventricular outflow tract, calculate the distance on the map based on the Euclidean distance, and obtain the left ventricular outflow tract width;

[0067] Step 3: Use the dataset PLAX-CDFI to train the Unet++ model, and use the trained model to extract the aortic valve features from the target patient's parasternal long-axis color Doppler image to output the aortic valve position information; process the regurgitant area of ​​the aortic valve position information, extract the contour of the abnormal regurgitant area, and then extract the upper and lower contour points of the contraction neck width to calculate the contraction neck width and the regurgitant jet width;

[0068] Step 4: Determine the severity of the target patient's heart valve regurgitation based on the target patient's left ventricular outflow tract width, contraction neck width, and regurgitation jet width.

[0069] Furthermore, the step 1 comprises:

[0070] Step 1.1: Acquire clear parasternal long-axis 2D images and parasternal long-axis color Doppler images of patients aged over 18 years old, and save the patient information to a document, including image ID, left ventricular outflow tract width, contraction neck width, and regurgitant jet width; preprocess the image and hide all text information in the image, including the patient's name, gender, hospital, and number;

[0071] Step 1.2: Label the parasternal long axis 2D image, use LabelImg as the labeling tool, label the upper and lower key points corresponding to the left ventricular outflow tract width, and mark the left ventricular outflow tract range with a rectangular frame to obtain the parasternal long axis 2D data set PLAX-2D;

[0072] Step 1.3: Label the parasternal long-axis color Doppler image, use LabelImg as the labeling tool, label the visible aortic valve area, and obtain the parasternal long-axis color Doppler data set PLAX-CDFI;

[0073] Step 1.4: Divide the datasets PLAX-2D and PLAX-CDFI into training sets, test sets, and validation sets in proportion.

[0074] The step 2 comprises:

[0075] Step 2.1: Use the training set and validation set of the PLAX-2D dataset to train the YOLOv11 deep learning model to obtain the automatic reasoning model of the upper and lower key points of the left ventricular outflow tract; use the automatic reasoning model of the upper and lower key points of the left ventricular outflow tract to extract key point features from the parasternal long axis two-dimensional image of the target patient. The recognition results are as follows: Figure 3 shown.

[0076] Step 2.2: Calculate the left ventricular outflow tract image ratio;

[0077] Step 2.2.1: The coordinates of the key points on each image are saved in the PLAX-2D dataset (X 1 ,Y1 ), the coordinates of the next key point (X 2 ,Y 2 ), find the Euclidean distance of each image

[0078] Step 2.2.2: Obtain the actual left ventricular outflow tract width from the document, and divide the left ventricular outflow tract width data into m types of data with different depths, where m is the set depth for measuring the left ventricular outflow tract width, m∈{11cm, 12cm, 13cm, 14cm};

[0079] Step 2.2.3: Find the image ratio corresponding to each depth Where m is the image depth, D i The LVOT width was actually measured for the parasternal long-axis 2D images;

[0080] Step 2.3: Use the automatic inference model of the upper and lower key points of the left ventricular outflow tract to infer the parasternal long axis two-dimensional image and obtain the coordinates of the upper key point (x 1 ,y 1 ), the coordinates of the next key point (x 2 ,y 2 ), calculate the Euclidean distance between the upper and lower key points

[0081] Step 2.4: Find the actual distance using Euclidean distance and graph ratio Where m is the depth corresponding to the input parasternal long axis 2D image.

[0082] like Figure 2 , the step 3 comprises:

[0083] Step 3.1: Use the training set and validation set of the PLAX-CDFI dataset to train the Unet++ deep learning model to obtain an automatic aortic valve segmentation model;

[0084] Step 3.2: Use the aortic valve automatic segmentation model to infer the parasternal long-axis color Doppler image. The result is as follows Figure 4 As shown, the coordinate point of the aortic valve region (x i ,y i );

[0085] Step 3.3: Expand the aortic valve area;

[0086] Step 3.3.1: Get the horizontal coordinate x of the leftmost point in the aortic valve area 1 , the vertical coordinate y of the top point 1 , establish the upper left coordinate point of the rectangular box (x 1 ,y 1 ), the abscissa x of the rightmost point in the aortic valve region 2, the ordinate of the lowest point is y 2 , establish the lower right coordinate point of the rectangular box (x 2 ,y 2 ), establish the minimum rectangular frame;

[0087] Step 3.3.2: h = x 2 -x 1 , w=y 2 -y 1 ;

[0088] Step 3.3.3: If h>2cm, jump to step 3.3.4, otherwise jump to step 3.3.5;

[0089] Step 3.3.4: If w>2cm, jump to step 3.4, otherwise jump to step 3.3.6;

[0090] Step 3.3.5: Expand the width of the rectangle to 2cm;

[0091] Step 3.3.6: Expand the height of the rectangular frame to 2cm;

[0092] Step 3.4: Extract the abnormal area rectangle L(x,y,w,h);

[0093] Step 3.5: Use traditional image processing methods to obtain the abnormal area, the width of the contraction neck and the width of the regurgitant jet;

[0094] Step 3.5.1: Convert the read image from BGR color space to HSV color space using color space conversion technology;

[0095] Step 3.5.2: Create the first color mask: define the lower and upper bounds of the HSV color value, and use threshold-based image processing techniques to generate a binary mask; the pixel values ​​in the mask indicate which pixels are within the specified color range and are marked as the target color, and extract the first specified color area;

[0096] Step 3.5.3: Create a second color mask: define the lower and upper bounds of the HSV color value, and use threshold-based image processing technology to generate a binary mask; the pixel values ​​in the mask indicate which pixels are within the specified color range and are marked as the target color, and the second specified color area is extracted.

[0097] Step 3.5.4: Use bitwise operation techniques to combine the two masks mask1 and mask2 into a combined mask to extract all target color areas;

[0098] Step 3.5.5: Perform an erosion operation on the combined mask to remove small noise;

[0099] Step 3.5.6: Perform a dilation operation on the eroded mask to restore the size of the target area;

[0100] Step 3.5.7: extracting the mask of the aortic valve region L;

[0101] Step 3.5.8: Convert the processed image into a grayscale image and generate a binary image through threshold processing; then, extract the contour points in the image;

[0102] Step 3.5.9: Divide the contour into n regions according to its width;

[0103] Step 3.5.10: For each divided area, filter out the upper and lower contour points and calculate the distance between them to find the closest point pair;

[0104] Step 3.5.11: The rightmost point pair is the upper and lower contour points corresponding to the width of the contraction neck. Calculate the Euclidean distance between the two contour points. Calculate the actual distance according to steps 2.2 to 2.3, which is the width of the contraction neck.

[0105] Step 3.5.12: The length of the line segment corresponding to the straight line with a distance of 1 cm (actual distance) between the line segments corresponding to the width of the contraction neck is the width of the reverse flow beam.

[0106] The step 4 comprises:

[0107] Step 4.1: Calculate RJW_ratio = contraction neck width / left ventricular outflow tract width;

[0108] Step 4.2: If RJW_ratio is less than 25% and the contraction neck width is less than 0.3 cm, the degree of regurgitation is judged as mild; if RJW_ratio is 25% to 64% and the contraction neck width is 0.3 cm to 0.6 cm, the degree of regurgitation is judged as moderate; if RJW_ratio is greater than 64% and the contraction neck width is greater than 0.6 cm, the degree of regurgitation is judged as severe. The grading standard of aortic valve regurgitation is shown in the following table.

[0109] Aortic regurgitation severity grading criteria

[0110]

[0111] Another specific embodiment of the present application provides an aortic valve regurgitation degree assessment device based on deep learning, comprising:

[0112] The data set acquisition unit is used to perform image preprocessing and image annotation on the parasternal long axis two-dimensional image to obtain the parasternal long axis two-dimensional data set PLAX-2D; perform image preprocessing and image annotation on the parasternal long axis color Doppler image to obtain the parasternal long axis color Doppler data set PLAX-CDFI;

[0113] The first model training and detection unit is used to train the YOLOv11 model using the data set PLAX-2D, and use the trained model to extract key point features from the parasternal long axis two-dimensional image of the target patient to obtain the positions of the upper and lower key points of the left ventricular outflow tract; calculate the Euclidean distance between the upper and lower key points of the left ventricular outflow tract, calculate the distance on the map based on the Euclidean distance, and obtain the left ventricular outflow tract width;

[0114] The first model training and detection unit is used to train the Unet++ model using the data set PLAX-CDFI, and use the trained model to extract the aortic valve features from the parasternal long-axis color Doppler image of the target patient to output the aortic valve position information; the regurgitation area of ​​the aortic valve position information is processed to extract the contour of the regurgitation abnormal area, and then the upper and lower contour points of the contraction neck width are extracted to calculate the contraction neck width and the regurgitation jet width;

[0115] The heart valve regurgitation severity judging unit is used to judge the heart valve regurgitation severity of the target patient according to the left ventricular outflow tract width, contraction neck width and regurgitation jet width of the target patient.

[0116] Another specific embodiment of the present application provides a cardiac image data processing terminal, including a processor and a memory, wherein the memory stores a computer-readable program, and when the computer-readable program is called and executed by the processor, the method described above is implemented.

[0117] Another specific embodiment of the present application provides a computer-readable medium, wherein the computer-readable medium stores a computer-readable program, and when the computer-readable program is called and executed by a computer, the method described above is implemented.

[0118] The above is only a preferred implementation of the present application. It should be pointed out that a person skilled in the art can make several modifications and improvements without departing from the inventive concept of the present application, and these all fall within the scope of protection of the present application.

Claims

1. A method for evaluating the degree of aortic valve regurgitation based on deep learning, characterized in that: The steps include: Step 1: Perform image preprocessing and image annotation on the parasternal long axis two-dimensional image to obtain the parasternal long axis two-dimensional data set PLAX-2D; perform image preprocessing and image annotation on the parasternal long axis color Doppler image to obtain the parasternal long axis color Doppler data set PLAX-CDFI; Step 2: Use the dataset PLAX-2D to train the YOLOv11 model, and use the trained model to extract key point features from the target patient's parasternal long axis two-dimensional image to obtain the positions of the upper and lower key points of the left ventricular outflow tract; calculate the Euclidean distance between the upper and lower key points of the left ventricular outflow tract, calculate the distance on the map based on the Euclidean distance, and obtain the left ventricular outflow tract width; Step 3: Use the dataset PLAX-CDFI to train the Unet++ model, and use the trained model to extract the aortic valve features from the target patient's parasternal long-axis color Doppler image to output the aortic valve position information; process the regurgitant area of ​​the aortic valve position information, extract the contour of the abnormal regurgitant area, and then extract the upper and lower contour points of the contraction neck width to calculate the contraction neck width and the regurgitant jet width; Step 4: Determine the severity of the target patient's heart valve regurgitation based on the target patient's left ventricular outflow tract width, contraction neck width, and regurgitation jet width.

2. The method for evaluating aortic valve regurgitation based on deep learning according to claim 1, characterized in that: The step 1 comprises: Step 1.1: Acquire clear parasternal long-axis 2D images and parasternal long-axis color Doppler images of patients aged over 18 years old, and save the patient information to a document, including image ID, left ventricular outflow tract width, contraction neck width, and regurgitant jet width; preprocess the image and hide all text information in the image, including the patient's name, gender, hospital, and number; Step 1.2: Label the parasternal long axis 2D image, use LabelImg as the labeling tool, label the upper and lower key points corresponding to the left ventricular outflow tract width, and mark the left ventricular outflow tract range with a rectangular frame to obtain the parasternal long axis 2D data set PLAX-2D; Step 1.3: Label the parasternal long-axis color Doppler image, use LabelImg as the labeling tool, label the visible aortic valve area, and obtain the parasternal long-axis color Doppler data set PLAX-CDFI; Step 1.4: Divide the datasets PLAX-2D and PLAX-CDFI into training sets, test sets, and validation sets in proportion.

3. The method for evaluating aortic valve regurgitation based on deep learning according to claim 2, characterized in that: The step 2 comprises: Step 2.1: Use the training set and validation set of the PLAX-2D dataset to train the YOLOv11 deep learning model to obtain an automatic inference model of the upper and lower key points of the left ventricular outflow tract; Step 2.2: Calculate the left ventricular outflow tract image ratio; Step 2.2.1: The upper keypoint coordinates (X1, Y1) and lower keypoint coordinates (X2, Y2) of each image are saved in the PLAX-2D dataset, and the Euclidean distance of each image is calculated. Step 2.2.2: Obtain the actual left ventricular outflow tract width from the document, and divide the left ventricular outflow tract width data into m types of data with different depths, where m is the set depth for measuring the left ventricular outflow tract width, m∈{11cm, 12cm, 13cm, 14cm}; Step 2.2.3: Find the image ratio corresponding to each depth Where m is the image depth, D i The LVOT width was actually measured for the parasternal long-axis 2D images; Step 2.3: Use the automatic inference model of the upper and lower key points of the left ventricular outflow tract to infer the parasternal long axis two-dimensional image, obtain the coordinates of the upper key point (x1, y1), the coordinates of the lower key point (x2, y2), and calculate the Euclidean distance between the upper and lower key points Step 2.4: Find the actual distance using Euclidean distance and graph ratio Where m is the depth corresponding to the input parasternal long axis 2D image.

4. The method for evaluating aortic valve regurgitation based on deep learning according to claim 3, characterized in that: The step 3 comprises: Step 3.1: Use the training set and validation set of the PLAX-CDFI dataset to train the Unet++ deep learning model to obtain an automatic aortic valve segmentation model; Step 3.2: Use the aortic valve automatic segmentation model to infer the parasternal long-axis color Doppler image and obtain the coordinate points of the aortic valve region (x i ,y i ); Step 3.3: Expand the aortic valve area; Step 3.3.1: Obtain the horizontal coordinate x1 of the leftmost point of the aortic valve region and the vertical coordinate y1 of the uppermost point, establish the upper left coordinate point (x1, y1) of the rectangular frame, the horizontal coordinate x2 of the rightmost point of the aortic valve region and the vertical coordinate y2 of the lowermost point, establish the lower right coordinate point (x2, y2) of the rectangular frame, and establish the minimum rectangular frame; Step 3.3.2: h = x2 - x1, w = y2 - y1; Step 3.3.3: If h>2cm, jump to step 3.3.4, otherwise jump to step 3.3.5; Step 3.3.4: If w>2cm, jump to step 3.4, otherwise jump to step 3.3.6; Step 3.3.5: Expand the width of the rectangle to 2cm; Step 3.3.6: Expand the height of the rectangular frame to 2cm; Step 3.4: Extract the abnormal area rectangle L(x,y,w,h); Step 3.5: Use traditional image processing methods to obtain the abnormal area, the contraction neck width and the regurgitation jet width; Step 3.5.1: Convert the read image from BGR color space to HSV color space using color space conversion technology; Step 3.5.2: Create the first color mask: define the lower and upper bounds of the HSV color value, and use threshold-based image processing techniques to generate a binary mask; the pixel values ​​in the mask indicate which pixels are within the specified color range and are marked as the target color, and extract the first specified color area; Step 3.5.3: Create a second color mask: define the lower and upper bounds of the HSV color value, and use threshold-based image processing technology to generate a binary mask; the pixel values ​​in the mask indicate which pixels are within the specified color range and are marked as the target color, and the second specified color area is extracted. Step 3.5.4: Use bitwise operation techniques to combine the two masks mask1 and mask2 into a combined mask to extract all target color areas; Step 3.5.5: Perform an erosion operation on the combined mask to remove small noise; Step 3.5.6: Perform a dilation operation on the eroded mask to restore the size of the target area; Step 3.5.7: extracting the mask of the aortic valve region L; Step 3.5.8: Convert the processed image into a grayscale image and generate a binary image through threshold processing; then, extract the contour points in the image; Step 3.5.9: Divide the contour into n regions according to its width; Step 3.5.10: For each divided area, filter out the upper and lower contour points and calculate the distance between them to find the closest point pair; Step 3.5.11: The rightmost point pair is the upper and lower contour points corresponding to the width of the contraction neck. Calculate the Euclidean distance between the two contour points. Calculate the actual distance according to steps 2.2 to 2.3, which is the width of the contraction neck. Step 3.5.12: The length of the line segment corresponding to the straight line with a distance of 1 cm between the line segments corresponding to the width of the contraction neck is the width of the reverse flow beam.

5. The method for evaluating the degree of aortic regurgitation based on deep learning according to claim 4, characterized in that: The step 4 comprises: Step 4.1: Calculate RJW_ratio = contraction neck width / left ventricular outflow tract width; Step 4.2: If RJW_ratio is less than 25% and the width of the contraction neck is less than 0.3 cm, the degree of reflux is judged to be mild; if RJW_ratio is 25% to 64% and the width of the contraction neck is 0.3 cm to 0.6 cm, the degree of reflux is judged to be moderate; if RJW_ratio is greater than 64% and the width of the contraction neck is greater than 0.6 cm, the degree of reflux is judged to be severe.

6. A device for evaluating the degree of aortic valve regurgitation based on deep learning, characterized in that: include: The data set acquisition unit is used to perform image preprocessing and image annotation on the parasternal long axis two-dimensional image to obtain the parasternal long axis two-dimensional data set PLAX-2D; perform image preprocessing and image annotation on the parasternal long axis color Doppler image to obtain the parasternal long axis color Doppler data set PLAX-CDFI; The first model training and detection unit is used to train the YOLOv11 model using the data set PLAX-2D, and use the trained model to extract key point features from the parasternal long axis two-dimensional image of the target patient to obtain the upper and lower key point positions of the left ventricular outflow tract; Calculate the Euclidean distance of the upper and lower key points of the left ventricular outflow tract, calculate the distance on the graph based on the Euclidean distance, and obtain the left ventricular outflow tract width; The first model training and detection unit is used to train the Unet++ model using the data set PLAX-CDFI, and use the trained model to extract the aortic valve features from the parasternal long-axis color Doppler image of the target patient to output the aortic valve position information; the regurgitation area of ​​the aortic valve position information is processed to extract the contour of the regurgitation abnormal area, and then the upper and lower contour points of the contraction neck width are extracted to calculate the contraction neck width and the regurgitation jet width; The heart valve regurgitation severity judging unit is used to judge the heart valve regurgitation severity of the target patient according to the left ventricular outflow tract width, contraction neck width and regurgitation jet width of the target patient.

7. A cardiac image data processing terminal, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer-readable program, and when the computer-readable program is called and executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable medium, characterized in that The computer-readable medium stores a computer-readable program, and when the computer-readable program is called and executed by a computer, the method according to any one of claims 1 to 5 is implemented.

Images