Image detection method and device for mitral valve and computer equipment

Abstract

The invention relates to an image detection method and device for a mitral valve, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring multiple frames of images including a heart, and performing multi-scale feature extraction on the multiple frames of images to obtain multi-scale image features of each frame of image; for each frame of image, determining a mitral valve area of the heart in each frame of image according to the multi-scale image features of the image; determining the area of a mitral valve opening in each frame of image based on the mitral valve area of the heart in each frame of image; and generating a detection result of the mitral valve membrane of the heart according to the area of the mitral valve opening in each frame of image. By adopting the method, the problems that a traditional manual measurement method is time-consuming and is easily influenced by subjective factors and the like can be solved, the efficiency and accuracy of mitral valve evaluation are also remarkably improved, professional requirements on operators are reduced, and the flexibility and practicability of clinical application are enhanced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an image detection method, apparatus, computer equipment, computer-readable storage medium and computer program product for a mitral valve. Background Art

[0002] The mitral valve is very important for cardiac analysis. As one of the four valves of the heart, the mitral valve is located between the left atrium and the left ventricle. It consists of anterior and posterior leaflets, attached to the fibrous ring or annulus, and connected to the papillary muscles on the wall of the left ventricle by chordae tendineae. Its main function is to open during the filling phase of the heart to allow blood to flow from the left atrium to the left ventricle, and to close during the systole of the heart to prevent blood from flowing back into the left atrium. Accurate assessment of the status and function of the mitral valve is crucial to the diagnosis and treatment of heart disease.

[0003] However, the traditional measurement method for the mitral valve orifice mainly relies on the experience and manual operation of echocardiography experts, which is not only time-consuming but also easily affected by subjective factors, resulting in differences in results between different observers. The dynamic and real-time nature of ultrasound scanning places very high demands on the operator. At the same time, the high difficulty of echocardiography scanning also makes its acquisition and diagnosis process highly subjective and greatly affected by the operator. Therefore, the use of echocardiography requires users to pay a very high learning cost. In addition, the manual measurement process is complicated and requires precise selection of the maximum mitral valve orifice area during diastole, and repeated operations in multiple cardiac cycles to improve measurement consistency, which is not always widely adopted in clinical practice. Summary of the invention

[0004] Based on this, it is necessary to provide an image detection method, device, computer equipment, computer-readable storage medium and computer program product for the mitral valve that can improve the efficiency and accuracy of measuring the maximum mitral valve orifice area in order to address the above technical problems.

[0005] In a first aspect, the present application provides an image detection method for a mitral valve, comprising:

[0006] Acquire multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image;

[0007] For each frame of image, determining the mitral valve region of the heart in each frame of image according to multi-scale image features of the image;

[0008] Determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image;

[0009] The detection result of the mitral valve of the heart is generated according to the area of ​​the mitral valve orifice in each frame of the image.

[0010] In one embodiment, for each frame of image, determining the mitral valve region of the heart in each frame of image according to multi-scale image features of the image includes:

[0011] Based on the multi-scale image features of the targeted image, a detection frame is generated in the targeted image, wherein the detection frame is used to characterize the positions of different tissue structures in the heart; according to image quality evaluation rules and the detection frame generated in the targeted image, the image quality of the targeted image is determined; and according to the image quality of each frame of the image, the mitral valve region of the heart in each frame of the image is determined.

[0012] In one embodiment, the detection frame at least includes a left ventricle detection frame; and determining the mitral valve region of the heart in each frame of image according to the image quality of each frame of image comprises:

[0013] According to the image quality of each frame of image, multiple frames of target images are screened out from the multiple frames of image, and the multiple frames of target images are images of multiple continuous frames; for each frame of target image, the target image is cropped according to the left ventricle detection frame in the target image to obtain a left ventricle image; each pixel point in the left ventricle image is classified to obtain a position type of each pixel point, and the position types include belonging to the mitral valve and not belonging to the mitral valve; according to the pixel points whose position types are pixels belonging to the mitral valve, the left ventricle image is segmented to obtain a mitral valve image, and the mitral valve image represents the mitral valve area of ​​the heart.

[0014] In one embodiment, each frame of the image is a frame of a mitral valve image; and generating the detection result of the mitral valve of the heart according to the area of ​​the mitral valve orifice in each frame of the image includes:

[0015] The area of ​​the mitral valve orifice in each frame of the mitral valve image is converted into a coordinate position in a preset coordinate system; a mitral valve orifice area change curve is generated according to the coordinate position of each frame of the mitral valve image in the preset coordinate system and the timestamp of each frame of the mitral valve image, wherein the mitral valve orifice area change curve represents in real time how the area of ​​the mitral valve orifice changes with time; and the detection result of the mitral valve of the heart is determined according to the mitral valve orifice area change curve.

[0016] In one embodiment, generating a mitral valve area change curve according to the coordinate position of each frame of the mitral valve image in a preset coordinate system and the timestamp of each frame of the mitral valve image includes:

[0017] An initial time domain curve is generated according to the coordinate position of each frame of the mitral valve image in a preset coordinate system and the timestamp of each frame of the mitral valve image; the initial time domain curve is converted from a time domain form to a frequency domain form to obtain an initial frequency domain curve; the initial frequency domain curve is low-frequency filtered by a low-pass filter to obtain a filtered frequency domain curve; the filtered frequency domain curve is converted from a frequency domain form to a time domain form to obtain a mitral valve orifice area change curve.

[0018] In one embodiment, determining the detection result of the mitral valve of the heart according to the mitral valve area change curve includes:

[0019] According to the mitral valve area change curve, the maximum area of ​​the mitral valve orifice is determined; the maximum area of ​​the mitral valve orifice is compared with the mitral valve stenosis threshold, and based on the comparison result, the mitral valve stenosis detection result of the heart is determined; according to the mitral valve area change curve, the mitral valve area change rate curve is generated, and the mitral valve area change rate curve represents the change trend of the area of ​​the mitral valve orifice over time in real time; according to the mitral valve area change rate curve, the recovery detection result of the mitral valve of the heart is determined.

[0020] In a second aspect, the present application further provides an image detection device for a mitral valve, comprising:

[0021] An extraction module, used to acquire multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image;

[0022] A first determination module is used to determine, for each frame of image, a mitral valve region of the heart in each frame of image according to multi-scale image features of the image;

[0023] A second determination module, configured to determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image;

[0024] A generating module is used to generate the detection result of the mitral valve of the heart according to the area of ​​the mitral valve orifice in each frame of the image.

[0025] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0026] Acquire multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image;

[0027] For each frame of image, determining the mitral valve region of the heart in each frame of image according to multi-scale image features of the image;

[0028] Determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image;

[0029] The detection result of the mitral valve of the heart is generated according to the area of ​​the mitral valve orifice in each frame of the image.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0031] Acquire multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image;

[0032] For each frame of image, determining the mitral valve region of the heart in each frame of image according to multi-scale image features of the image;

[0033] Determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image;

[0034] The detection result of the mitral valve of the heart is generated according to the area of ​​the mitral valve orifice in each frame of the image.

[0035] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0036] Acquire multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image;

[0037] For each frame of image, determining the mitral valve region of the heart in each frame of image according to multi-scale image features of the image;

[0038] Determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image;

[0039] The detection result of the mitral valve of the heart is generated according to the area of ​​the mitral valve orifice in each frame of the image.

[0040] The above-mentioned image detection method, device, computer equipment, computer-readable storage medium and computer program product for the mitral valve obtain multi-frame images including the heart, extract multi-scale features from the multi-frame images, and obtain multi-scale image features for each frame of the image; image features at different scales are captured, thereby more accurately identifying the heart structure. This approach helps to improve the accuracy of positioning the heart anatomical structure (such as the mitral valve) in subsequent steps. It also reduces the high dependence on the operator's experience and skills, so that even inexperienced operators can obtain high-quality heart images.

[0041] For each frame of image, the mitral valve area of ​​the heart in each frame of image is determined based on the multi-scale image features of the image; the mitral valve area is automatically detected and located without manual intervention, which greatly improves work efficiency and avoids human errors. And the determination of the mitral valve area based on multi-scale features can better adapt to changes and noise in the image, and improve the system's ability to process images of different quality and viewing angles.

[0042] Based on the mitral valve region of the heart in each frame of the image, the area of ​​the mitral valve orifice in each frame of the image is determined; the mitral valve orifice area (MVA) in each frame of the image is automatically calculated, thereby achieving a quantitative evaluation of the mitral valve function and providing more objective data support.

[0043] The detection result of the mitral valve of the heart is generated according to the area of ​​the mitral valve orifice in each frame of the image. By summarizing the MVA data in each frame of the image, a MVA curve that changes over time can be constructed to monitor the functional state of the mitral valve in real time and provide feedback information to clinicians in a timely manner.

[0044] Through the above steps, not only the problems of traditional manual measurement methods being time-consuming and susceptible to subjective factors are solved, but also the efficiency and accuracy of mitral valve assessment are significantly improved, the professional requirements for operators are reduced, and the flexibility and practicality of clinical applications are enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A diagram showing an application environment of an image detection method for a mitral valve in one embodiment;

[0047] Figure 2is a schematic diagram of a flow chart of an image detection method for a mitral valve in one embodiment;

[0048] Figure 3 is an overall framework diagram of an image detection method for a mitral valve in one embodiment;

[0049] Figure 4 is a schematic flow chart of an image detection method for a mitral valve in another embodiment;

[0050] Figure 5 is a structural block diagram of an image detection device for a mitral valve in one embodiment;

[0051] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] The image detection method for the mitral valve provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 is used to generate an image detection request for the mitral valve, and send the image detection request for the mitral valve to the server 104, so that the server 104 generates the detection result of the mitral valve of the heart according to the area of ​​the mitral valve orifice in each frame of the image. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0054] In an exemplary embodiment, Figure 2 As shown, a method for image detection of mitral valve is provided, and the method is applied to Figure 1The server 104 in the example is used as an example to illustrate, including the following steps 202 to 208. Among them:

[0055] Step 202: Acquire multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image.

[0056] Among them, multi-frame images refer to a series of static images extracted from a continuous video stream or dynamic image. Each frame represents a picture at a certain moment in the video. For cardiac echocardiography, these frames capture the state of the heart at different time points, including diastole (when the heart is relaxed) and systole (when the heart pumps blood).

[0057] Multi-scale image features refer to extracting representative information from an image by processing the image at different resolutions or windows of different sizes. For example, at a larger scale, you may only be able to see the general outline of the entire heart; while at a smaller scale, you can see finer structural details, such as the specific morphology of the mitral valve.

[0058] Specifically, first, a multi-frame image including the heart is obtained, including: converting the dynamic cardiac image from the ultrasound device (especially the parasternal short-axis mitral valve section PSAX-MV perspective) into a single-frame image. The central area of ​​each frame image is cropped to ensure that the image focuses on the cardiac structure and removes unnecessary background information. The cropped image is adjusted to a uniform resolution (e.g., 320x320 pixels) using bilinear interpolation to obtain a multi-frame image of the heart for consistency and efficiency of subsequent processing.

[0059] Multi-scale feature extraction is then performed on multiple frames of images, including: creating a set of input images containing multiple resolution versions. Each version corresponds to a different scale and is used to capture different levels of features from global to local. The mitral valve image detection network is used, which adopts a feature pyramid architecture and can extract multi-scale image features at different scales. The two subnets of the mitral valve image detection network perform classification tasks (identifying key anatomical structures) and regression tasks (optimizing the position and size of the bounding box) to accurately mark the key anatomical structures of the heart, including the left ventricle, right ventricle, anterior leaflet of the mitral valve, and posterior leaflet of the mitral valve.

[0060] Finally, the multi-scale image features of each frame are obtained, including: after being processed by the feature pyramid and the mitral valve image detection network, the multi-scale feature maps corresponding to each frame are obtained. These feature maps contain information at different levels, including both the overall outline of the heart and details such as the mitral valve.

[0061] Step 204 : for each frame of image, determine the mitral valve region of the heart in each frame of image according to the multi-scale image features of the image.

[0062] The mitral valve is one of the four valves of the heart, located between the left atrium and the left ventricle. It consists of two leaflets: the anterior leaflet and the posterior leaflet. The two leaflets are attached to a ring-shaped structure called the annulus fibrosus or annulus and connected to the papillary muscles on the wall of the left ventricle by chordae tendineae.

[0063] The mitral valve region refers to the portion of the heart image that can be clearly identified to include the anterior and posterior leaflets of the mitral valve and the surrounding anatomical structures. Specifically, the mitral valve region refers to the specific anatomical location that can be identified and defined in each frame of the echocardiographic image that includes the mitral valve.

[0064] Specifically, after completing the anatomical structure detection, the mitral valve area in each frame of the image is further accurately defined. Specifically, the multiple frames of images that have been cropped twice and adjusted in resolution are input into the segmentation branch model. The segmentation branch model is specifically used to accurately segment the mitral valve leaflets based on the multi-scale image features of the multiple frames of images, thereby clearly defining the mitral valve area. The segmentation model will output a binary image in which the specific location of the mitral valve is marked. This area is the mitral valve area, which includes the anterior and posterior leaflets of the mitral valve and the range of their attachment points.

[0065] Step 206: Determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image.

[0066] The mitral valve orifice refers to the opening through which blood flows from the left atrium to the left ventricle when the mitral valve opens. This opening is formed by the two leaflets of the mitral valve, the anterior leaflet and the posterior leaflet, and is open during the filling phase (diastole) of the heart and closed during the contraction phase (ejection phase).

[0067] The area of ​​the mitral valve orifice refers to the maximum cross-sectional area of ​​the mitral valve orifice when it is open. This is an important parameter to measure the size of the mitral valve opening, especially in the evaluation of diseases such as mitral stenosis.

[0068] Specifically, first, the contour of the mitral valve orifice is outlined, including: based on the segmentation results, using an edge detection algorithm or morphological operation to identify and outline the contour of the mitral valve orifice. Optionally, special attention should be paid to the image at the end of diastole, because the mitral valve orifice reaches the maximum open state at this time. The outlined contour is smoothed to remove possible noise points or abnormal protrusions, and finally ensure that the obtained mitral valve orifice contour is continuous and smooth. Then the mitral valve orifice area is calculated, including: using a suitable geometric method or numerical integration technique to calculate the area of ​​the mitral valve orifice according to the coordinates of the contour points, and recording the calculated mitral valve orifice area. Optional calculation methods include but are not limited to polygonal area formula, Green's formula, etc.

[0069] Step 208: Generate a detection result of the mitral valve of the heart according to the area of ​​the mitral valve orifice in each frame of the image.

[0070] The detection result refers to the information set that is ultimately generated by the image detection method and can reflect the functional status of the heart's mitral valve. It combines various features extracted from multiple frames of images and is obtained through a series of processing steps (such as feature extraction, region definition, area calculation, etc.), aiming to provide doctors with a reliable basis for diagnosis.

[0071] Specifically, the mitral valve area data is first summarized, including: extracting the calculated mitral valve area value from each video frame, and arranging these mitral valve area values ​​in chronological order to form a time series data set to reflect the change of the mitral valve area with the cardiac cycle.

[0072] Then, the mitral valve area change curve is constructed and optimized, including: based on the time series data, a frame-by-frame mitral valve area change curve is drawn. This curve reflects the change of the mitral valve area over time in real time, especially the different performances in diastole and systole. Optionally, in order to improve the accuracy of detection, a Fourier transform-based denoising module is introduced. The specific steps include fast Fourier transform, low-pass filtering, and inverse fast Fourier transform to remove high-frequency noise and retain low-frequency components, so as to obtain a more refined and smooth mitral valve area change curve.

[0073] Next, the mitral valve function is quantitatively evaluated, including: identifying whether the mitral valve opening is restricted by observing the mitral valve area change curve. When the mitral valve area decreases below a certain threshold (for example, less than 2 square centimeters is moderate stenosis, and less than 1.5 square centimeters is severe stenosis), it indicates that mitral stenosis may exist. The mitral valve area change curve can help evaluate the closure of the mitral valve during systole. If the mitral valve area is found to be abnormally increased during systole, it may be a sign of mitral regurgitation.

[0074] Finally, the qualitative description and diagnostic recommendations include: combining the mitral valve area change curve and quantitative evaluation results to describe in detail the functional status of the mitral valve, such as whether there is stenosis or regurgitation, and its severity. For patients who have received treatment, the mitral valve area change curve is used to track the changes in mitral valve function before and after treatment to evaluate the effectiveness of the treatment. Based on the evaluation results, provide doctors with diagnostic recommendations, including further examinations and treatment options.

[0075] In one of the embodiments, a detection frame is generated in the targeted image based on multi-scale image features, and the detection frame is used to characterize the positions of different tissue structures in the heart; the image quality of the targeted image is determined according to image quality evaluation rules and the detection frame generated in the targeted image; and the mitral valve region of the heart in each frame of the image is determined based on the image quality of each frame of the image.

[0076] Among them, the detection frame refers to a rectangular boundary used to mark or enclose a specific target object in an image. In the present application, the detection frame is used to characterize the location of different tissue structures in the heart, such as the left ventricle, right ventricle, anterior leaflet of the mitral valve, and posterior leaflet of the mitral valve. Tissue structure refers to different components inside the heart, which appear as different morphological and texture features in echocardiographic images, including but not limited to the left ventricle, right ventricle, anterior leaflet of the mitral valve, and posterior leaflet of the mitral valve. Image quality evaluation rules refer to a set of predefined standards or criteria used to evaluate the quality of each frame of the image. These rules are based on whether key anatomical structures can be clearly displayed in the image, as well as factors such as the overall clarity and contrast of the image. Image quality refers to the extent to which the image meets predetermined quality standards, especially in capturing and displaying the internal structure of the heart.

[0077] Specifically, refer to Figure 3In the detection branch, the classification subnet and regression subnet in the mitral valve image detection network first identify and locate key anatomical structures (such as the left ventricle, right ventricle, anterior leaflet and posterior leaflet of the mitral valve) according to the multi-scale image features of each frame, and output the precise bounding box containing these structures, namely the detection box. Then a set of image quality evaluation rules is established. Optionally, when the detection box cannot identify the left ventricle, the image quality is 1 point, when the detection box can identify the left ventricle but cannot identify the right ventricle, the image quality is 2 points, when the detection box can identify the left ventricle and the right ventricle but cannot identify the anterior leaflet and the posterior leaflet of the valve, the image quality is 3 points, when the detection box can identify the left ventricle and the right ventricle but can only identify one valve, the image quality is 4 points, and when the detection box can simultaneously identify the left ventricle, the right ventricle, the anterior leaflet and the posterior leaflet of the valve, the image quality is 5 points. Combined with the detection box information, a quality score is generated for each frame of the image according to the image quality evaluation rules. Then record the video segments with quality scores greater than the preset quality threshold (for example, 3) to ensure that the images used for further analysis are of high quality. Finally, based on the image quality score, images for further analysis are screened out in each frame of the image, and the image quality of the screened out images for further analysis is determined.

[0078] The introduction of image quality evaluation rules ensures that only high-quality images are used for further analysis. This method reduces the risk of false detection or missed detection due to low-quality images (such as the presence of noise or artifacts), enhances the robustness of the system and the reliability of the results. And by scoring the quality of each frame of the image, high-quality image segments suitable for further analysis can be quickly screened out, thereby speeding up the overall diagnosis process and improving clinical work efficiency.

[0079] In one of the embodiments, based on the image quality of each frame of image, multiple frames of target images are screened out from the multiple frames of image, and the multiple frames of target images are images of multiple consecutive frames; for each frame of target image, the target image is cropped according to the left ventricle detection frame in the target image to obtain a left ventricle image; each pixel point in the left ventricle image is classified to obtain a position type of each pixel point, and the position types include belonging to the mitral valve and not belonging to the mitral valve; based on the pixel points whose position type is that of the mitral valve, the left ventricle image is segmented to obtain a mitral valve image, and the mitral valve image represents the mitral valve area of ​​the heart.

[0080] The multi-frame target images refer to high-quality images of multiple consecutive frames selected from the original multi-frame images. These images have undergone image quality assessment and have sufficient resolution and clarity to accurately display the internal structure of the heart.

[0081] The left ventricle detection box is a rectangular bounding box generated in each frame of the target image to mark and enclose the position of the left ventricle. The detection box identifies and locates the left ventricle in the heart through the mitral valve image detection network.

[0082] The left ventricle image is the image obtained by cropping the left ventricle detection frame from each frame of the target image. The cropping process removes unnecessary background information, making the image more focused on the left ventricle and surrounding areas.

[0083] The location type refers to the classification result of each pixel in the left ventricle image, which is divided into two types, including: belonging to the mitral valve (indicating that the pixel is located in the mitral valve area) and not belonging to the mitral valve (indicating that the pixel is not in the mitral valve area).

[0084] The mitral valve image is an image obtained through segmentation processing, which specifically represents the mitral valve area of ​​the heart. The image consists of all pixels classified as "belonging to the mitral valve" and clearly identifies the locations of the anterior and posterior leaflets of the mitral valve.

[0085] Specifically, refer to Figure 3 The segmentation branch in , firstly selects high-quality and continuous target images from the original multiple frames of images, including: generating a quality score for each frame of image based on predefined image quality evaluation rules. And record the video segments whose quality scores are greater than the preset quality threshold to ensure that these images are of high quality and continuous. This step ensures that the images used for subsequent analysis are clear and reliable. It can be understood that by selecting multiple frames of high-quality target images based on image quality scores, the images used for subsequent analysis are ensured to be clear and reliable. This reduces the risk of false detection or missed detection due to low-quality images and improves the accuracy of the final analysis results.

[0086] Then, a left ventricle detection frame is generated in each frame of the target image, and the image is cropped according to the frame to obtain an image focused on the left ventricle and its surrounding area, including: using a mitral valve image detection network to process each frame of the target image, the network uses a feature pyramid architecture to extract multi-scale image features, and outputs an accurate bounding box containing the position of the left ventricle, i.e., a detection box. According to the identified left ventricle detection frame, secondary cropping is performed in the ultrasound image to remove unnecessary background information, so that the image is more focused on the left ventricle and surrounding key anatomical structures.

[0087] Next, each pixel in the cropped left ventricle image is classified to determine whether it belongs to the mitral valve region, including: using a pixel classification model to classify each pixel in the left ventricle image into two position types: "belonging to the mitral valve" and "not belonging to the mitral valve". A binary image is generated, in which the position type of each pixel is marked, especially the specific position of the mitral valve.

[0088] Finally, based on the pixel classification results, the left ventricle image is segmented to obtain an image specifically representing the mitral valve area, including: based on the classification results, all pixels classified as "belonging to the mitral valve" are combined together to form a mitral valve image. The image clearly identifies the positions of the anterior and posterior leaflets of the mitral valve. Optionally, additional smoothing or morphological operations are introduced to remove possible noise points or abnormal protrusions to ensure the continuity and smoothness of the segmentation results.

[0089] Since the target image is cropped twice using the left ventricle detection frame, the focus is on the key anatomical structures inside the heart, especially the mitral valve. This method enhances the ability to capture details such as the mitral valve and ensures the accuracy of subsequent analysis. The entire process from image screening to the final definition of the mitral valve area is automated without manual intervention. This not only improves work efficiency, but also maintains consistency and repeatability, is not affected by the operator's subjective factors, and enhances the robustness and reliability of the system. In addition, by classifying each pixel in the left ventricle image and segmenting it according to the pixels belonging to the mitral valve, an image specifically representing the mitral valve area is generated. This detailed segmentation and classification helps to more comprehensively evaluate the functional status of the mitral valve and provide a more objective and reliable basis for diagnosis.

[0090] In one of the embodiments, the area of ​​the mitral valve orifice in each frame of the mitral valve image is converted into a coordinate position in a preset coordinate system; a mitral valve orifice area change curve is generated based on the coordinate position of each frame of the mitral valve image in the preset coordinate system and the timestamp of each frame of the mitral valve image, and the mitral valve orifice area change curve represents in real time how the area of ​​the mitral valve orifice changes with time; based on the mitral valve orifice area change curve, the detection result of the mitral valve of the heart is determined.

[0091] The preset coordinate system refers to a unified reference frame used to standardize the mitral valve area information in different frames. This coordinate system can be two-dimensional or three-dimensional and has a fixed origin and axis to ensure that all data are compared and analyzed under the same standard.

[0092] The coordinate position refers to the specific position of the mitral valve area in each frame of the mitral valve image in a preset coordinate system. These positions can be described by one or more pairs of values ​​(such as x, y coordinates), depending on the type of coordinate system used. It can be understood that each coordinate position represents the spatial location of the mitral valve area in a frame of the image, so that data between different frames can be accurately compared and tracked, which is particularly important when evaluating changes in the mitral valve orifice over time.

[0093] Timestamp refers to the time mark that records the moment each frame of the image is captured. It can be an absolute time (for example, a specific date and time) or a relative time (for example, the number of seconds relative to the start of the video). In this application, the timestamp provides information about the time dimension for each frame of the image, so that the changes in the mitral valve area can be tracked in a time series. This is crucial for constructing an accurate mitral valve area change curve because it allows the area changes to be associated with specific cardiac cycle stages.

[0094] The mitral valve area change curve refers to a curve generated by summarizing the mitral valve area data in multiple frames of images and combining their corresponding coordinate positions and timestamps to represent in real time how the mitral valve area changes over time.

[0095] Specifically, the mitral valve orifice area calculated in each frame of the mitral valve image is first converted into a unified preset coordinate system to ensure that all data are compared under the same standard, including: establishing a preset coordinate system (such as a two-dimensional or three-dimensional coordinate system) with a fixed origin and axis. For each frame of the mitral valve image, the position information of the mitral valve orifice area is converted to a specific coordinate position in the preset coordinate system. This step may involve operations such as geometric transformation and scaling to ensure data consistency between different frames.

[0096] Then record the timestamp of each frame of the mitral valve image, including: adding a timestamp to each frame of the image, recording the specific time it was captured or the time point relative to the beginning of the video. This can be achieved through the time encoding function of the ultrasound device, or it can be added manually during post-processing.

[0097] Next, based on the coordinate position and timestamp of each frame of the mitral valve image in the preset coordinate system, the mitral valve area data in all frames are summarized to generate a curve that can represent the change of the mitral valve area over time in real time, including: collecting the mitral valve area values ​​in all frame images and organizing them together with the corresponding timestamps into a time series data set. Based on the time series data, a frame-by-frame mitral valve area change curve is drawn. This curve intuitively reflects the change trend of the mitral valve area in different cardiac cycles, especially the different performances in diastole and systole. Optionally, in order to improve the accuracy of the prediction, a Fourier transform-based denoising module (such as fast Fourier transform, low-pass filtering, and inverse fast Fourier transform) is introduced to optimize the original curve to remove high-frequency noise and retain low-frequency components, thereby obtaining a more refined and smooth mitral valve area change curve.

[0098] Finally, based on the generated mitral valve area change curve, the functional state of the mitral valve of the heart is comprehensively evaluated, and the final test results are obtained, including: by observing the mitral valve area change curve, identifying whether the mitral valve opening is restricted (for example, for evaluating mitral stenosis), or evaluating the closure of the mitral valve during systole (for example, finding signs of mitral regurgitation). Combined with the mitral valve area change curve and the quantitative evaluation results, the functional state of the mitral valve is described in detail, such as whether there is stenosis or regurgitation and its severity. And for patients who have received treatment, the mitral valve area change curve is used to track the changes in mitral valve function before and after treatment to evaluate the effectiveness of the treatment.

[0099] By converting the mitral valve area into a preset coordinate system, all measured data are ensured to be in the same standard framework. This eliminates errors caused by different scanning angles, equipment resolution differences, and other factors, and improves the consistency and reliability of data analysis. In addition, the introduction of timestamps allows each frame of the image to have clear time information, which can accurately track the changes in the mitral valve area over time. This is very important for understanding the dynamic behavior of the heart during a complete cardiac cycle, especially for evaluating the different performances of the mitral valve in diastole and systole. The generated mitral valve area change curve can intuitively show the trend of the mitral valve area over time, which helps to identify potential problems such as mitral stenosis or regurgitation. After the curve is denoised and optimized by Fourier transform technology, the obtained mitral valve area change curve is more refined and smoother, which further improves the stability and accuracy of the prediction, thereby improving the reliability of diagnosis.

[0100] In one of the embodiments, an initial time domain curve is generated based on the coordinate position of each frame of the mitral valve image in a preset coordinate system and the timestamp of each frame of the mitral valve image; the initial time domain curve is converted from a time domain form to a frequency domain form to obtain an initial frequency domain curve; the initial frequency domain curve is low-frequency filtered by a low-pass filter to obtain a filtered frequency domain curve; the filtered frequency domain curve is converted from a frequency domain form to a time domain form to obtain a mitral valve area change curve.

[0101] The initial time domain curve refers to a curve generated by summarizing the coordinate position of each frame of the mitral valve image in a preset coordinate system and its corresponding timestamp, which can represent the change of the mitral valve orifice area over time in real time.

[0102] The time domain format refers to the way in which signals or data are presented in chronological order. In this format, each data point is associated with a specific time point and is usually used to directly show how the signal changes over time. Understandably, data in the time domain format is easy to understand and visualize, and the specific trend of changes in the mitral valve area over time can be directly observed. However, time domain data may contain noise and other high-frequency fluctuations, affecting the accuracy of the analysis.

[0103] Frequency domain refers to the way of converting time domain signals into frequency components through mathematical transformations (such as Fourier transform). In the frequency domain, the signal is decomposed into a series of sine wave combinations with different frequencies and amplitudes. Understandably, the frequency domain form allows us to analyze the frequency composition of the signal and identify which frequency components represent actual physiological phenomena and which are noise. This is very helpful for removing high-frequency noise and retaining low-frequency useful information.

[0104] The initial frequency domain curve refers to the curve obtained by converting the initial time domain curve from the time domain to the frequency domain through fast Fourier transform. This curve shows the frequency component distribution of the original mitral valve area change curve.

[0105] A low-pass filter is a signal processing tool used to retain low-frequency components in a signal while removing high-frequency components. It determines which frequency components can be retained by setting a cutoff frequency. In this application, the role of the low-pass filter is to remove high-frequency noise in the initial frequency domain curve and only retain low-frequency components, which are more consistent with actual physiological phenomena, thereby improving the accuracy of subsequent analysis.

[0106] The filtered frequency domain curve refers to the frequency domain curve after being processed by a low-pass filter. This curve has removed most of the high-frequency noise and only retains the useful low-frequency components.

[0107] Specifically, refer to Figure 3 The correction branch in the algorithm first summarizes the mitral valve area data in all frames based on the coordinate position of each frame of the mitral valve image in the preset coordinate system and its timestamp, and constructs an initial time domain curve. This curve intuitively reflects the trend of the change of the mitral valve area over time. Then, the initial time domain curve is converted from the time domain to the frequency domain using the fast Fourier transform to obtain the initial frequency domain curve. This step reveals the frequency component distribution of the original signal, including low-frequency and high-frequency components. Next, a low-pass filter is applied to the initial frequency domain curve, and a suitable cutoff frequency is selected to remove high-frequency noise and retain only low-frequency components. This ensures that the final curve better reflects the actual change in the mitral valve area. Finally, the filtered frequency domain curve is converted back to the time domain form by the inverse fast Fourier transform to obtain the optimized mitral valve area change curve. This curve is more refined and smooth, which enhances the quality of the signal and improves the stability and accuracy of the prediction.

[0108] Since the generated initial time domain curve intuitively reflects the changing trend of the mitral valve area over time, especially in different stages of the cardiac cycle (such as diastole and systole). This method can accurately capture the dynamic changes of the mitral valve area, provide detailed physiological information, and help to more accurately evaluate cardiac function. And the initial time domain curve is converted into frequency domain form by Fourier transform, and then a low-pass filter is applied to remove high-frequency noise, leaving only low-frequency components. This step significantly improves the quality of the signal, removes high-frequency fluctuations and artifacts in the original data, and makes the final mitral valve area change curve smoother and more stable. And the entire process from generating the initial time domain curve to finally generating the optimized mitral valve area change curve is automated, reducing the need for human intervention and reducing the influence of subjective factors of the operator. This not only improves work efficiency, but also ensures the consistency and repeatability of the results.

[0109] In one of the embodiments, the maximum area of ​​the mitral valve orifice is determined based on the mitral valve orifice area change curve; the maximum area of ​​the mitral valve orifice is compared with the mitral valve stenosis threshold, and based on the comparison result, the mitral valve stenosis detection result of the heart is determined; based on the mitral valve orifice area change curve, the mitral valve orifice area change rate curve is generated, and the mitral valve orifice area change rate curve represents in real time the changing trend of the area of ​​the mitral valve orifice over time; based on the mitral valve orifice area change rate curve, the recovery detection result of the mitral valve of the heart is determined.

[0110] Among them, the maximum area of ​​the mitral valve orifice refers to the maximum value of the mitral valve orifice area in the mitral valve orifice area change curve. It usually occurs at the end of cardiac diastole, that is, when the left ventricle is filling. Understandably, the maximum area of ​​the mitral valve orifice is a key parameter for evaluating the functional status of the mitral valve, and is used to identify whether there are problems such as mitral stenosis. Under normal circumstances, the mitral valve orifice area is approximately 4-6 square centimeters; when the MVA decreases to less than 2 square centimeters, it is considered to be moderate stenosis; when it is less than 1.5 square centimeters, it is considered to be severe stenosis.

[0111] The mitral valve stenosis threshold refers to the standard critical value used to determine whether the mitral valve is stenotic. It can be set to a specific area value, such as 2 square centimeters or 1.5 square centimeters, to distinguish between normal and abnormal conditions.

[0112] The comparison result refers to the result obtained by comparing the maximum area of ​​the mitral valve orifice with the threshold value of mitral valve stenosis. Through this comparison, it can be determined whether the mitral valve orifice area is lower than the critical value, thereby judging whether there is stenosis.

[0113] The stenosis test result refers to the specific conclusion of mitral valve stenosis determined based on the comparison results. It may include information such as whether stenosis exists and the degree of stenosis (mild, moderate or severe).

[0114] The mitral valve area change rate curve refers to a curve that can represent the change trend of the mitral valve area over time in real time by taking the derivative of the mitral valve area change curve. This curve reflects the speed of area change. Understandably, the mitral valve area change rate curve not only shows the change trend of the mitral valve area, but also reveals the time point of rapid change, which is very important for evaluating the functional status of the mitral valve. In addition, it helps to identify potential problems, such as mitral regurgitation, and evaluate the effect of treatment.

[0115] The recovery test result refers to the specific conclusion of the heart mitral valve recovery determined based on the mitral valve area change rate curve. This includes but is not limited to evaluating the changes in mitral valve function before and after treatment, and monitoring the progress of the patient's recovery process.

[0116] Specifically, firstly, the maximum area of ​​the mitral valve orifice is found from the mitral valve orifice area change curve, including: identifying the maximum value by analyzing the mitral valve orifice area change curve. This maximum value usually occurs at the end of the cardiac diastole, that is, when the left ventricle is filled. And the specific value of the maximum area is clearly recorded as the basis for subsequent comparison.

[0117] Then compare the maximum area of ​​the mitral valve orifice with the preset stenosis threshold (e.g., 2 square centimeters or 1.5 square centimeters) to determine whether there is stenosis, including: referring to medical standards, setting the critical value of mitral valve stenosis (e.g., less than 2 square centimeters for moderate stenosis, less than 1.5 square centimeters for severe stenosis). Compare the maximum area determined in the previous step with the preset stenosis threshold to determine whether it is lower than the critical value. And clearly record the comparison results, such as the maximum area is greater than 2 square centimeters or the maximum area is less than 1.5 square centimeters.

[0118] Based on the comparison results, a specific stenosis detection conclusion is drawn, including whether stenosis exists and its severity, including: generating a detailed stenosis detection report based on the comparison results. For example, if the maximum area is less than 1.5 square centimeters, it is judged as severe stenosis; if it is between 1.5 and 2 square centimeters, it is judged as moderate stenosis.

[0119] Next, by taking the derivative of the mitral valve area change curve, a curve is generated that can represent the change trend of the mitral valve area over time in real time, including: performing differential processing on the mitral valve area change curve, calculating the rate of change of the area at each moment, and generating a mitral valve area change rate curve. Optionally, in order to improve the quality of the mitral valve area change rate curve, smoothing or filtering technology can be introduced to remove possible noise points or abnormal protrusions, so as to ensure the continuity and smoothness of the mitral valve area change rate curve.

[0120] Finally, based on the mitral valve area change rate curve, the changes in mitral valve function before and after treatment are evaluated, the patient's recovery process is monitored, and corresponding medical advice is provided, including: evaluating the effect of treatment by observing the trend of the mitral valve area change rate curve before and after treatment. For example, if the curve tends to be stable after treatment and the maximum area increases, it indicates that the treatment is effective.

[0121] By determining the maximum area of ​​the mitral valve orifice and comparing it with the stenosis threshold, it is possible to accurately determine whether mitral stenosis exists and its severity. This method provides a clear quantitative basis and reduces the errors caused by subjective judgment. The generated mitral valve area change rate curve can characterize the changing trend of the mitral valve area over time in real time, helping doctors to dynamically monitor changes in cardiac function, especially the cardiac recovery process before and after treatment. By taking the derivative of the mitral valve area change curve and generating a change rate curve, the noise and abnormal fluctuations in the original data can be better removed, the real functional change information can be retained, and the quality and reliability of the signal can be improved.

[0122] In an exemplary embodiment, Figure 4 As shown, it includes steps 402 to 408. Among them:

[0123] Step 402, acquiring multiple frames of images including the heart, performing multi-scale feature extraction on the multiple frames of images, and obtaining multi-scale image features of each frame of image;

[0124] Step 404, based on the multi-scale image features of the targeted image, a detection frame is generated in the targeted image, the detection frame is used to characterize the positions of different tissue structures in the heart; according to the image quality evaluation rule and the detection frame generated in the targeted image, the image quality of the targeted image is determined; according to the image quality of each frame of the image, multiple frames of target images are screened out from the multiple frames of the image, and the multiple frames of the target image are images of multiple consecutive frames; for each frame of the target image, according to the left ventricle detection frame in the targeted target image, the targeted target image is cropped to obtain a left ventricle image; each pixel point in the left ventricle image is classified to obtain a position type of each pixel point, and the position type includes belonging to the mitral valve and not belonging to the mitral valve; according to the pixel point whose position type is belonging to the mitral valve, the left ventricle image is segmented to obtain a mitral valve image, and the mitral valve image represents the mitral valve area of ​​the heart;

[0125] Step 406, determining the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image;

[0126] Step 408, convert the area of ​​the mitral valve orifice in each frame of the mitral valve image into a coordinate position in a preset coordinate system; generate an initial time domain curve according to the coordinate position of each frame of the mitral valve image in the preset coordinate system and the timestamp of each frame of the mitral valve image; convert the initial time domain curve from a time domain form to a frequency domain form to obtain an initial frequency domain curve; perform low-frequency filtering on the initial frequency domain curve through a low-pass filter to obtain a filtered frequency domain curve; convert the filtered frequency domain curve from a frequency domain form to a time domain form to obtain a mitral valve orifice area change curve, and the mitral valve orifice area The change curve represents in real time how the area of ​​the mitral valve orifice changes with time; based on the mitral valve orifice area change curve, the maximum area of ​​the mitral valve orifice is determined; the maximum area of ​​the mitral valve orifice is compared with the mitral valve stenosis threshold, and based on the comparison result, the mitral valve stenosis detection result of the heart is determined; based on the mitral valve orifice area change curve, a mitral valve orifice area change rate curve is generated, and the mitral valve orifice area change rate curve represents in real time the changing trend of the area of ​​the mitral valve orifice with time; based on the mitral valve orifice area change rate curve, the recovery detection result of the mitral valve of the heart is determined.

[0127] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0128] Based on the same inventive concept, the embodiment of the present application also provides an image detection device for the mitral valve for implementing the above-mentioned image detection method for the mitral valve. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the image detection device for the mitral valve provided below can refer to the limitations of the image detection method for the mitral valve above, and will not be repeated here.

[0129] In an exemplary embodiment, Figure 5 As shown, an image detection device 500 for the mitral valve is provided, comprising: an extraction module 502, a first determination module 504, a second determination module 506 and a generation module 508, wherein:

[0130] An extraction module 502 is used to obtain multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image;

[0131] A first determination module 504 is used to determine, for each frame of image, a mitral valve region of the heart in each frame of image according to multi-scale image features of the image;

[0132] A second determination module 506 is used to determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image;

[0133] The generating module 508 is used to generate the detection result of the mitral valve of the heart according to the area of ​​the mitral valve orifice in each frame of the image.

[0134] In one embodiment, the first determination module 504 is used to generate a detection frame in the targeted image based on multi-scale image features of the targeted image, and the detection frame is used to characterize the positions of different tissue structures in the heart; determine the image quality of the targeted image according to image quality evaluation rules and the detection frame generated in the targeted image; and determine the mitral valve area of ​​the heart in each frame of the image according to the image quality of each frame of the image.

[0135] In one embodiment, the first determination module 504 is used to screen out multiple frames of target images from multiple frames of images based on the image quality of each frame of image, and the multiple frames of target images are images of multiple consecutive frames; for each frame of target image, the target image is cropped according to the left ventricle detection frame in the target image to obtain a left ventricle image; each pixel in the left ventricle image is classified to obtain a position type of each pixel, and the position types include belonging to the mitral valve and not belonging to the mitral valve; according to the pixel points whose position type is belonging to the mitral valve, the left ventricle image is segmented to obtain a mitral valve image, and the mitral valve image represents the mitral valve area of ​​the heart.

[0136] In one embodiment, the first determination module 508 is used to convert the area of ​​the mitral valve orifice in each frame of the mitral valve image into a coordinate position in a preset coordinate system; generate a mitral valve orifice area change curve according to the coordinate position of each frame of the mitral valve image in the preset coordinate system and the timestamp of each frame of the mitral valve image, the mitral valve orifice area change curve representing in real time the change of the area of ​​the mitral valve orifice over time; determine the detection result of the mitral valve of the heart according to the mitral valve orifice area change curve.

[0137] In one embodiment, the first determination module 508 is used to generate an initial time domain curve based on the coordinate position of each frame of the mitral valve image in a preset coordinate system and the timestamp of each frame of the mitral valve image; convert the initial time domain curve from a time domain form to a frequency domain form to obtain an initial frequency domain curve; perform low-frequency filtering on the initial frequency domain curve through a low-pass filter to obtain a filtered frequency domain curve; convert the filtered frequency domain curve from a frequency domain form to a time domain form to obtain a mitral valve area change curve.

[0138] In one embodiment, the first determination module 508 is used to determine the maximum area of ​​the mitral valve orifice based on the mitral valve orifice area change curve; compare the maximum area of ​​the mitral valve orifice with the mitral valve stenosis threshold, and determine the mitral valve stenosis detection result of the heart based on the comparison result; generate a mitral valve orifice area change rate curve based on the mitral valve orifice area change curve, the mitral valve orifice area change rate curve represents the change trend of the area of ​​the mitral valve orifice over time in real time; determine the recovery detection result of the mitral valve of the heart based on the mitral valve orifice area change rate curve.

[0139] Each module in the above-mentioned image detection device for the mitral valve can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0140] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to image detection of the mitral valve. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for image detection of the mitral valve is implemented.

[0141] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0143] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0144] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0145] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0147] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0148] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for image detection of mitral valve, characterized in that: The method comprises: Acquire multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image; For each frame of image, determining the mitral valve region of the heart in each frame of image according to multi-scale image features of the image; Determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image; The detection result of the mitral valve of the heart is generated according to the area of ​​the mitral valve orifice in each frame of the image.

2. The method according to claim 1, characterized in that The step of determining the mitral valve region of the heart in each frame of image according to the multi-scale image features of the image includes: Based on multi-scale image features of the targeted image, a detection frame is generated in the targeted image, wherein the detection frame is used to characterize the positions of different tissue structures in the heart; Determine the image quality of the targeted image according to an image quality evaluation rule and a detection frame generated in the targeted image; According to the image quality of each frame of image, the mitral valve region of the heart in each frame of image is determined.

3. The method according to claim 2, characterized in that The detection frame at least includes a left ventricle detection frame; Determining the mitral valve region of the heart in each frame of image according to the image quality of each frame of image includes: According to the image quality of each frame of image, a plurality of frames of target images are screened out from the plurality of frames of image, wherein the plurality of frames of target images are images of a plurality of consecutive frames; For each frame of the target image, the target image is cropped according to the left ventricle detection frame in the target image to obtain a left ventricle image; Classifying each pixel point in the left ventricle image to obtain a position type of each pixel point, wherein the position type includes belonging to the mitral valve and not belonging to the mitral valve; According to the pixel points whose position type is that they belong to the mitral valve, the left ventricle image is segmented to obtain a mitral valve image, and the mitral valve image represents the mitral valve region of the heart.

4. The method according to claim 3, characterized in that Each frame of image is a frame of mitral valve image; Generating the detection result of the mitral valve of the heart according to the area of ​​the mitral valve orifice in each frame of the image includes: Converting the area of ​​the mitral valve orifice in each frame of the mitral valve image into a coordinate position in a preset coordinate system; Generate a mitral valve orifice area change curve according to the coordinate position of each frame of the mitral valve image in a preset coordinate system and the timestamp of each frame of the mitral valve image, wherein the mitral valve orifice area change curve represents the change of the area of ​​the mitral valve orifice over time in real time; The detection result of the mitral valve of the heart is determined according to the mitral valve orifice area change curve.

5. The method according to claim 4, characterized in that The step of generating a mitral valve area change curve according to the coordinate position of each frame of the mitral valve image in a preset coordinate system and the timestamp of each frame of the mitral valve image comprises: generating an initial time domain curve according to the coordinate position of each frame of the mitral valve image in a preset coordinate system and the time stamp of each frame of the mitral valve image; Converting the initial time domain curve from a time domain form to a frequency domain form to obtain an initial frequency domain curve; Performing low-frequency filtering on the initial frequency domain curve by using a low-pass filter to obtain a filtered frequency domain curve; The filtered frequency domain curve is converted from the frequency domain form to the time domain form to obtain the mitral valve area change curve.

6. The method according to claim 4, characterized in that Determining the detection result of the mitral valve of the heart according to the mitral valve area change curve includes: determining the maximum area of ​​the mitral valve orifice according to the mitral valve orifice area change curve; Comparing the maximum area of ​​the mitral valve orifice with the mitral valve stenosis threshold, and determining the stenosis detection result of the mitral valve of the heart according to the comparison result; Generating the mitral valve area change rate curve according to the mitral valve area change curve, wherein the mitral valve area change rate curve represents the change trend of the area of ​​the mitral valve over time in real time; The recovery detection result of the mitral valve of the heart is determined according to the mitral valve area change rate curve.

7. An image detection device for mitral valve, characterized in that: The device comprises: An extraction module, used to acquire multiple frames of images including the heart, perform multi-scale feature extraction on the multiple frames of images, and obtain multi-scale image features of each frame of image; A first determination module is used to determine, for each frame of image, a mitral valve region of the heart in each frame of image according to multi-scale image features of the image; A second determination module, configured to determine the area of ​​the mitral valve orifice in each frame of image based on the mitral valve region of the heart in each frame of image; A generating module is used to generate the detection result of the mitral valve of the heart according to the area of ​​the mitral valve orifice in each frame of the image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images