A method and system for shoulder cyst localization based on magnetic resonance imaging images

Abstract

The present invention provides a method and system for locating shoulder cysts based on magnetic resonance imaging (MRI) images, which relates to the technical field of medical image processing. The method includes: acquiring multiple MRI images; respectively constructing a target detection model for the humeral head region and a target detection model for cysts based on a deep learning algorithm; inputting the MRI images into the target detection model for the humeral head region for detection and outputting an image of the humeral head region; inputting the image of the humeral head region into the target detection model for cysts for detection and outputting an image of the cyst region; and determining the position of the cyst according to the center point coordinates of the cyst region image through a spatial positioning algorithm. The present invention reduces the influence of MRI images by speckle noise and echo perturbation, as well as the dependence on doctors' cognitive abilities and clinical experience, improves the image quality, makes the difference between cysts and normal tissues more obvious, and avoids confusing cysts with fluid accumulation caused by rotator cuff injuries.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and particularly to a method and system for locating shoulder cysts based on magnetic resonance imaging (MRI) images. Background Art

[0002] With the progress of modern medical imaging technology, the detection and diagnosis of shoulder diseases have been gradually improved. As a clinically common and frequently-occurring shoulder disease, the humeral head cyst in the shoulder is closely related to aging and rotator cuff lesions. According to the statistical data of relevant associations, the incidence of shoulder diseases has increased sharply in the past decade, and the humeral head cyst accounts for 15%-45% of all shoulder diseases, ranking among the top three in all shoulder diseases. The humeral head cyst can cause pain in the shoulder joint area and, in severe cases, lead to limited movement of the shoulder joint, making it difficult for patients to perform normal movements. Therefore, the detection and treatment of the humeral head cyst are particularly important.

[0003] In the current technology, compared with CT (Computed Tomography), magnetic resonance imaging (MRI) has greater advantages. MRI can generate high-quality images in any plane (such as transverse plane, coronal plane, sagittal plane), providing more comprehensive anatomical information. In addition, MRI is more sensitive in the detection of tumors and soft tissues, and the display of shoulder structures is also clearer. In the detection of humeral head cysts, the advantages of MRI are particularly obvious.

[0004] However, the clinical evaluation of shoulder cyst images based on MRI is still challenging. On the one hand, MRI images are affected by speckle noise and echo perturbation, which affects the image quality and makes the difference between cysts and normal tissues less obvious. On the other hand, doctors are prone to confuse humeral head cysts with fluid accumulation caused by rotator cuff injuries during the diagnosis process, which highly depends on the doctor's cognitive ability and clinical experience. Summary of the Invention

[0005] In order to solve the technical problems that traditional MRI images are affected by speckle noise and echo perturbation, which affects the image quality and makes the difference between cysts and normal tissues less obvious, and doctors are prone to confuse humeral head cysts with fluid accumulation caused by rotator cuff injuries during the diagnosis process, which highly depends on the doctor's cognitive ability and clinical experience, the present invention provides a method and system for locating shoulder cysts based on magnetic resonance imaging images.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect:

[0008] A method for locating shoulder cysts based on magnetic resonance imaging images provided by an embodiment of the present invention includes:

[0009] S1: Obtain multiple magnetic resonance imaging (MRI) images;

[0010] S2: Respectively construct a target detection model for the humeral head region and a target detection model for cysts based on deep learning algorithms;

[0011] S3: Input the MRI images into the target detection model for the humeral head region for detection, and output the humeral head region images;

[0012] S4: Input the humeral head region images into the target detection model for cysts for detection, and output the cyst region images;

[0013] S5: Determine the location of the cyst through a spatial positioning algorithm based on the center point coordinates of the cyst region image.

[0014] Second aspect:

[0015] A shoulder cyst localization system based on magnetic resonance imaging images provided by an embodiment of the present invention includes: a memory and one or more processors;

[0016] One or more application programs are stored in the memory, and the one or more application programs are adapted to be executed by the one or more processors to implement the above-mentioned shoulder cyst localization method based on magnetic resonance imaging images.

[0017] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0018] In the present invention, by inputting the MRI images into the target detection model for the humeral head region for detection and outputting the humeral head region images, and then inputting the humeral head region images into the target detection model for cysts for detection and outputting the cyst region images, the influence of speckle noise and echo perturbation on the MRI images is reduced, the image quality is improved, and the difference between the cyst and normal tissues becomes more obvious. According to the center point coordinates of the cyst region image, the location of the cyst is determined through a spatial positioning algorithm, reducing the dependence on the doctor's cognitive ability and clinical experience, realizing automatic positioning, and avoiding confusing the humeral head cyst with the effusion caused by rotator cuff injury. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1Schematic flow chart of a method for locating shoulder cysts based on magnetic resonance imaging (MRI) images provided by an embodiment of the present invention;

[0021] Figure 2 Schematic diagram of the detection of the humeral head region provided by an embodiment of the present invention;

[0022] Figure 3 Schematic structural diagram of a system for locating shoulder cysts based on magnetic resonance imaging (MRI) images provided by an embodiment of the present invention. Detailed implementation manners

[0023] The technical solutions in the present invention will be described below with reference to the accompanying drawings.

[0024] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0025] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] Refer to the attached drawings of the specification Figure 1 , which shows a schematic flow chart of a method for locating shoulder cysts based on magnetic resonance imaging (MRI) images provided by an embodiment of the present invention.

[0027] The embodiments of the present invention provide a method for locating shoulder cysts based on magnetic resonance imaging (MRI) images. This method can be implemented by a device for locating shoulder cysts based on magnetic resonance imaging (MRI) images, and the device for locating shoulder cysts based on magnetic resonance imaging (MRI) images can be a terminal or a server. The processing flow of the method for locating shoulder cysts based on magnetic resonance imaging (MRI) images can include the following steps:

[0028] S1: Obtain multiple magnetic resonance imaging (MRI) images.

[0029] For example, obtain 15 magnetic resonance imaging (MRI) images of each patient.

[0030] Among them, Magnetic Resonance Imaging (MRI) is a medical imaging technique that generates detailed images of internal structures through a strong magnetic field and radio waves. It does not use ionizing radiation but utilizes the arrangement and energy release of hydrogen atoms to obtain high-resolution soft tissue images. MRI can clearly display the details of the brain, spinal cord, joints, and other soft tissues and is widely used in the diagnosis of the nervous system, musculoskeletal system, abdomen, and cardiovascular system. Due to its superior image contrast and radiation-free characteristics, this technique has important diagnostic value in the medical field.

[0031] S2: Construct a humeral head region target detection model and a cyst target detection model based on deep learning algorithms respectively.

[0032] Optionally, the deep learning algorithm includes a long short-term memory neural network and a recurrent neural network.

[0033] In the present invention, the deep learning model can automatically extract useful features from the image without manual feature definition, so it can learn more complex and subtle features, thereby improving the accuracy of target detection. Magnetic Resonance Imaging (MRI) images usually have high dimensions and complex structures, and deep learning algorithms are particularly suitable for processing these high-dimensional data because they can learn high-level representations and patterns in the images. In addition, the long short-term memory network (LSTM) or the recurrent neural network (RNN) can handle the temporal dependencies in the image sequence. If the image sequence has temporal or spatial correlations, these algorithms can capture these correlations, thereby further improving the accuracy and stability of detection.

[0034] Refer to the attached Figure 2 illustrates a schematic diagram of humeral head region detection provided by an embodiment of the present invention.

[0035] S3: Input the magnetic resonance imaging image into the humeral head region target detection model for detection, and output the humeral head region image.

[0036] In a possible implementation manner, S3 specifically includes sub-steps S301 to S304:

[0037] S301: Input the magnetic resonance imaging image into the humeral head region target detection model for detection, and output the humeral head position information.

[0038] Among them, the humeral head position information is specifically:

[0039] R1 = {cx1, cy1, w1, h1}

[0040] Among them, R1 represents the position information of the humeral head, cx1 and cy1 respectively represent the ratios of the abscissa and ordinate of the center point of the humeral head region image in the magnetic resonance imaging (MRI) image to the height and width of the MRI image, and w1 and h1 respectively represent the ratios of the width and height of the humeral head detection box to the width and height of the MRI image.

[0041] S302: Calculate the center point coordinates of the humeral head region image in the magnetic resonance imaging image and the width and height of the humeral head detection box according to the magnetic resonance imaging image and the position information of the humeral head.

[0042] In a possible implementation manner, S302 is specifically:

[0043] Calculate the center point coordinates of the humeral head region image in the magnetic resonance imaging image and the width and height of the humeral head detection box according to the following formulas:

[0044] X A = cx1 × W

[0045] Y A = cy1 × H

[0046] W A = w1 × W

[0047] H A = h1 × H

[0048] Among them, X A and Y A respectively represent the abscissa and ordinate of the center point of the humeral head region image in the magnetic resonance imaging image, W and H respectively represent the width and height of the magnetic resonance imaging image, and W A and H A respectively represent the width and height of the humeral head detection box.

[0049] S303: Calculate the vertex coordinates of the humeral head detection box according to the center point coordinates of the humeral head region image in the magnetic resonance imaging image and the width and height of the humeral head detection box.

[0050] In a possible implementation manner, S303 is specifically:

[0051] Calculate the vertex coordinates of the humeral head detection box according to the following formulas:

[0052]

[0053] Among them, X1 and Y1 respectively represent the abscissa and ordinate of vertex A of the humeral head detection frame, X2 and Y2 respectively represent the abscissa and ordinate of vertex B of the humeral head detection frame, X3 and Y3 respectively represent the abscissa and ordinate of vertex C of the humeral head detection frame, and X4 and Y4 respectively represent the abscissa and ordinate of vertex D of the humeral head detection frame.

[0054] S304: Output the humeral head region image according to the vertex coordinates of the humeral head detection frame.

[0055] It should be noted that the width of the output humeral head region image is W A , and the height is H A .

[0056] In the present invention, through the deep learning model, the humeral head region can be automatically recognized and located from the MRI image, reducing the subjectivity and error of manual annotation, thereby improving the accuracy of positioning. When detecting the humeral head region, the vertex coordinates of the detection frame can be accurately calculated, so as to extract a more accurate humeral head region. This is very important for subsequent cyst detection and positioning, ensuring that the subsequent steps can be carried out in the correct region. During the training and use process, the standardized humeral head region image can improve the robustness and stability of the model, so that the model can still maintain a high detection performance when facing the MRI images of different patients.

[0057] S4: Input the humeral head region image into the cyst target detection model for detection, and output the cyst region image.

[0058] It should be noted that the width of the output cyst region image is W A , and the height is H A .

[0059] In a possible implementation manner, S4 specifically includes sub-steps S401 to S402:

[0060] S401: Input the humeral head region image into the cyst target detection model for detection, and output the cyst position information.

[0061] Among them, the cyst position information is specifically:

[0062] R2 = {cx2, cy2, w2, h2}

[0063] Among them, R2 represents the cyst position information, cx2 and cy2 respectively represent the ratio of the abscissa of the center point and the ordinate of the center point of the cyst region image in the humeral head region image to the height and width of the humeral head region image, and w2 and h2 respectively represent the ratio of the width and height of the cyst detection frame to the width and height of the humeral head region image.

[0064] S402: Output the coordinates of the center point of the cyst area image in the humeral head area image based on the humeral head area image and the cyst position information.

[0065] In a possible implementation, S402 is specifically:

[0066] Output the coordinates of the center point of the cyst area image in the humeral head area image according to the following formula:

[0067] X C = cx2 × W A

[0068] Y C = cy2 × H A

[0069] Wherein, X C and Y C respectively represent the abscissa and ordinate of the center point of the cyst area image in the humeral head area image.

[0070] In the present invention, by specifically detecting cysts in the humeral head area image, the influence of background interference is reduced. The cyst detection model only focuses on specific areas within the humeral head area, thereby being able to detect and locate cysts more precisely, and reducing the interference of noise and irrelevant parts in the image on the detection result. Using the cyst position information (such as the coordinates of the center point, the ratio of the detection box) to calculate the coordinates of the center point of the cyst area image can more accurately locate the cyst. This method enables the model to focus on the detected cyst area, improving the detection accuracy. By outputting the coordinates of the center point of the cyst area image, the precise positioning of the cyst area is ensured. This provides consistent and reliable data support for subsequent analysis, evaluation, and possible formulation of treatment plans.

[0071] S5: Determine the position of the cyst through a spatial positioning algorithm according to the coordinates of the center point of the cyst area image.

[0072] In a possible implementation, S5 specifically includes sub-steps S501 to S507:

[0073] S501: Establish a rectangular coordinate system with the center point of the humeral head area image as the coordinate origin:

[0074]

[0075] Wherein, X B and Y B respectively represent the abscissa and ordinate of the center point of the humeral head area image.

[0076] Specifically, in each magnetic resonance imaging image, establish a rectangular coordinate system with the center point of the humeral head area image as the coordinate origin.

[0077] In the present invention, by establishing a rectangular coordinate system with the center point of the humeral head region image as the coordinate origin, the position of the cyst can be accurately located in each magnetic resonance imaging (MRI) image. Such a coordinate system helps to uniformly transform the position data of the cyst from different images into the same coordinate system, improving the accuracy of positioning.

[0078] S502: Save the cyst detection result of each magnetic resonance imaging image as a sequence vector:

[0079] L i =(l x ,l y ,l z )

[0080]

[0081] where L i represents the sequence vector of the cyst detection result of the i-th magnetic resonance imaging image, l x and l y respectively represent the relative positions of the cyst region image on the X-axis and Y-axis in the rectangular coordinate system, l z represents the serial number of the magnetic resonance imaging image, x i B and y i B respectively represent the abscissa and ordinate of the center point of the i-th humeral head region image, x i C and y i C respectively represent the abscissa and ordinate of the center point of the cyst region image in the i-th humeral head region image.

[0082] In the present invention, saving the cyst detection result of each magnetic resonance imaging image as a sequence vector and considering the correlation in the image sequence helps to capture the changes of the cyst in different images. This method can process and analyze the temporal changes in the image sequence, enhancing the stability and reliability of detection and positioning.

[0083] S503: Count the serial numbers of the magnetic resonance imaging images that show cyst detection results for each magnetic resonance imaging image.

[0084] S504: Determine whether the cyst is located in the anterior or posterior side of the humeral head region according to the number of the counted serial numbers of the magnetic resonance imaging images:

[0085] C front >C back , located in the anterior side

[0086] C front <C back, located at the rear side

[0087] Among them, C front represents the number of cysts located at the front side of the humeral head region, and C back represents the number of cysts located at the rear side of the humeral head region.

[0088] For example, count the serial numbers of the magnetic resonance imaging (MRI) images that show cyst detection results in each MRI image. The number of MRI images with serial numbers 1 - 8 showing cyst detection results is counted as C front , and the number of MRI images with serial numbers 8 - 15 showing cyst detection results is counted as C back . Compare C front with C back to determine whether the cyst is located at the front side or the rear side of the humeral head region, and divide the rectangular coordinate system into eight regions.

[0089] Specifically, when the cyst is located at the front side of the humeral head region, that is, for the MRI images with serial numbers 1 - 8, the second and third quadrants in the rectangular coordinate system are the sides closer to the body. When the cyst is located at the rear side of the humeral head region, that is, for the MRI images with serial numbers 8 - 15, the first and fourth quadrants in the rectangular coordinate system are the sides closer to the body. In this way, the rectangular coordinate system is divided into eight regions.

[0090] In the present invention, by counting the number of cyst region images in each quadrant of the rectangular coordinate system, the main distribution region of the cysts can be determined. This method helps to understand the distribution of cysts in the humeral head region, which is conducive to further analysis and processing. By comparing the image data of different serial numbers, it is possible to effectively determine whether the cyst is located at the front side or the rear side of the humeral head region. This zoning method makes the positioning of the cysts more accurate, providing strong data support for the formulation of diagnostic and treatment plans.

[0091] S505: Determine the quadrant in the rectangular coordinate system where the cyst region image is located according to the central point coordinates of the cyst region image.

[0092] S506: Count the number of cyst region images in each quadrant of the rectangular coordinate system, and take the quadrant with the largest number of cyst region images as the quadrant where the cyst is located:

[0093] max{C first , C second , C third , C fourth}

[0094] Among them, C first represents the number of cyst region images in the first quadrant, and C second represents the number of cyst region images in the second quadrant, and Cthird Indicates the number of cyst area images in the third quadrant, C fourth Indicates the number of cyst area images in the fourth quadrant.

[0095] S507: Determine the location of the cyst according to the quadrant where the cyst is located.

[0096] Further, after the cyst positioning task judgment is completed, output the location of the cyst to the folder of the positioning name.

[0097] In the present invention, by determining the quadrant where the cyst area image is located according to the central point coordinates of the cyst area image, the location of the cyst can be accurately positioned. Different quadrants represent different positions of the cyst in the humeral head area. This accurate spatial positioning can provide useful position information. Counting the number of cyst area images in each quadrant and selecting the quadrant with the largest number as the quadrant where the cyst is located helps to identify the area where the cyst most frequently appears. This statistical analysis can reveal the distribution pattern of the cyst, which is helpful for diagnosis and treatment. Outputting the location of the cyst to the specified folder helps to organize and manage the positioning results. Structured file management can facilitate subsequent data query, processing and analysis, and improve work efficiency.

[0098] In a possible implementation manner, the training method of the model includes:

[0099] Collect 512 magnetic resonance imaging (MRI) images of cysts in the shoulder humeral head as the initial data set.

[0100] Two surgeons use the labelme image annotation software to annotate the collected MRI images of cysts in the shoulder humeral head, and a kinematic injury expert checks them.

[0101] Enlarge the data set. After data enlargement, 1239 data sets are used as the training data set, and 99 are used as the validation data set.

[0102] According to the training data set, set the batch size to 2 and the number of training times to 150 times, train the model, and update the model parameters through the AMD optimization algorithm, where the initial learning rate is 0.001.

[0103] In the present invention, by collecting 512 MRI images of cysts in the shoulder humeral head and having two surgeons and a kinematic injury expert perform annotation and inspection, the annotation quality and accuracy of the data are ensured. This multi-level annotation and review mechanism effectively reduces annotation errors and omissions and improves the reliability of the training data. Setting the batch size to 2 and the number of training times to 150 times can balance the computational efficiency and model performance during the training process. A smaller batch size helps the model to more finely adjust the weights during each update, while a larger number of training times can ensure that the model fully learns the data features.

[0104] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0105] In the present invention, by inputting the magnetic resonance imaging (MRI) image into the target detection model of the humeral head region for detection, the humeral head region image is output, and then the humeral head region image is input into the cyst target detection model for detection, the cyst region image is output. This reduces the influence of speckle noise and echo perturbation on the MRI image, improves the image quality, makes the difference between the cyst and normal tissues more obvious. According to the center point coordinates of the cyst region image, the position of the cyst is determined through a spatial positioning algorithm, reducing the dependence on the doctor's cognitive ability and clinical experience, realizing automatic positioning, and avoiding confusing the humeral head cyst with the effusion caused by rotator cuff injury.

[0106] Refer to the attached Figure 2 illustrates a schematic structural diagram of a shoulder cyst positioning system provided by the present invention.

[0107] The present invention also provides a shoulder cyst positioning system 30 based on magnetic resonance imaging images, including: a memory 303 and one or more processors 301.

[0108] One or more application programs are stored in the memory 303, and the one or more application programs are adapted to be executed by the one or more processors 301 to implement the shoulder cyst positioning method based on magnetic resonance imaging images described in the method embodiments.

[0109] The shoulder cyst positioning system 30 based on magnetic resonance imaging images includes: a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as through a bus 302.

[0110] The structure of the shoulder cyst positioning system 30 based on magnetic resonance imaging images does not constitute a limitation to the embodiments of the present invention.

[0111] The processor 301 can be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. The processor 301 can also be a combination for implementing computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0112] The bus 302 may include a path for transmitting information between the above components. The bus 302 can be a PCI bus, an EISA bus, or the like. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0113] The memory 303 can be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or it can also be an EEPROM, a CD-ROM, or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but not limited to this.

[0114] It should be noted that the shoulder cyst localization system 30 based on magnetic resonance imaging (MRI) images can implement the above-mentioned shoulder cyst localization method based on MRI images and can achieve the same or similar technical effects. To avoid repetition, the present invention will not be described in detail herein.

[0115] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0116] In the present invention, by inputting the MRI image into the humeral head region target detection model for detection to output the humeral head region image, and then inputting the humeral head region image into the cyst target detection model for detection to output the cyst region image, the influence of speckle noise and echo perturbation on the MRI image is reduced, the image quality is improved, the difference between the cyst and normal tissues becomes more obvious, and according to the center point coordinates of the cyst region image, the position of the cyst is determined through a spatial positioning algorithm, reducing the dependence on the doctor's cognitive ability and clinical experience, realizing automatic positioning, and avoiding confusing the humeral head cyst with the effusion caused by rotator cuff injury.

[0117] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and the computer program can be loaded and executed by a processor to perform the shoulder cyst localization method based on MRI images described in the first aspect.

[0118] As mentioned above, the above are only the specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0119] The following points need to be explained:

[0120] (1) The accompanying drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the usual designs.

[0121] (2) For clarity, in the accompanying drawings used to describe the embodiments of the present invention, the thickness of layers or regions is enlarged or reduced, that is, these drawings are not drawn to actual scale. It can be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be intermediate elements.

[0122] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0123] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for locating shoulder cysts based on magnetic resonance imaging images, characterized in that, Including: S1: Obtain multiple magnetic resonance imaging (MRI) images; S2: Respectively construct a target detection model for the humeral head region and a target detection model for cysts based on a deep learning algorithm; S3: Input the MRI images into the target detection model for the humeral head region for detection, and output the humeral head region image; S4: Input the humeral head region image into the target detection model for cysts for detection, and output the cyst region image; S5: Determine the location of the cyst through a spatial positioning algorithm according to the center point coordinates of the cyst region image; Among them, the specific steps of S5 include: S501: Establish a rectangular coordinate system with the center point of the humeral head region image as the coordinate origin; Among them, X C and Y C respectively represent the abscissa and ordinate of the center point of the cyst area image in the humeral head area image, X B and Y B respectively represent the abscissa and ordinate of the center point of the humeral head area image, W A and H A respectively represent the width and height of the humeral head detection box; S502: Save the cyst detection results of each MRI image as a sequence vector; L i ＝(l x ,l y ,l z ) Among them, L i represents the sequence vector of the cyst detection result of the i-th magnetic resonance imaging image, l x and l y respectively represent the relative positions of the cyst region image on the X-axis and Y-axis in the rectangular coordinate system, l z represents the serial number of the magnetic resonance imaging image, x i B and y i B respectively represent the abscissa and ordinate of the center point of the i-th humeral head region image, x i C and y i C respectively represent the abscissa and ordinate of the center point of the cyst region image in the i-th humeral head region image; S503: Count the serial numbers of the MRI images where cyst detection results appear in each MRI image; S504: Determine whether the cyst is located in the front or rear side of the humeral head region according to the number of the serial numbers of the statistically obtained MRI images; C front > C back , located on the front side C front <C back , located at the rear Among them, C front represents the number of cysts located on the anterior side of the humeral head region, and C back represents the number of cysts located on the posterior side of the humeral head region; S505: Determine the quadrant where the cyst region image is located in the rectangular coordinate system according to the center point coordinates of the cyst region image; S506: Count the number of cyst region images in each quadrant of the rectangular coordinate system, and take the quadrant with the largest number of cyst region images as the quadrant where the cyst is located; max{C first ,C second ,C third ,C fourth} Among them, C first represents the number of cyst area images in the first quadrant, C second represents the number of cyst area images in the second quadrant, C third represents the number of cyst area images in the third quadrant, C fourth represents the number of cyst area images in the fourth quadrant; S507: Determine the location of the cyst according to the quadrant where the cyst is located.

2. The method for locating shoulder cysts based on magnetic resonance imaging images according to claim 1, wherein The specific steps of S3 include: S301: Input the MRI images into the target detection model for the humeral head region for detection, and output the humeral head position information; S302: Calculate the center point coordinates of the humeral head region image in the MRI image and the width and height of the humeral head detection box according to the MRI image and the humeral head position information; S303: Calculate the vertex coordinates of the humeral head detection box according to the center point coordinates of the humeral head region image in the MRI image and the width and height of the humeral head detection box; S304: Output the humeral head region image according to the vertex coordinates of the humeral head detection box.

3. The method for localizing shoulder cysts based on magnetic resonance imaging images according to claim 2, wherein, The specific content of the humeral head position information is: R1 = {cx1, cy1, w1, h1} Wherein, R1 represents the humeral head position information, cx1 and cy1 respectively represent the ratio of the abscissa and ordinate of the center point of the humeral head region image in the MRI image to the height and width of the MRI image, and w1 and h1 respectively represent the ratio of the width and height of the humeral head detection box to the width and height of the MRI image.

4. The method for locating shoulder cysts based on magnetic resonance imaging images according to claim 3, wherein, The specific content of S302 is: Calculate the center point coordinates of the humeral head region image in the MRI image and the width and height of the humeral head detection box according to the following formula: X A = cx1 × W Y A = cy1 × H W A = w1 × W H A = h1 × H Among them, X A and Y A respectively represent the abscissa and ordinate of the center point of the humeral head region image in the magnetic resonance imaging image. W and H respectively represent the width and height of the magnetic resonance imaging image. W A and H A respectively represent the width and height of the humeral head detection box.

5. The method for locating shoulder cysts based on magnetic resonance imaging images according to claim 4, characterized in that, The specific content of S303 is: Calculate the vertex coordinates of the humeral head detection box according to the following formula: Among them, X1 and Y1 respectively represent the abscissa and ordinate of vertex A of the humeral head detection frame, X2 and Y2 respectively represent the abscissa and ordinate of vertex B of the humeral head detection frame, X3 and Y3 respectively represent the abscissa and ordinate of vertex C of the humeral head detection frame, and X4 and Y4 respectively represent the abscissa and ordinate of vertex D of the humeral head detection frame.

6. The method for locating shoulder cysts based on magnetic resonance imaging images according to claim 1, wherein Specifically, S4 includes: S401: Input the humeral head region image into the cyst target detection model for detection, and output the cyst position information; S402: According to the humeral head region image and the cyst position information, output the center point coordinates of the cyst region image in the humeral head region image.

7. The method for localizing shoulder cysts based on magnetic resonance imaging images according to claim 6, wherein, The cyst position information is specifically: R2 = {cx2, cy2, w2, h2} Among them, R2 represents the cyst position information, cx2 and cy2 respectively represent the ratios of the abscissa and ordinate of the center point of the cyst region image in the humeral head region image to the height and width of the humeral head region image, and w2 and h2 respectively represent the ratios of the width and height of the cyst detection frame to the width and height of the humeral head region image.

8. The method for locating shoulder cysts based on magnetic resonance imaging images according to claim 7, characterized in that Specifically, S402 is: According to the following formula, output the center point coordinates of the cyst region image in the humeral head region image: X C = cx2 × W A Y C = cy2 × H A Among them, X C and Y C respectively represent the abscissa and ordinate of the center point of the cyst area image in the humeral head area image.

9. A shoulder cyst localization system based on magnetic resonance imaging images, characterized in that, Including: A memory and one or more processors; One or more application programs are stored in the memory, and the one or more application programs are adapted to be executed by the one or more processors to implement the shoulder cyst positioning method based on magnetic resonance imaging images according to any one of claims 1 to 8.

Images