Method and device for automatically detecting myocardial cell sarcoglyph area and storage medium

Abstract

The invention relates to a method and device for automatically detecting a myocardial cell sarcoglyph area and a storage medium, and is applied to the technical field of myocardial cell detection. The method specifically comprises the following steps: fusing original video data into an image, and expressing regions of cells during rhythmic contraction and relaxation; the structural strength of the image is calculated based on the fused and sharpened image, and according to the structural strength, a high structural strength region mask is generated and represents a region with a muscle segment; and finally, carrying out iterative optimization on the high-structural-strength region mask graph through a centroid-driven polar ray method to obtain a myocardial cell internal sarcoglyph region graph. According to the method, structural feature calculation is carried out on the image obtained after fusion of the multiple frames of images to obtain the pan-sarcomedo region, and the smooth inscribed contour of the sarcomedo region is obtained through the centroid driven polar ray method, so that compared with the prior art, myocardial cells do not need to be positioned, the sarcomedo is directly positioned through structural strength, the obtained sarcomedo ROI is more adaptive to subsequent sarcomedo motion parameter calculation, and the accuracy of the obtained sarcomedo motion parameters is improved. And the influence of human subjective factors is avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of myocardial cell detection, and in particular relates to a method, a device and a storage medium for automatically detecting the sarcomere region of myocardial cells. Background Art

[0002] Cardiomyocytes are the basic functional units of the heart. Their rhythmic contraction and relaxation characteristics are closely related to heart diseases. One of the main methods to study cardiomyocyte activity is to analyze the movement patterns of sarcomeres in cardiomyocytes. Sarcomeres are the basic contractile units of cardiomyocytes. Their movement patterns can be used to evaluate the contractile function of cardiomyocytes, and then used in the study of cardiovascular diseases and drug screening. In actual research, accurate selection of the region of interest (ROI) where the sarcomere is located is a prerequisite for data analysis. Its accuracy directly affects the subsequent calculation results, thereby determining the quality of experimental data and the reliability of research results.

[0003] Currently, the contractile characteristics of cardiomyocytes are mainly evaluated using microscopy video data analysis technology. Its standard process usually includes the following steps: (1) primary cardiomyocytes are isolated from rat or mouse heart tissue; (2) the cardiomyocytes are observed through an optical microscope pixel system and the microscopy video data of the rhythmic contraction of cardiomyocytes is continuously captured; (3) the researchers need to select the target cardiomyocytes from the video and manually define a static ROI in the sarcomere region (usually limited to a single frame image); (4) the sarcomere motion parameters such as length, motion trajectory, and power spectrum are calculated based on the frequency domain characteristics of the sarcomere ROI region. The existing technology mainly relies on manual annotation of sarcomere regions, which has the following problems: (1) Lack of dynamic feature capture: The sarcomere region presents temporal dynamic changes with the rhythmic contraction and relaxation of myocardial cells, while the traditional manual annotation method only considers a single-frame static image and cannot find the corresponding area of ​​the most relaxed sarcomere during the continuous change of the sarcomere, resulting in inaccurate sarcomere region selection; (2) Inefficiency and non-scalability: Sample processing is time-consuming and cannot form high-throughput and automated analysis, making it difficult to meet the sarcomere region detection needs of large-scale myocardial cell data; (3) Subjective bias: Manual annotation relies on manual operation and is affected by human subjective factors. There are annotation deviations between and within individuals, poor consistency, and low repeatability. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device and storage medium for automatically detecting the sarcomere area of ​​cardiomyocytes, so as to solve the problems in the prior art that only a single-frame static image is considered, and the corresponding area of ​​the most relaxed sarcomere cannot be found during the continuous change of the sarcomere, resulting in inaccurate sarcomere area selection, time-consuming sample processing, inability to form high-throughput and automated analysis, and difficulty in meeting the sarcomere area detection needs of large-scale myocardial cell data, as well as manual labeling that relies on manual operation and is affected by human subjective factors, and has labeling deviations between and within individuals, poor consistency, and low repeatability.

[0005] According to a first aspect of an embodiment of the present invention, a method for automatically detecting a myocardial cell sarcomere region is provided, the method comprising: Acquire microscope video data of rhythmic contraction of myocardial cells, fuse and sharpen multiple frames of images in the microscope video data to obtain a sharpening enhancement image; The gradients of the sharpening enhancement image in the X and Y directions are calculated by the Sobel operator to obtain an X-direction gradient image and a Y-direction gradient image; an X-direction gradient intensity image, a Y-direction gradient intensity image and an XY-direction correlation image are obtained by the X-direction gradient image and the Y-direction gradient image. The X-direction gradient intensity map, the Y-direction gradient intensity map, and the XY-direction correlation map are filtered by a Gaussian filter and the structural strength is extracted to obtain a structural strength map; Acquire a high structural strength region mask map based on the structural strength map; The high structure intensity region mask map is iteratively optimized by the centroid driven polar ray method to obtain the sarcomere region map inside the cardiomyocyte.

[0006] Preferably, The fusing and sharpening of multiple frames of images in the microscope video data to obtain a sharpening enhancement image comprises: Obtaining an average image of multiple frames of images in the microscope video data; Normalizing the average image, and convolving the normalized average image with a Laplace sharpening filter to obtain an enhanced edge information image; The enhanced edge information image is normalized to obtain the sharpening enhancement image.

[0007] Preferably, The step of acquiring a high structural strength region mask map based on the structural strength map comprises: Normalizing the structure intensity map, extracting a binary mask map of a high structural feature region in the normalized structure intensity map by Gaussian adaptive threshold segmentation, and reversing pixel values ​​of the binary mask map of the high structural feature region to obtain an inverted binary mask map; The inverted binary mask image is expanded and eroded, the largest area is retained, and other small areas are eliminated, so as to obtain the high structural strength area mask image.

[0008] Preferably, The iterative optimization of the high structure intensity region mask map by the centroid driven polar ray method to obtain the myocardial cell internal sarcomere region map includes: Extracting the centroid from the high structural strength region mask map by a spatial moment analysis method; Based on the centroid, the optimized myocardial ROI map is obtained by using the centroid-driven polar ray method; the centroid of the optimized myocardial ROI map is obtained, and based on the new centroid, the optimized myocardial ROI map is obtained by using the centroid-driven polar ray method again; it is repeated, the centroid is continuously moved and the boundary is optimized until a preset target number of iterations is completed or the intersection-and-union ratio of the optimized myocardial ROI map for three consecutive times to the previous optimized myocardial ROI map is greater than a preset target percentage, and then the iteration is exited to obtain the final myocardial ROI map; The final myocardial ROI image is subjected to centroid regression to obtain the sarcomere region map inside the myocardial cells.

[0009] Preferably, The step of obtaining the centroid of the optimized myocardial ROI image comprises: The distances between all boundary points and the centroid in the optimized myocardial ROI image are obtained, and the point with the largest distance is selected as the new centroid.

[0010] Preferably, The optimized myocardial ROI image obtained based on the centroid by using the centroid-driven polar ray method comprises: With the centroid as the center and the image coordinate system as the reference, a ray is emitted clockwise at an interval of 1°, for a total of 360 rays. Each ray starts from the centroid and extends radially pixel by pixel within the mask until it encounters a mask boundary point, which is recorded as the farthest valid boundary point in that direction. Then, the optimized myocardial ROI map is generated based on the 360 ​​farthest valid boundary points obtained from the current centroid.

[0011] Preferably, The performing centroid regression on the final myocardial ROI map to obtain the myocardial cell internal sarcomere region map comprises: The centroid of the final myocardial ROI image is calculated by spatial moment, and the centroid-driven polar ray method is used based on the centroid of the final myocardial ROI image to obtain the myocardial cell internal sarcomere region map.

[0012] According to a second aspect of an embodiment of the present invention, there is provided a device for automatically detecting the sarcomere region of a cardiomyocyte, the device comprising: Image fusion module: used to obtain microscope video data of rhythmic contraction of myocardial cells, fuse and sharpen multiple frames of images in the microscope video data to obtain a sharpening enhancement image; Structural tensor acquisition module: used to calculate the gradients of the sharpening enhancement image in the X and Y directions respectively through the Sobel operator to obtain the X-direction gradient image and the Y-direction gradient image; obtain the X-direction gradient intensity image, the Y-direction gradient intensity image and the XY-direction correlation image respectively through the X-direction gradient image and the Y-direction gradient image; Structural strength acquisition module: used to filter the X-direction gradient intensity map, the Y-direction gradient intensity map and the XY-direction correlation map through a Gaussian filter and extract the structural strength to obtain a structural strength map; A mask map acquisition module: used for acquiring a mask map of a high structural strength area based on the structural strength map; Sarcomere region map acquisition module: used for iteratively optimizing the high structure intensity region mask map by centroid driven polar ray method to obtain the sarcomere region map inside the myocardial cell.

[0013] According to a third aspect of an embodiment of the present invention, there is provided a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a main controller, each step in the above method is implemented.

[0014] The technical solution provided by the embodiments of the present invention may have the following beneficial effects: The present application obtains microscope video data of rhythmic contraction of myocardial cells, fuses and sharpens multiple frames of images in the microscope video data, and obtains a sharpening enhancement map; calculates the gradients of the sharpening enhancement map in the X and Y directions respectively by the Sobel operator to obtain an X-direction gradient map and a Y-direction gradient map; obtains an X-direction gradient intensity map, a Y-direction gradient intensity map, and an XY-direction correlation map respectively by the X-direction gradient map and the Y-direction gradient map; and filters the X-direction gradient intensity map, the Y-direction gradient intensity map, and the XY-direction correlation map by a Gaussian filter to extract structural strong degree to obtain a structural strength map; based on the structural strength map, a mask map of high structural strength areas is obtained; the mask map of high structural strength areas is iteratively optimized by the centroid-driven polar ray method to obtain a sarcomere area map inside the cardiomyocyte; the present application obtains a pan-sarcomere area by calculating the structural features of the image after fusion of multiple frames of images, and obtains a smooth inscribed contour of the sarcomere area by the centroid-driven polar ray method. Compared with the prior art, there is no need to locate myocardial cells, and the sarcomere is directly located by structural strength. The obtained sarcomere ROI is more suitable for subsequent sarcomere motion parameter calculations, and the calculation process is efficient and fully automatic, and is not affected by human subjective factors.

[0015] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0017] Figure 1 is a flow chart of a method for automatically detecting the sarcomere region of a cardiomyocyte according to an exemplary embodiment; Figure 2 is a schematic diagram of obtaining a sharpening enhancement image according to another exemplary embodiment; Figure 3 is a schematic diagram of obtaining a structural tensor according to another exemplary embodiment; Figure 4 is a schematic diagram of obtaining a mask of a high structural strength region according to another exemplary embodiment; Figure 5 is a schematic diagram of iterative optimization according to another exemplary embodiment; Figure 6 is a schematic diagram of obtaining a myomere region according to another exemplary embodiment; Figure 7 is a system schematic diagram of a device for automatically detecting the sarcomere region of a cardiomyocyte according to another exemplary embodiment; In the attached figure: 1-image fusion module, 2-structure tensor acquisition module, 3-structure strength acquisition module, 4-mask map acquisition module, 5-sarcomere area map acquisition module. DETAILED DESCRIPTION

[0018] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0019] Embodiment 1 Figure 1 FIG. 1 is a flow chart of a method for automatically detecting the sarcomere region of a cardiomyocyte according to an exemplary embodiment. Figure 1 As shown, the method includes: S1, obtaining microscope video data of rhythmic contraction of myocardial cells, fusing and sharpening multiple frames of images in the microscope video data to obtain a sharpening enhancement image; S2, respectively calculating the gradients of the sharpening enhancement image in the X and Y directions by using the Sobel operator to obtain an X-direction gradient image and a Y-direction gradient image; respectively obtaining an X-direction gradient intensity image, a Y-direction gradient intensity image and an XY-direction correlation image by using the X-direction gradient image and the Y-direction gradient image; S3, filtering the X-direction gradient intensity map, the Y-direction gradient intensity map, and the XY-direction correlation map through a Gaussian filter and extracting the structural strength to obtain a structural strength map; S4, obtaining a high structural strength region mask map based on the structural strength map; S5, iteratively optimizing the high structure intensity region mask map by a centroid driven polar ray method to obtain a sarcomere region map inside the cardiomyocyte; It is understandable that if Figure 2 As shown, the present application observes and continuously captures microscope video data of rhythmic contraction of myocardial cells through an optical microscope pixel system, calculates an average image of multiple frames of images in the microscope video data; normalizes the average image so that its pixel range is changed from (0-255) to (0-1), and uses a Laplace sharpening filter to perform convolution processing on the normalized average image to obtain an enhanced edge information image. This operation can highlight the details in the image and improve the resolution of tiny structures such as the sarcomere area; the enhanced image is normalized again, and the pixel range is adjusted back to (0-255) to obtain a sharpened enhanced image; As attached Figure 3As shown, based on the above-mentioned sharpening enhancement map, the Sobel operator is used to calculate the gradients in the X and Y directions, and the X-direction gradient map and the Y-direction gradient map are obtained. The structure tensor is calculated, including the X-direction gradient intensity J11, the Y-direction gradient intensity J22 and the XY direction correlation J12. The specific calculation method is: J11 = sobel_x* sobel_x J22 = sobel_y* sobel_y J12 = sobel_x* sobel_y As attached Figure 4 As shown, use Gaussian filter to filter J11, J22, and J12 respectively to make them smoother, and calculate the structural strength structure_strength. The specific calculation method is as follows: Lambda1 = (J11 + J22) / 2 + sqrt((J11 - J22)*(J11 - J22) / 4 + J12 *J12); Lambda2 = (J11 + J22) / 2 - sqrt((J11 - J22)*(J11 - J22) / 4 + J12 *J12); structure_strength = Lambda1 - Lambda2; Normalize structure_strength to (0-255), extract the binary mask of the area with high structural features through Gaussian adaptive threshold segmentation, and invert the pixel values ​​to obtain the inverted binary mask map. Dilate and erode the high structural feature area in the inverted binary mask map, retain the largest area, eliminate other small areas, and obtain the mask map of the high structural strength area; As attached Figure 5As shown in the figure, the initial centroid of the mask map of the high structural intensity area is extracted by the spatial moment analysis method, and the centroid-driven polar ray method is used to iteratively optimize the myocardial ROI (ROI represents the region of interest) to eliminate the influence of the edge structure; the centroid-driven polar ray method is specifically as follows: with the centroid as the center and the direction of the image coordinate system as the reference, one ray is emitted clockwise at an interval of 1°, and a total of 360 rays are emitted. Each ray starts from the centroid and radiates pixel by pixel in the mask until it encounters a mask boundary point, which is recorded as the farthest valid boundary point in this direction. Then, a new myocardial ROI is generated based on the 360 ​​farthest valid boundary points obtained from the current centroid. The first generated myocardial ROI is called the initial myocardial ROI; based on the initial myocardial ROI, the homogeneous centroids of all boundary points are calculated The point with the largest distance is selected as the new centroid, and the centroid-driven polar ray method is used again to shift the centroid toward the external structure of ROI, thereby optimizing the boundary position and generating a new myocardial ROI; based on the new myocardial ROI, the distance between all boundary points and the centroid is calculated, and the point with the largest distance is selected as the new centroid. The centroid-driven polar ray method is used to repeat this iterative process, constantly moving the centroid and optimizing the boundary. The shape of the myocardial ROI after each optimization gradually becomes smoother, and it gradually fits the actual sarcomere area until the target number of iterations is completed, or the intersection-over-union ratio of the myocardial ROI with the previous myocardial ROI for three consecutive times is greater than the target percentage, and the iteration is exited, and the myocardial ROI obtained in the last iteration is used as the final myocardial ROI map; As attached Figure 6 As shown in the figure, the centroid of the final myocardial ROI image is calculated by spatial moment to return it to a more balanced position. The final mask is generated based on the centroid of the final myocardial ROI image using the centroid-driven polar ray method to accurately extract the sarcomere area inside the myocardial cells.

[0020] Embodiment 2: Figure 7 is a system schematic diagram of a device for automatically detecting the sarcomere region of a cardiomyocyte according to another exemplary embodiment, the device comprising: Image fusion module 1: used to obtain microscope video data of rhythmic contraction of myocardial cells, fuse and sharpen multiple frames of images in the microscope video data to obtain a sharpening enhancement image; Structural tensor acquisition module 2: used to calculate the gradients of the sharpening enhancement image in the X and Y directions respectively through the Sobel operator to obtain the X-direction gradient image and the Y-direction gradient image; obtain the X-direction gradient intensity image, the Y-direction gradient intensity image and the XY-direction correlation image respectively through the X-direction gradient image and the Y-direction gradient image; Structural strength acquisition module 3: used to filter the X-direction gradient intensity map, the Y-direction gradient intensity map and the XY-direction correlation map through a Gaussian filter and extract the structural strength to obtain a structural strength map; Mask map acquisition module 4: used to acquire a high structural strength area mask map based on the structural strength map; Sarcomere region map acquisition module 5: used to iteratively optimize the high structure intensity region mask map by centroid driven polar ray method to obtain the sarcomere region map inside the myocardial cell.

[0021] Embodiment three: This embodiment provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a main controller, each step in the above method is implemented; It is understandable that the storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0022] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0023] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "a small number of sparsely distributed" refers to at least two.

[0024] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code that includes one or less sparsely distributed executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0025] It should be understood that the various parts of the present invention can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, a small number of sparsely distributed steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0026] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0027] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0028] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0029] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or a small number of sparsely distributed embodiments or examples in a suitable manner.

[0030] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for automatically detecting the sarcomere region of a cardiomyocyte, characterized in that: The method comprises: Acquire microscope video data of rhythmic contraction of myocardial cells, fuse and sharpen multiple frames of images in the microscope video data to obtain a sharpening enhancement image; The gradients of the sharpening enhancement image in the X and Y directions are calculated by the Sobel operator to obtain an X-direction gradient image and a Y-direction gradient image; an X-direction gradient intensity image, a Y-direction gradient intensity image and an XY-direction correlation image are obtained by the X-direction gradient image and the Y-direction gradient image. The X-direction gradient intensity map, the Y-direction gradient intensity map, and the XY-direction correlation map are filtered by a Gaussian filter and the structural strength is extracted to obtain a structural strength map; Acquire a high structural strength region mask map based on the structural strength map; The high structure intensity region mask map is iteratively optimized by the centroid driven polar ray method to obtain the sarcomere region map inside the cardiomyocyte.

2. The method according to claim 1, characterized in that The fusing and sharpening of multiple frames of images in the microscope video data to obtain a sharpening enhancement image comprises: Obtaining an average image of multiple frames of images in the microscope video data; Normalizing the average image, and convolving the normalized average image with a Laplace sharpening filter to obtain an enhanced edge information image; The enhanced edge information image is normalized to obtain the sharpening enhancement image.

3. The method according to claim 2, characterized in that The step of acquiring a high structural strength region mask map based on the structural strength map comprises: Normalizing the structure intensity map, extracting a binary mask map of a high structural feature region in the normalized structure intensity map by Gaussian adaptive threshold segmentation, and reversing pixel values ​​of the binary mask map of the high structural feature region to obtain an inverted binary mask map; The inverted binary mask image is expanded and eroded, the largest area is retained, and other small areas are eliminated, so as to obtain the high structural strength area mask image.

4. The method according to claim 3, characterized in that The iterative optimization of the high structure intensity region mask map by the centroid driven polar ray method to obtain the myocardial cell internal sarcomere region map includes: Extracting the centroid from the high structural strength region mask map by a spatial moment analysis method; Based on the centroid, the optimized myocardial ROI map is obtained by using the centroid-driven polar ray method; the centroid of the optimized myocardial ROI map is obtained, and based on the new centroid, the optimized myocardial ROI map is obtained by using the centroid-driven polar ray method again; it is repeated, the centroid is continuously moved and the boundary is optimized until a preset target number of iterations is completed or the intersection-and-union ratio of the optimized myocardial ROI map for three consecutive times to the previous optimized myocardial ROI map is greater than a preset target percentage, and then the iteration is exited to obtain the final myocardial ROI map; The final myocardial ROI image is subjected to centroid regression to obtain the sarcomere region map inside the myocardial cells.

5. The method according to claim 4, characterized in that The step of obtaining the centroid of the optimized myocardial ROI image comprises: The distances between all boundary points and the centroid in the optimized myocardial ROI image are obtained, and the point with the largest distance is selected as the new centroid.

6. The method according to claim 5, characterized in that The optimized myocardial ROI image obtained based on the centroid by using the centroid-driven polar ray method comprises: With the centroid as the center and the image coordinate system as the reference, a ray is emitted clockwise at an interval of 1°, for a total of 360 rays. Each ray starts from the centroid and extends radially pixel by pixel within the mask until it encounters a mask boundary point, which is recorded as the farthest valid boundary point in that direction. Then, the optimized myocardial ROI map is generated based on the 360 ​​farthest valid boundary points obtained from the current centroid.

7. The method according to claim 6, characterized in that The performing centroid regression on the final myocardial ROI map to obtain the myocardial cell internal sarcomere region map comprises: The centroid of the final myocardial ROI image is calculated by spatial moment, and the centroid-driven polar ray method is used based on the centroid of the final myocardial ROI image to obtain the myocardial cell internal sarcomere region map.

8. A device for automatically detecting the sarcomere region of a cardiomyocyte, characterized in that: The device comprises: Image fusion module: used to obtain microscope video data of rhythmic contraction of myocardial cells, fuse and sharpen multiple frames of images in the microscope video data to obtain a sharpening enhancement image; Structural tensor acquisition module: used to calculate the gradients of the sharpening enhancement image in the X and Y directions respectively through the Sobel operator to obtain the X-direction gradient image and the Y-direction gradient image; obtain the X-direction gradient intensity image, the Y-direction gradient intensity image and the XY-direction correlation image respectively through the X-direction gradient image and the Y-direction gradient image; Structural strength acquisition module: used to filter the X-direction gradient intensity map, the Y-direction gradient intensity map and the XY-direction correlation map through a Gaussian filter and extract the structural strength to obtain a structural strength map; A mask map acquisition module: used for acquiring a mask map of a high structural strength area based on the structural strength map; Sarcomere region map acquisition module: used for iteratively optimizing the high structure intensity region mask map by centroid driven polar ray method to obtain the sarcomere region map inside the myocardial cell.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the main controller, each step of the method for automatically detecting the myocardial cell sarcomere area as described in any one of claims 1 to 7 is implemented.

Images