Method and system for evaluating rotator cuff tearing recovery

Abstract

The invention relates to the technical field of sports medicine auxiliary diagnosis, in particular to a rotator cuff tearing recovery evaluation method and system. By combining multiple groups of indexes and image group feature data, the rotator cuff tearing recovery process can be effectively evaluated, score data reflecting the current rotator cuff repair postoperative development state can be obtained, and the postoperative recovery degree and potential risks are more visually determined through the score data. Therefore, automatic evaluation and prediction of the repair process are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sports medicine auxiliary diagnosis, in particular to a rotator cuff tear recovery evaluation method and system. BACKGROUND

[0002] The shoulder joint is the joint with the largest range of motion in the human body, but because of this, it is also more prone to various problems. The health of the rotator cuff is crucial for the normal movement of the shoulder joint, especially in daily life and sports activities, the function of the rotator cuff directly affects the flexibility and strength of the shoulder. Rotator cuff tear is a common shoulder disease, especially more common in high-intensity athletes.

[0003] POSS is one of the common complications after rotator cuff repair. If not treated in time, it will cause the patient's shoulder joint to appear pain and decreased range of motion, seriously affecting the patient's quality of life. Therefore, early prediction of the risk of POSS and taking relevant preventive measures is crucial for the treatment of rotator cuff tear SUMMARY

[0004] In order to solve the technical problems existing in the prior art, the embodiments of the present application provide an auxiliary evaluation method and system for combining computer medical images and multiple clinical indicators during the recovery process of rotator cuff tear. By extracting the image features, the extracted features and clinical data are automatically evaluated based on a prediction model, reducing secondary damage caused by complications during the recovery process.

[0005] In order to achieve the above purpose, the technical scheme adopted by the embodiments of the present application is as follows:

[0006] In a first aspect, a rotator cuff tear recovery evaluation method is provided, the method comprising: obtaining clinical data of a patient and image group feature data of a target region of the patient; the image group feature data includes MRI image feature data, and the clinical data includes age, disease duration, number of tendon tears, and VAS evaluation data; the target region is a damaged rotator cuff region; inputting the clinical data and the image group feature data into an evaluation model to calculate an evaluation value; the evaluation model is a nomogram model.

[0007] Further, the image group feature data includes a plurality of first-order features, a plurality of gray level co-occurrence matrix features, a plurality of gray level run-length matrix features, a plurality of gray level size zone matrix features, and a plurality of gray level correlation matrixes.

[0008] Further, the plurality of first-order features includes a first-order median, mean absolute deviation, quartile range, and root mean square of the damaged rotator cuff region.

[0009] Further, the plurality of gray level co-occurrence matrix features includes cluster prominence of the damaged rotator cuff region.

[0010] Further, the plurality of gray level run length matrix features include a run entropy of the damaged rotator cuff region.

[0011] Further, the plurality of gray level size region matrix features include a small region high gray level emphasis, a region entropy, a large region high gray level emphasis, a normalized region size non-uniformity, and a small region low gray level emphasis of the damaged rotator cuff region.

[0012] Further, the plurality of gray level dependence matrices include a normalized dependence non-uniformity of the damaged rotator cuff region.

[0013] Further, the inputting the clinical data and the image group feature data into the risk prediction model to calculate a risk value includes: obtaining a first score, a second score, a third score, a fourth score, and a fifth score corresponding to the age, the disease duration, the number of tendon tears, the VAS evaluation data, and the image group feature data, respectively, and a corresponding total score based on the nomogram model.

[0014] Further, the obtaining the fourth score corresponding to the image group feature data includes: obtaining a sub-score corresponding to a first-order median, a mean absolute deviation, a quartile range, a root mean square, a cluster prominence, a run entropy, a small region high gray level emphasis, a region entropy, a large region high gray level emphasis, a normalized region size non-uniformity, and a small region low gray level emphasis of the damaged rotator cuff region, respectively, and updating and weighting the sub-score to obtain the fifth score after weighting according to the calculation weight corresponding to the above data.

[0015] In a second aspect, a rotator cuff tear recovery evaluation system is provided, and the system includes: a data acquisition unit configured to acquire clinical data of a patient and image group feature data of a target region of the patient; and a risk prediction unit configured to input the clinical data and the image group feature data into an evaluation model to calculate an evaluation value.

[0016] In the technical scheme provided in the embodiments of the present application, the plurality of groups of indexes and the image group feature data are combined to effectively evaluate the recovery process of the rotator cuff tear, the score data reflecting the development state after the rotator cuff repair is obtained, and the postoperative recovery degree and the potential risk are more intuitively determined through the score data, so that the automatic evaluation and prediction of the repair process are realized. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] The methods, systems, and / or programs of the various aspects described herein can be implemented on one or more computers. The computers can each include a processor for executing programs and instructions stored in memory. Where computers execute instructions, the execution can be in sequence or in parallel. The computers can be general purpose computers, special purpose computers, microcode, or any other programming code or virtual machines, including general and special purpose computers combined into a special or general purpose computer. The computers can also include multiple individual computers or processing units interconnected via a computer network or other data network.

[0019] Figure 1 is a schematic diagram of a method for evaluating recovery of rotator cuff tear provided by an embodiment of the present application.

[0020] Figure 2 is a nomogram model schematic diagram in an embodiment of the present application.

[0021] Figure 3 is a schematic diagram of a system structure provided by an embodiment of the present application.

[0022] Figure 4 is a schematic diagram of a terminal device structure provided by an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to better understand the above technical solutions, the technical solutions of the present application will be described in detail below through the drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present application and the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0024] In the following detailed description, many specific details are set forth in order to provide a thorough understanding of the relevant teachings. However, it will be apparent to one skilled in the art that the present application can be practiced without these details. In other instances, well-known methods, procedures, systems, components, and / or circuits have been described at a relatively high level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

[0025] The flow diagrams in this application illustrate the execution processes performed by the systems according to the embodiments of the present application. It should be clearly understood that the execution processes of the flow diagrams can not be executed in sequence. On the contrary, these execution processes can be executed in reverse order or simultaneously. In addition, at least one other execution process can be added to the flow diagram. One or more execution processes can be deleted from the flow diagram.

[0026] Before the embodiments of the present application are further described in detail, the terms and terms involved in the embodiments of the present application are explained, and the terms and terms involved in the embodiments of the present application are applicable to the following explanation.

[0027] (1) In response to, for indicating the condition or state that the operation depends on, when the dependent condition or state is met, one or more operations performed can be real-time or have a set delay; in the absence of special instructions, there is no restriction on the execution order of multiple operations performed.

[0028] (2) Based on, for indicating the condition or state that the operation depends on, when the dependent condition or state is met, one or more operations performed can be real-time or have a set delay; in the absence of special instructions, there is no restriction on the execution order of multiple operations performed.

[0029] The embodiment of the application provides a rotator cuff tear recovery evaluation method, which obtains an MRI image by performing magnetic resonance imaging on a target region of a patient, extracts and screens image group features in the MRI image to obtain a plurality of image group feature data, and processes the plurality of image group feature data and a plurality of clinical data based on a joint scoring model to obtain an evaluation on a rotator cuff tear recovery process degree, especially an indirect prediction on a possibility of a complication in the recovery process.

[0030] The embodiment provides a rotator cuff tear recovery evaluation method, which establishes a joint evaluation model by using an MRI image and a plurality of clinical indicators, and evaluates a recovery process and degree of a rotator cuff tear based on the joint evaluation model, so that the detection rate and the accuracy are high.

[0031] For the prediction method, refer to Figure 1 , comprising the following steps:

[0032] Step S11. Obtain clinical data of a patient and image group feature data of a target region of the patient.

[0033] In the embodiment, the joint prediction method is used to evaluate the rotator cuff tear recovery process, and the logic of the joint prediction method is that a score corresponding to each indicator is obtained based on a nomogram by using a prediction model, and then a total score is obtained, the total score is used to determine the rotator cuff tear recovery degree and indirectly evaluate and predict the risk.

[0034] In the embodiment, the indicators include clinical data and MRI image group feature data. The image group feature data is MRI image feature data of a damaged rotator cuff region, and the risk prediction model is a nomogram model.

[0035] Specifically, for the clinical data in the index includes age, disease duration, number of tendon tears, VAS evaluation data. For the acquisition of image group feature data, first through image segmentation and region of interest extraction on the MRI image, wherein the image segmentation in the prior art generally adopts manual segmentation method, which depends on the judgment of the doctor, the time cost of segmentation is high, and because it depends on the experience of the doctor, it will have a certain influence on the segmentation result.

[0036] To solve this problem, in the embodiment, the segmentation of the MRI image is performed using a multi-scale feature extraction network. The multi-scale feature extraction network includes a down-sampling stage and an up-sampling stage, and feature fusion is performed between the down-sampling and the up-sampling. In the down-sampling stage, different size of dilated convolution is used to capture multi-scale context information, and each feature map extracted by the dilated convolution is grouped and processed by convolution, each group containing dilated convolution with expansion rate of 1, 6, 12 and 18, which can expand the receptive field of multi-scale features without increasing additional calculation, and then the multi-scale feature maps are spliced in the channel dimension to obtain the multi-scale feature maps.

[0037] The final multi-scale feature map uses the SE attention module to calculate the corresponding channel attention coefficient, so as to adaptively assign the importance of different scale features. Finally, the feature map is multiplied by the re-scaled channel attention weight to obtain a multi-scale feature attention feature map, and then a Concat splicing operation is performed to obtain the final feature map, which integrates all the multi-scale feature map information to obtain the final segmentation result.

[0038] Then extract multiple image group feature data in the segmentation result, and the image group feature data includes multiple first-order features, multiple gray level co-occurrence matrix features, multiple gray level run length matrix features, multiple gray level size zone matrix features and multiple gray level correlation matrixes.

[0039] The first-order features include the first-order median, mean absolute deviation, quartile range and root mean square of the damaged rotator cuff region. The gray level co-occurrence matrix features include the cluster prominence of the damaged rotator cuff region. The gray level run length matrix features include the run length entropy of the damaged rotator cuff region. The multiple gray level size zone matrix features include small region high gray level emphasis, region entropy, large region high gray level emphasis, normalized region size non-uniformity and small region low gray level emphasis of the damaged rotator cuff region. The gray level correlation matrix includes the normalized dependence non-uniformity of the damaged rotator cuff region.

[0040] Step S12. Input the clinical data and the image group feature data into the evaluation model to calculate the evaluation value.

[0041] In the embodiment, for the evaluation model is nomogram model, the nomogram model obtains the mapping score corresponding to the plurality of clinical data and the image group feature data obtained in step S11, and obtains a total score based on the score corresponding to each index and the image group feature data, wherein the total score is the evaluation value in the embodiment, which is used to represent the recovery degree of rotator cuff tear.

[0042] Specifically, the first score, the second score, the third score, the fourth score and the fifth score corresponding to the age, the disease duration, the number of tendon tears, the VAS evaluation data and the image group feature data are obtained respectively, and the corresponding total score is obtained.

[0043] The calculation result of the nomogram model can be referred to Figure 2 , wherein radsocre is the overall calculation score of the image group feature data, that is, the fourth score value. The calculation of radscore score is based on the following formula: Radscore=first order median of damaged rotator cuff region*0.00582+average absolute deviation of damaged rotator cuff region*0.00016+quartile range of damaged rotator cuff region*0.00044+root mean square of damaged rotator cuff region*0.23918+cluster prominence of damaged rotator cuff region*-0.16302+travel entropy of damaged rotator cuff region*0.00012+small region high gray emphasis of damaged rotator cuff region*-0.02745+region entropy of damaged rotator cuff region*2.0935+large region high gray emphasis of damaged rotator cuff region*0.07707398+normalized region size unevenness of damaged rotator cuff region*-0.01724+small region low gray emphasis of damaged rotator cuff region*4217343+normalized dependence unevenness of damaged rotator cuff region*-0.0004.

[0044] The specific calculation process of the nomogram in the embodiment can be directly referred to Figure 3 As shown, the calculation logic of the nomogram can be realized, and in the embodiment, it will not be described again.

[0045] In summary, in the embodiment, the recovery degree of rotator cuff tear and the complication risk can be effectively evaluated and predicted by combining the above multiple groups of indexes, and the recovery degree of rotator cuff tear can be more directly determined by the score data, so as to realize the overall automatic evaluation of the recovery of rotator cuff tear.

[0046] Referring to Figure 3 , for the method provided in steps S11-S12, in the embodiment, a prediction system 30 is further provided, and the system comprises:

[0047] A data acquisition unit 31 is configured to acquire clinical data of a patient and image group feature data of a target region of the patient.

[0048] The risk prediction unit 32 inputs the clinical data and the image feature data into an evaluation model to calculate an evaluation value.

[0049] In this embodiment, the risk prediction model is a nomogram model.

[0050] Referring to Figure 4 The above method can also be integrated into the terminal device 40 provided. Due to different configurations or performances, the terminal device can include one or more processors 401 and memories 402. The memory 402 can store one or more application programs or data. The memory 402 can be temporary or persistent. The application program stored in the memory 402 can include one or more modules (not shown in the figure), each of which can include a series of computer executable instructions in the terminal device. Further, the processor 401 can be configured to communicate with the memory 402, and execute a series of computer executable instructions in the memory 402 on the terminal device. The terminal device can also include one or more power supplies 403, one or more wired or wireless network interfaces 404, one or more input / output interfaces 405, one or more keyboards 406, and the like.

[0051] In one specific embodiment, the terminal device includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and one or more programs can include one or more modules, and each module can include a series of computer executable instructions in the terminal device, and the one or more programs configured to be executed by the one or more processors include computer executable instructions for:

[0052] Obtaining clinical data of a patient and image feature data of a target region of the patient;

[0053] The risk prediction unit 32 inputs the clinical data and the image feature data into an evaluation model to calculate an evaluation value.

[0054] The various components of the processor are specifically introduced as follows:

[0055] In the embodiment, the processor is an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the application, for example, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs).

[0056] Optionally, the processor can perform various functions by running or executing software programs stored in the memory, and calling data stored in the memory, such as performing the above-mentioned Figure 1 method.

[0057] In a specific implementation, as an embodiment, the processor can include one or more microprocessors.

[0058] The memory is configured to store software programs for implementing the schemes of the application, and the processor is configured to control the execution of the software programs. The specific implementation can refer to the above-mentioned method embodiments, and will not be described here.

[0059] Optionally, the memory can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, an optical disk storage (including a compact disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory can be integrated with the processor, or can exist independently, and is coupled to the processing unit through an interface circuit of the processor. The embodiments of the application are not limited in this regard.

[0060] It should be noted that the structure of the processor shown in the embodiment does not constitute a limitation on the device. The actual device can include more or fewer components than shown, or combine certain components, or arrange different components.

[0061] In addition, the technical effects of the processor can refer to the technical effects of the method described in the above method embodiments, which will not be repeated here.

[0062] It should be understood that the processor in the embodiments of the present application can be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0063] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0064] The above-described embodiments can be implemented in part or in whole through software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded and executed by a computer, the computer instructions or computer programs can cause the computer to perform the processes or functions described above. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as from a website, a computer, a server, or a data center to another website, computer, server, or data center through a wired (e.g., infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium or a collection of medium accessible by a computer or a data storage device such as a server, data center, etc. that includes one or more of the available medium. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0065] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following (one)" or the like means any combination of the items, including a single item (one) or a combination of multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0066] It should be understood that the size of the sequence number of each process described above in various embodiments of the present application does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0067] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0068] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0069] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0070] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0071] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0072] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the essential part or part of the technical solutions that make contributions to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0073] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for assessing rotator cuff tear recovery, characterized in that, The method includes: Acquire the patient's clinical data and imaging feature data of the target region of the patient; the imaging feature data includes MRI image feature data, and the clinical data includes age, disease duration, number of tendon tears, and VAS assessment data; the target region is the injured rotator cuff area. The clinical data and the imaging feature data are input into the evaluation model to calculate the evaluation value; the evaluation model is a nomogram model.

2. The rotator cuff tear recovery assessment method according to claim 1, characterized in that, The image group feature data includes multiple first-order features, multiple gray-level co-occurrence matrix features, multiple gray-level run-length matrix features, multiple gray-level size region matrix features, and multiple gray-level correlation matrices.

3. The rotator cuff tear recovery assessment method according to claim 2, characterized in that, The first-order features include the first-order median, mean absolute deviation, interquartile range, and root mean square of the damaged rotator cuff region.

4. The rotator cuff tear recovery assessment method according to claim 3, characterized in that, The gray-scale co-occurrence matrix features include clustered protrusions in the damaged rotator cuff region.

5. The rotator cuff tear recovery assessment method according to claim 4, characterized in that, The grayscale travel matrix features include the travel entropy of the damaged rotator cuff region.

6. The rotator cuff tear recovery assessment method according to claim 5, characterized in that, The multiple grayscale region matrix features include high grayscale emphasis in small regions of the damaged rotator cuff region, region entropy, high grayscale emphasis in large regions, normalized region size non-uniformity, and low grayscale emphasis in small regions.

7. The rotator cuff tear recovery assessment method according to claim 6, characterized in that, The grayscale correlation matrix includes the normalized dependency non-uniformity of the damaged rotator cuff region.

8. The rotator cuff tear recovery assessment method according to claim 7, characterized in that, The step of inputting the clinical data and the imaging feature data into the risk prediction model to calculate the risk value includes: obtaining the first score, second score, third score, fourth score, and fifth score corresponding to the age, disease duration, number of tendon tears, VAS assessment data, and the imaging feature data, as well as the corresponding total score, based on the nomogram model.

9. The rotator cuff tear recovery assessment method according to claim 8, characterized in that, The process of obtaining the fourth score corresponding to the feature data of the image group includes: obtaining the first-order median, mean absolute deviation, interquartile range, root mean square, cluster prominence, stroke entropy, high gray-scale emphasis in small regions, region entropy, high gray-scale emphasis in large regions, normalized region size inhomogeneity, and low gray-scale emphasis in small regions for the damaged rotator cuff region, and then updating the sub-scores according to the calculation weights corresponding to the above data and weighting them to obtain the fifth score.

10. A rotator cuff tear recovery assessment system, characterized in that, The system includes: The data acquisition unit is used to acquire the patient's clinical data and the image group feature data of the patient's target area; The risk prediction unit inputs the clinical data and the imaging group feature data into the evaluation model to calculate the evaluation value.

Images