An orthopedic consumable identification method, system, electronic device and storage medium

Abstract

The application discloses an orthopedic consumable identification method and system, an electronic device and a storage medium. The method comprises the following steps: labeling an orthopedic consumable image to be identified to obtain an orthopedic consumable image to be identified with labels; performing target detection on the orthopedic consumable image to be identified with labels to identify a target position of the orthopedic consumable to be identified; segmenting the orthopedic consumable image to be identified with labels according to the target position to obtain a mask image of the orthopedic consumable to be identified; identifying a central axis of the orthopedic consumable to be identified by using a skeleton algorithm based on the mask image of the orthopedic consumable to be identified; and identifying the specification of the orthopedic consumable to be identified based on the central axis. The application can improve the identification efficiency and accuracy of orthopedic consumables.

Description

Technical Field

[0001] This application relates to the field of medical consumables identification technology, and in particular to an orthopedic consumables identification method, system, electronic device and storage medium. Background Technology

[0002] In the current medical field, especially in orthopedic surgery, the accurate identification and specification confirmation of orthopedic consumables are crucial to ensuring the smooth progress of the surgery. Orthopedic surgery uses a wide variety of high-value consumables, with complex specifications and a significant number of small-sized components. Traditional methods for identifying orthopedic consumables typically involve manually observing their appearance and then comparing them to a specification sheet. This method is not only time-consuming and labor-intensive, leading to low efficiency, but is also susceptible to human error, resulting in inconsistent accuracy. Furthermore, although image recognition-based consumable identification technologies have emerged, these technologies often only achieve rough category identification and cannot accurately identify the specifications of orthopedic consumables, thus failing to meet the high-precision identification requirements of the medical field. Summary of the Invention

[0003] The main purpose of this application is to overcome the shortcomings and deficiencies of the prior art and provide a method, system, electronic device and storage medium for identifying orthopedic consumables, which can improve the identification efficiency and accuracy of orthopedic consumables.

[0004] To achieve the above objectives, this application adopts the following technical solution:

[0005] In a first aspect, this application provides a method for identifying orthopedic consumables, comprising the following steps:

[0006] The images of orthopedic consumables to be identified are labeled to obtain tagged images of orthopedic consumables to be identified;

[0007] Target detection is performed on the tagged image of the orthopedic consumable to be identified in order to identify the target location of the orthopedic consumable;

[0008] The image of the tagged orthopedic consumable to be identified is segmented according to the target location to obtain a mask image of the orthopedic consumable to be identified.

[0009] Based on the mask image of the orthopedic consumable to be identified, the skeleton algorithm is used to identify the central axis of the orthopedic consumable to be identified;

[0010] Based on the central axis, the specifications of the orthopedic consumable to be identified are obtained.

[0011] As a preferred technical solution, before performing target detection on the tagged orthopedic consumable image to be identified, the method further includes performing random image enhancement processing on the orthopedic consumable image to be identified.

[0012] The random image enhancement process includes randomly scaling the image, randomly cropping the image, randomly flipping the image, randomly rotating the image, and randomly adjusting the image's brightness, contrast, saturation, and chroma.

[0013] As a preferred technical solution, before performing target detection on the tagged orthopedic consumable image to be identified, the method further includes processing the tagged orthopedic consumable image to be identified into a preset pixel size and scaling the pixel values ​​to a preset range.

[0014] As a preferred technical solution, the preset pixel size includes 416x416 or 640x640 pixels;

[0015] The preset range is [0,1].

[0016] As a preferred technical solution, the YOLOv8 target detection model is used to perform target detection on the labeled orthopedic consumable image to identify the category and target location of the orthopedic consumable, including:

[0017] Features are extracted from the labeled images of orthopedic consumables to be identified, resulting in a high-dimensional feature map that includes semantic information at different levels.

[0018] The high-dimensional feature maps of the different levels of semantic information are fused to obtain a fused feature map.

[0019] Based on the fused feature map, each potential target is predicted, and the target location, confidence level, and class probability are obtained; wherein, the target location is represented in the form of a rectangular box.

[0020] As a preferred technical solution, the following are also included:

[0021] Non-maximum suppression is applied to the rectangular boxes to remove those with an overlap exceeding a preset overlap threshold.

[0022] As a preferred technical solution, the step of segmenting the image of the tagged orthopedic consumable to be identified based on the target location to obtain a mask image of the orthopedic consumable to be identified includes:

[0023] Features of the orthopedic consumables to be identified within the rectangular frame are extracted to obtain orthopedic consumables features at different scales;

[0024] The features of orthopedic consumables at different scales are fused to obtain a fused orthopedic consumable feature map;

[0025] Based on the fused orthopedic consumable feature map, a mask map of the orthopedic consumable to be identified is predicted; wherein, each pixel of the mask map of the orthopedic consumable to be identified is assigned a category label.

[0026] As a preferred technical solution, the method further includes inputting the mask image of the orthopedic consumable to be identified into a preset neural network for further segmentation.

[0027] As a preferred technical solution, the step of identifying the central axis of the orthopedic consumable based on the mask image of the consumable to be identified using a skeleton algorithm includes:

[0028] The mask image of the orthopedic consumable to be identified is processed into grayscale to obtain a grayscale mask image;

[0029] The grayscale mask image is binarized to obtain a binary mask image;

[0030] Starting from the edge of the binary mask, the pixels at the edge of the target object are gradually removed inward through an erosion operation;

[0031] The dilation operation recovers some of the pixels removed during the erosion operation;

[0032] The erosion and dilation operations are performed iteratively until the orthopedic consumable to be identified is simplified to a skeleton of a single pixel width.

[0033] The central axis is extracted from the skeleton with a width of one pixel.

[0034] As a preferred technical solution, the binarization is to divide the pixel values ​​in the grayscale mask into pixel values ​​of the target object and pixel values ​​of the background, so as to highlight the outline and shape of the target object.

[0035] As a preferred technical solution, the step of identifying the specifications of the orthopedic consumable to be identified based on the central axis includes:

[0036] Determine the intersection point of the two ends of the mask image of the orthopedic consumable to be identified;

[0037] The length of the orthopedic consumable to be identified is obtained by calculating the distance between the two intersection points.

[0038] Draw a perpendicular line on the central axis;

[0039] Sort the distances between the vertical line and the boundary of the mask image of the orthopedic consumable to be identified in descending order;

[0040] The distance ranked first is taken as the diameter of the orthopedic consumable to be identified;

[0041] Calculate the first difference between the length of the orthopedic consumable to be identified and the length of each specification in the preset orthopedic consumable specification library;

[0042] Calculate the second difference between the diameter of the orthopedic consumable to be identified and the diameter of each specification in the preset orthopedic consumable specification library;

[0043] The absolute values ​​of the first difference and the second difference of the orthopedic consumable to be identified are summed to obtain the comprehensive difference between the orthopedic consumable to be identified and each specification in the preset orthopedic consumable specification library.

[0044] Sort the combined differences in ascending order;

[0045] In the preset orthopedic consumables specification library, the specification with the highest comprehensive difference ranking is selected as the final specification of the orthopedic consumable to be identified.

[0046] Secondly, this application provides an orthopedic consumable identification system, applied to the aforementioned orthopedic consumable identification method, including a labeling module, a target detection module, a segmentation module, a central axis identification module, and an orthopedic consumable specification identification module;

[0047] The annotation module is used to annotate the orthopedic consumable images to be identified, so as to obtain orthopedic consumable images with labels.

[0048] The target detection module is used to perform target detection on the tagged image of the orthopedic consumable to be identified, so as to identify the target location of the orthopedic consumable to be identified.

[0049] The segmentation module is used to segment the image of the labeled orthopedic consumable to be identified according to the target location to obtain a mask image of the orthopedic consumable to be identified.

[0050] The central axis identification module is used to identify the central axis of the orthopedic consumable to be identified based on the mask image of the orthopedic consumable to be identified, using a skeleton algorithm.

[0051] The orthopedic consumable specification identification module is used to identify the specifications of the orthopedic consumable to be identified based on the central axis.

[0052] As a preferred technical solution, an enhanced processing module is also included;

[0053] The enhancement processing module is used to perform random image enhancement processing on the orthopedic consumable image to be identified before performing target detection on the tagged orthopedic consumable image to be identified.

[0054] The random image enhancement process includes randomly scaling the image, randomly cropping the image, randomly flipping the image, randomly rotating the image, and randomly adjusting the image's brightness, contrast, saturation, and chroma.

[0055] As a preferred technical solution, a pixel processing module is also included;

[0056] The pixel processing module is used to process the labeled orthopedic consumable image to a preset pixel size and scale the pixel values ​​to a preset range before performing target detection on the image of the orthopedic consumable to be identified.

[0057] As a preferred technical solution, the target detection module is specifically used for:

[0058] The YOLOv8 object detection model is used to perform object detection on the labeled orthopedic consumable images to identify the category and location of the orthopedic consumables, including:

[0059] Features are extracted from the labeled images of orthopedic consumables to be identified, resulting in a high-dimensional feature map that includes semantic information at different levels.

[0060] The high-dimensional feature maps of the different levels of semantic information are fused to obtain a fused feature map.

[0061] Based on the fused feature map, each potential target is predicted, and the target location, confidence level, and class probability are obtained; wherein, the target location is represented in the form of a rectangular box.

[0062] As a preferred technical solution, the segmentation module is specifically used for:

[0063] Features of the orthopedic consumables to be identified within the rectangular frame are extracted to obtain orthopedic consumables features at different scales;

[0064] The features of orthopedic consumables at different scales are fused to obtain a fused orthopedic consumable feature map;

[0065] Based on the fused orthopedic consumable feature map, a mask map of the orthopedic consumable to be identified is predicted; wherein, each pixel of the mask map of the orthopedic consumable to be identified is assigned a category label.

[0066] As a preferred technical solution, the centerline identification module is specifically used for:

[0067] The mask image of the orthopedic consumable to be identified is processed into grayscale to obtain a grayscale mask image;

[0068] The grayscale mask image is binarized to obtain a binary mask image;

[0069] Starting from the edge of the binary mask, the pixels at the edge of the target object are gradually removed inward through an erosion operation;

[0070] The dilation operation recovers some of the pixels removed during the erosion operation;

[0071] The erosion and dilation operations are performed iteratively until the orthopedic consumable to be identified is simplified to a skeleton of a single pixel width.

[0072] The central axis is extracted from the skeleton with a width of one pixel.

[0073] As a preferred technical solution, the orthopedic consumable specification identification module is specifically used for:

[0074] Determine the intersection point of the two ends of the mask image of the orthopedic consumable to be identified;

[0075] The length of the orthopedic consumable to be identified is obtained by calculating the distance between the two intersection points.

[0076] Draw a perpendicular line on the central axis;

[0077] Sort the distances between the vertical line and the boundary of the mask image of the orthopedic consumable to be identified in descending order;

[0078] The distance ranked first is taken as the diameter of the orthopedic consumable to be identified;

[0079] Calculate the first difference between the length of the orthopedic consumable to be identified and the length of each specification in the preset orthopedic consumable specification library;

[0080] Calculate the second difference between the diameter of the orthopedic consumable to be identified and the diameter of each specification in the preset orthopedic consumable specification library;

[0081] The absolute values ​​of the first difference and the second difference of the orthopedic consumable to be identified are summed to obtain the comprehensive difference between the orthopedic consumable to be identified and each specification in the preset orthopedic consumable specification library.

[0082] Sort the combined differences in ascending order;

[0083] In the preset orthopedic consumables specification library, the specification with the highest comprehensive difference ranking is selected as the final specification of the orthopedic consumable to be identified.

[0084] Thirdly, this application provides an electronic device, the electronic device comprising:

[0085] At least one processor; and a memory communicatively connected to said at least one processor;

[0086] The memory stores computer program instructions that can be executed by the at least one processor, which are then executed by the at least one processor to enable the at least one processor to perform the orthopedic consumable identification method.

[0087] Fourthly, this application provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the aforementioned method for identifying orthopedic consumables.

[0088] In summary, compared with the prior art, the effective effects of the technical solution provided in this application include at least the following:

[0089] This application proposes a method for identifying orthopedic consumables. The method involves labeling an image of the orthopedic consumable to be identified, obtaining a labeled image; performing target detection on the labeled image to identify the target location of the consumable; segmenting the labeled image based on the target location to obtain a mask image of the consumable; using the mask image to identify the central axis of the consumable; and identifying the specifications of the consumable based on the central axis. This application employs a target detection algorithm to perform target detection on images of labeled orthopedic consumables, accurately identifying the category and location of the consumables. Through image segmentation algorithms, it can accurately extract features of orthopedic consumables of different shapes and sizes, segmenting the image into foreground and background for more accurate contour extraction. Furthermore, a skeleton algorithm is used to identify the central axis of the consumables, and based on this information, the specifications of the consumables are accurately determined. This improves the accuracy and efficiency of identification, meeting the high-precision identification needs of the medical field. Attached Figure Description

[0090] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0091] Figure 1 A flowchart illustrating an orthopedic consumable identification method provided in one embodiment of this application;

[0092] Figure 2 A flowchart illustrating the steps of target detection in orthopedic consumable images provided in one embodiment of this application;

[0093] Figure 3 A flowchart illustrating the steps of orthopedic consumable image segmentation provided in one embodiment of this application;

[0094] Figure 4 A mask image of an orthopedic consumable to be identified, provided in one embodiment of this application;

[0095] Figure 5A flowchart illustrating the steps for identifying the centerline in one embodiment of this application;

[0096] Figure 6 A schematic diagram of the central axis obtained by the skeleton algorithm is provided in one embodiment of this application;

[0097] Figure 7 A flowchart illustrating the steps for identifying orthopedic consumable specifications based on the central axis, as provided in one embodiment of this application;

[0098] Figure 8 This is a block diagram of an orthopedic consumable identification system provided in one embodiment of this application. Detailed Implementation

[0099] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative effort are within the scope of protection of the present application.

[0100] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0101] Example:

[0102] Please see Figure 1 One embodiment of this application provides a method for identifying orthopedic consumables, comprising the following steps:

[0103] S1. Label the images of orthopedic consumables to be identified to obtain labeled images of orthopedic consumables to be identified.

[0104] In this embodiment, a high-speed document scanner is first used to capture images of orthopedic consumables. The height of the high-speed document scanner is fixed so that the size of the actual object does not change with the shooting height. Then, the orthopedic consumable images are labeled with category tags. Based on the specific tags of the actual object images, the image recognition algorithm is labeled onto the tags.

[0105] In this application embodiment, more than 60 categories of orthopedic consumables were collected, and the category labels included: (1) Mini T-plate Type 3, (2) Minimally Invasive Mini Y-plate Type 1, (3) Minimally Invasive Mini Y-plate Type 3, (4) Mini T-plate Type 1, (5) Minimally Invasive Mini Locking Plate Type 2, (6) Minimally Invasive Mini Locking Plate Type 3, (7) Large T-locking Plate Type 1, (8) Large Proximal Locking Plate Proximal Femoral Type 1, (9) Small Distal Locking Plate Lateral Distal Humerus Minimally Invasive Type 1, (10) Small Distal Locking Plate Medial Distal Humerus Type 1, (11) Minimally Invasive Mini Locking Plate Type 1, (12) Minimally Invasive Hook Locking Plate Minimally Invasive Type 1, (13) Mini L-plate Type 1, (14) Minimally Invasive T-plate Type 1, (15) Medium Proximal Locking Plate Type 1 for proximal tibia locking plate, (16) Medium proximal locking plate for proximal tibia locking plate for lateral tibia locking plate, (17) Medium proximal locking plate for proximal tibia locking plate for lateral tibia locking plate (minimally invasive type 1), (18) Medium L-shaped locking plate for type 2, (19) Large T-shaped support locking plate for lateral tibia locking plate (minimally invasive type 1), (20) Trefoil locking plate for type 1, (21) Medium T-shaped locking plate for type 1, (22) Medium T-shaped locking plate for type 2, (23) Large locking plate (stable type), (24) Medium distal locking plate for lateral distal tibia locking plate, (25) Medium distal locking plate for medial distal tibia locking plate, (26) Narrow locking plate (limited contact type), (27) Calcaneal locking plate for type 1, (28) Small Y-shaped locking plate for type 1, (29) Small T-shaped locking plate for type 1, (30) Medium Y-shaped locking plate Type 1, (31) Small locking plate with limited contact, (32) Tubular locking plate Type 1, (33) Reconstruction locking plate Type 1, (34) Small distal locking plate for lateral distal humerus Type 1, (35) Small distal locking plate for distal fibula Type 1, (36) Small distal locking plate for fibula Type 2, (37) Pelvic system bone plate, (38) Small proximal locking plate for olecranon of ulna Type 1, (39) Small proximal locking plate for proximal humerus Type 1, (40) Narrow locking plate for stability, (41) Small Y-shaped locking plate for minimally invasive Type 3, (42) Small T-shaped support locking plate Type 1, (43) Clavicle hook locking plate Type 1, (44) Arc-shaped reconstruction locking plate Type 2, (45) Small L-shaped locking plate Type 1, (46) Small proximal locking plate Type 3 olecranon screw for ulna, (47) Type 4 tail screw for locked intramedullary nail for humerus, (48) Type 4 transverse locking screw for locked intramedullary nail for humerus, (49) Main nail for locked intramedullary nail for humerus, (50) Type 1 spiral blade for locked intramedullary nail for humerus, (51) Type 2 tail screw for locked intramedullary nail for humerus, (52) Type 4 transverse locking screw for locked intramedullary nail for femur, (53) Main nail for locked intramedullary nail for femur, (54) Type 2 fully threaded headless compression screw, (55) Ordinary washer, (56) Self-tapping semi-threaded hollow screw, (57) Type 2 self-tapping regular threaded tapered locking screw, (58) Type 1 self-tapping regular threaded tapered locking screw, (59) Ordinary cortical bone screw, (60) Double threaded hollow screw, (61) Fully threaded cancellous bone screw.

[0106] Furthermore, before performing target detection on the tagged orthopedic consumable image to be identified, random image enhancement processing is also performed on the orthopedic consumable image to be identified.

[0107] The random image enhancement process includes randomly scaling the image, randomly cropping the image, randomly flipping the image, randomly rotating the image, and randomly adjusting the image's brightness, contrast, saturation, and chroma.

[0108] Using random image augmentation methods not only increases the diversity of the dataset, but also effectively improves the robustness of the model, helping it adapt to different shooting conditions and scenarios in real-world applications. Through these augmentation techniques, the YOLOv8 object detection model can better identify and locate objects, especially when dealing with complex and ever-changing environments, where it performs even better.

[0109] Before performing target detection on the tagged orthopedic consumable images to be identified, the method also includes processing the tagged orthopedic consumable images to be identified into a preset pixel size and scaling the pixel values ​​to a preset range.

[0110] Specifically, the preset pixel size includes 416x416 or 640x640 pixels; the preset range is [0,1].

[0111] The images of tagged orthopedic consumables to be identified are processed to a fixed size (416x416 or 640x640 pixels), and the pixel values ​​are scaled to the range of [0,1]. The purpose is to enable the subsequent YOLOv8 object detection model to process the images efficiently while maintaining sufficient detail.

[0112] S2. Perform target detection on the image of the orthopedic consumable to be identified with the label to identify the target location of the orthopedic consumable to be identified.

[0113] This application embodiment uses the YOLOv8 object detection model to perform object detection on the labeled image of orthopedic consumables to be identified, in order to identify the category and target location of the orthopedic consumables. Please refer to [link to relevant documentation]. Figure 2 The steps include:

[0114] S21. Extract features from the labeled orthopedic consumable image to obtain a high-dimensional feature map including semantic information at different levels;

[0115] The backbone network in the YOLOv8 object detection model extracts features from labeled orthopedic consumable images and transforms these features into a series of high-dimensional feature maps. Each feature map captures different levels of semantic information. From low-level edge and texture information to high-level target structure information, these feature maps provide rich feature representations for subsequent object detection.

[0116] The backbone network can be a CSPDarknet network, which can more effectively extract feature information from images, thereby improving the accuracy and inference speed of the model, enabling faster and more accurate acquisition of key features in consumable identification and localization tasks.

[0117] S22. The high-dimensional feature maps of the different levels of semantic information are fused to obtain a fused feature map;

[0118] Furthermore, the Neck network (such as FPN or PANet) in the YOLOv8 object detection model is used to fuse features at different scales. By fusing feature maps of different resolutions, YOLOv8 can better detect targets of different sizes, especially when the target sizes vary greatly. This multi-scale feature fusion mechanism can significantly improve detection performance, enabling the model to more accurately locate and identify consumables of various sizes.

[0119] The Neck network employs an improved FPN or PANet, and YOLOv8 can better handle objects of different scales, especially showing greater accuracy in detecting small objects. In orthopedic consumable identification, small-sized screws and other consumables can be detected and located more accurately, effectively improving the model's performance in practical applications.

[0120] S23. Based on the fused feature map, predict each potential target to obtain the target location, confidence level and class probability; wherein the target location is represented in the form of a rectangular box.

[0121] Furthermore, the YOLOv8 object detection model will eventually output the target location, confidence level, and class probability for each orthopedic consumable.

[0122] Here, the target location represents the position of the target in the image, usually a normalized value relative to the image size. The target location has four coordinates, which can be represented as the top-left corner (x1, y1) and bottom-right corner (x2, y2), or the center point (cx, cy), width (w), and height (h). The target location is represented by a bounding box (i.e., the predicted bounding box of the target location). The confidence score represents the confidence that the target is contained within the bounding box (predicted bounding box of the target location), ranging from 0 to 1. The closer the value is to 1, the more likely the target is to exist. The class probability represents the probability of each box corresponding to a different class. YOLOv8 can detect multiple classes and output the probability value for each class, thereby achieving the identification of different types of consumables.

[0123] After identifying the target location, confidence level, and class probability, the process includes using Non-Maximum Suppression (NMS) to process multiple bounding boxes, removing duplicates and retaining the best one. The core idea of ​​NMS is that if the overlap between two boxes exceeds a certain threshold, the box with the highest confidence level is retained, and other overlapping boxes are removed. The final output bounding box includes location, confidence level, and class. Typically, only bounding boxes with a confidence level greater than a certain threshold (e.g., 0.5) are retained as the final target identification and localization result.

[0124] The YOLOv8 object detection model in this embodiment optimizes the loss functions for localization and classification during training, enabling it to learn target location and category information more effectively. This allows for more accurate identification and localization of orthopedic consumables in practical detection. Furthermore, to ensure efficient inference on various hardware and support real-time detection applications, YOLOv8 employs optimization techniques such as quantization, pruning, and TensorRT. These techniques effectively reduce the model's computational complexity and improve inference speed, enabling rapid and accurate identification and localization of consumables in real-time applications, meeting real-time requirements.

[0125] S3. Segment the image of the tagged orthopedic consumable to be identified according to the target location to obtain a mask image of the orthopedic consumable to be identified.

[0126] This application also constructs a segmentation model based on the YOLOv8 algorithm and uses the YOLOv8 segmentation model to segment the labeled orthopedic consumable images.

[0127] Please see Figure 3 The steps include segmenting the image of the tagged orthopedic consumable to be identified based on the target location to obtain a mask image of the orthopedic consumable to be identified, and the following steps:

[0128] S31. Extract the features of the orthopedic consumables to be identified within the rectangular frame to obtain orthopedic consumables features at different scales;

[0129] Furthermore, the backbone network in the YOLOv8 segmentation model uses an efficient CNN architecture, such as CSPDarknet, to extract features of orthopedic consumables within rectangular boxes.

[0130] S32. The features of orthopedic consumables at different scales are fused to obtain a fused orthopedic consumables feature map;

[0131] The Neck network in the YOLOv8 segmentation model fuses features from multiple scales of orthopedic consumables to help handle targets of different sizes. Segmentation tasks require capturing fine-grained spatial information, especially at object boundaries. Multi-scale feature fusion can better capture this detailed information and improve segmentation accuracy.

[0132] The YOLOv8 segmentation model Neck network can use either FPN or PANet.

[0133] S33. Based on the fused orthopedic consumable feature map, a mask map of the orthopedic consumable to be identified is predicted; wherein, each pixel of the mask map of the orthopedic consumable to be identified is assigned a category label.

[0134] For the predicted mask image of the orthopedic consumable to be identified, please refer to [link / reference]. Figure 4 .

[0135] Furthermore, the Head in the YOLOv8 segmentation model is adjusted according to the specific task. For segmentation tasks, the Head outputs the category information for each pixel. Specifically, it predicts a category label for each pixel, distinguishing different objects within the same category. In this embodiment, to meet the requirements of subsequent algorithm measurements, the instance segmentation model is changed to a semantic segmentation model, where the segmentation category is set to 0-1, with 1 representing the foreground (orthopedic consumables) and 0 representing the background. This simplifies the segmentation results and facilitates subsequent image processing algorithms for identifying specifications and models.

[0136] This application also includes inputting the mask image of the orthopedic consumable to be identified into a preset neural network for further segmentation, which can ensure that small consumables, especially screws, are segmented more accurately.

[0137] This application can output the bounding box set of objects through the segmentation model, which makes the acquisition of information such as the shape and contour of consumables more detailed and accurate, creating favorable conditions for subsequent targeted specification measurement according to different types of consumables, and further improving the accuracy and practicality of the entire recognition.

[0138] S4. Based on the mask image of the orthopedic consumable to be identified, the skeleton algorithm is used to identify the central axis of the orthopedic consumable to be identified.

[0139] Please see Figure 5 Based on the mask image of the orthopedic consumable to be identified, a skeleton algorithm is used to identify the central axis of the orthopedic consumable to be identified. The steps include:

[0140] S41. Perform grayscale processing on the mask image of the orthopedic consumable to be identified to obtain a grayscale mask image;

[0141] S42. Binarize the grayscale mask to obtain a binary mask;

[0142] In this application, grayscale masks are binarized using methods such as thresholding or Otsu's method to convert them into black-and-white binarized masks (with a white background and a black target).

[0143] Specifically, binarization involves dividing the pixel values ​​in the grayscale mask into pixel values ​​of the target object and pixel values ​​of the background to highlight the outline and shape of the target object.

[0144] S43. Starting from the edge of the binary mask, remove the pixels at the edge of the target object step by step inward through an erosion operation;

[0145] S44. Recover some of the pixels removed in the erosion operation through the dilation operation;

[0146] S45. Iteratively execute the erosion and dilation operations until the orthopedic consumable to be identified is simplified to a skeleton with a single pixel width.

[0147] S46. Extract the central axis from the skeleton with the width of the single pixel;

[0148] Skeleton algorithms simplify objects in an image to their central axis or main skeleton. (See also: [link to relevant documentation]) Figure 6 This is achieved through iterative morphological operations, namely alternating erosion and dilation operations. This process is called thinning, which continuously reduces the boundaries of an object to eventually obtain a thin skeleton.

[0149] S5. Based on the central axis, the specifications of the orthopedic consumable to be identified are obtained.

[0150] Please see Figure 7 Based on the central axis, the specifications of the orthopedic consumable to be identified are determined, and the steps include:

[0151] S51. Determine the intersection point of the two ends of the mask image of the orthopedic consumable to be identified;

[0152] S52. Calculate the distance between the two intersection points to obtain the length of the orthopedic consumable to be identified;

[0153] S53. Draw a perpendicular line on the central axis;

[0154] S54. Sort the distances between the vertical line and the boundary of the mask image of the orthopedic consumable to be identified in descending order;

[0155] S55. The distance ranked first is taken as the diameter of the orthopedic consumable to be identified;

[0156] S56. Calculate the first difference between the length of the orthopedic consumable to be identified and the length of each specification in the preset orthopedic consumable specification library;

[0157] S57. Calculate the second difference between the diameter of the orthopedic consumable to be identified and the diameter of each specification in the preset orthopedic consumable specification library;

[0158] S58. Sum the absolute values ​​of the first difference and the second difference of the orthopedic consumable to be identified to obtain the comprehensive difference between the orthopedic consumable to be identified and each specification in the preset orthopedic consumable specification library.

[0159] S59. Sort the comprehensive differences in ascending order;

[0160] S510. In the preset orthopedic consumables specification library, select the specification ranked first by the comprehensive difference as the final specification of the orthopedic consumable to be identified.

[0161] By determining the intersection points of the central axis at both ends of the orthopedic consumable mask, the length of the orthopedic consumable is obtained by calculating the distance between the two intersection points. A perpendicular line is drawn on the central axis, and the distances between the perpendicular line and the boundaries of the orthopedic consumable mask are sorted in descending order. The distance ranked first is selected as the diameter of the orthopedic consumable. Then, the difference between this distance and the length and diameter in a pre-set orthopedic consumable specification library is calculated, and the combined differences are sorted. Finally, the specification ranked first in the combined difference is selected as the final identification specification of the orthopedic consumable. For example, suppose the length of the orthopedic consumable to be identified is 52 mm and the diameter is 3.1 mm; the pre-set orthopedic consumable specification library has two specifications, specification A (50 mm long, 3 mm diameter) and specification B (55 mm long, 3.2 mm diameter); then the length of the orthopedic consumable to be identified is calculated compared with the length and diameter in specification A. The first difference in length is 2 mm, and the second difference between the length of the orthopedic consumable to be identified and the diameter in specification A is 0.1 mm. The first difference between the length of the orthopedic consumable to be identified and the length in specification B is -3 mm, and the second difference between the length of the orthopedic consumable to be identified and the diameter in specification B is 0.1 mm. The total difference between the orthopedic consumable to be identified and specification A is calculated to be 2 + 0.1 = 2.1 mm, and the total difference between the orthopedic consumable to be identified and specification B is 3 + 0.1 = 3.1 mm. The total difference of specification A is smaller, so specification A is selected as the final identified specification of the orthopedic consumable to be identified. This achieves accurate matching of orthopedic consumable specifications and effectively solves the problem that traditional methods cannot accurately identify orthopedic consumable specifications, providing more accurate and reliable consumable information for orthopedic surgery.

[0162] The orthopedic consumable identification method of this application is applicable to various types, specifications, and sizes of orthopedic consumables. This application employs a target detection algorithm to perform target detection on the image of the labeled orthopedic consumable to be identified, accurately identifying the target location of the consumable. Through image segmentation algorithms, it can accurately extract the features of orthopedic consumables of different shapes and sizes, segmenting the image of the consumable into foreground and background, thereby more accurately extracting the outline of the consumable. Based on this, a skeleton algorithm is used to identify the central axis of the consumable, and then, based on the central axis information, the specifications of the consumable are accurately identified. This improves the accuracy and efficiency of identification, meeting the high-precision identification needs of the medical field.

[0163] It should be noted that, for the sake of simplicity, the aforementioned method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously.

[0164] Based on the same idea as the orthopedic consumable identification method in the above embodiments, this application also provides an orthopedic consumable identification system, which can be used to execute the above-described orthopedic consumable identification method. For ease of explanation, the schematic diagram of an embodiment of an orthopedic consumable identification system only shows the parts related to the embodiments of this application. Those skilled in the art will understand that the illustrated structure does not constitute a limitation on the system, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0165] Please see Figure 8 In another embodiment of this application, an orthopedic consumable identification system is provided, which includes a labeling module 101, a target detection module 102, a segmentation module 103, a central axis identification module 104, and an orthopedic consumable specification identification module 105.

[0166] The annotation module 101 is used to annotate the orthopedic consumable image to be identified, so as to obtain the orthopedic consumable image to be identified with a label.

[0167] The target detection module 102 is used to perform target detection on the image of the tagged orthopedic consumable to be identified, so as to identify the target location of the orthopedic consumable to be identified.

[0168] The segmentation module 103 is used to segment the image of the labeled orthopedic consumable to be identified according to the target position to obtain a mask image of the orthopedic consumable to be identified.

[0169] The central axis identification module 104 is used to identify the central axis of the orthopedic consumable to be identified based on the mask image of the orthopedic consumable to be identified and using a skeleton algorithm.

[0170] The orthopedic consumable specification identification module 105 is used to identify the specification of the orthopedic consumable to be identified based on the central axis.

[0171] As a preferred technical solution, an enhanced processing module is also included;

[0172] The enhancement processing module is used to perform random image enhancement processing on the orthopedic consumable image to be identified before performing target detection on the tagged orthopedic consumable image to be identified.

[0173] The random image enhancement process includes randomly scaling the image, randomly cropping the image, randomly flipping the image, randomly rotating the image, and randomly adjusting the image's brightness, contrast, saturation, and chroma.

[0174] As a preferred technical solution, a pixel processing module is also included;

[0175] The pixel processing module is used to process the labeled orthopedic consumable image to a preset pixel size and scale the pixel values ​​to a preset range before performing target detection on the image of the orthopedic consumable to be identified.

[0176] As a preferred technical solution, the target detection module 102 is specifically used for:

[0177] The YOLOv8 object detection model is used to perform object detection on the labeled orthopedic consumable images to identify the category and location of the orthopedic consumables, including:

[0178] Features are extracted from the labeled images of orthopedic consumables to be identified, resulting in a high-dimensional feature map that includes semantic information at different levels.

[0179] The high-dimensional feature maps of the different levels of semantic information are fused to obtain a fused feature map.

[0180] Based on the fused feature map, each potential target is predicted, and the target location, confidence level, and class probability are obtained; wherein, the target location is represented in the form of a rectangular box.

[0181] As a preferred technical solution, the segmentation module 103 is specifically used for:

[0182] Features of the orthopedic consumables to be identified within the rectangular frame are extracted to obtain orthopedic consumables features at different scales;

[0183] The features of orthopedic consumables at different scales are fused to obtain a fused orthopedic consumable feature map;

[0184] Based on the fused orthopedic consumable feature map, a mask map of the orthopedic consumable to be identified is predicted; wherein, each pixel of the mask map of the orthopedic consumable to be identified is assigned a category label.

[0185] As a preferred technical solution, the centerline identification module 104 is specifically used for:

[0186] The mask image of the orthopedic consumable to be identified is processed into grayscale to obtain a grayscale mask image;

[0187] The grayscale mask image is binarized to obtain a binary mask image;

[0188] Starting from the edge of the binary mask, the pixels at the edge of the target object are gradually removed inward through an erosion operation;

[0189] The dilation operation recovers some of the pixels removed during the erosion operation;

[0190] The erosion and dilation operations are performed iteratively until the orthopedic consumable to be identified is simplified to a skeleton of a single pixel width.

[0191] The central axis is extracted from the skeleton with a width of one pixel.

[0192] As a preferred technical solution, the orthopedic consumable specification identification module 105 is specifically used for:

[0193] Determine the intersection point of the two ends of the mask image of the orthopedic consumable to be identified;

[0194] The length of the orthopedic consumable to be identified is obtained by calculating the distance between the two intersection points.

[0195] Draw a perpendicular line on the central axis;

[0196] Sort the distances between the vertical line and the boundary of the mask image of the orthopedic consumable to be identified in descending order;

[0197] The distance ranked first is taken as the diameter of the orthopedic consumable to be identified;

[0198] Calculate the first difference between the length of the orthopedic consumable to be identified and the length of each specification in the preset orthopedic consumable specification library;

[0199] Calculate the second difference between the diameter of the orthopedic consumable to be identified and the diameter of each specification in the preset orthopedic consumable specification library;

[0200] The absolute values ​​of the first difference and the second difference of the orthopedic consumable to be identified are summed to obtain the comprehensive difference between the orthopedic consumable to be identified and each specification in the preset orthopedic consumable specification library.

[0201] Sort the combined differences in ascending order;

[0202] In the preset orthopedic consumables specification library, the specification with the highest comprehensive difference ranking is selected as the final specification of the orthopedic consumable to be identified.

[0203] It should be noted that the orthopedic consumable identification system and the orthopedic consumable identification method of this application correspond one-to-one. The technical features and beneficial effects described in the embodiments of the orthopedic consumable identification method described above are also applicable to the embodiments of the orthopedic consumable identification system. For details, please refer to the description in the embodiments of the method of this application. It will not be repeated here.

[0204] Furthermore, in the above embodiment of the orthopedic consumable identification system, the logical division of each program module is only an example. In actual applications, the above functions can be assigned to different program modules as needed, for example, for the sake of corresponding hardware configuration requirements or software implementation convenience. That is, the internal structure of the orthopedic consumable identification system is divided into different program modules to complete all or part of the functions described above.

[0205] In another embodiment, an electronic device for implementing an orthopedic consumable identification method is provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; when the processor executes the computer program, it implements an orthopedic consumable identification method according to any embodiment of this application.

[0206] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete this application. The one or more module units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the device.

[0207] The device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The device may include, but is not limited to, a processor and memory.

[0208] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the device, connecting various parts of the device via various interfaces and lines.

[0209] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc. In addition, the memory may include high-speed random access memory and non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0210] Accordingly, this application also provides a computer-readable storage medium, which includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform an orthopedic consumable identification method as described in any of the above embodiments.

[0211] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0212] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0213] The above embodiments are preferred embodiments of this application, but the implementation of this application is not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of this application shall be considered equivalent substitutions and shall be included within the protection scope of this application.

Claims

1. A method for identifying orthopedic consumables, characterized in that, Includes the following steps: The images of orthopedic consumables to be identified are labeled to obtain tagged images of orthopedic consumables to be identified; Target detection is performed on the tagged image of the orthopedic consumable to be identified in order to identify the target location of the orthopedic consumable; The image of the tagged orthopedic consumable to be identified is segmented according to the target location to obtain a mask image of the orthopedic consumable to be identified. Based on the mask image of the orthopedic consumable to be identified, the skeleton algorithm is used to identify the central axis of the orthopedic consumable to be identified; Specifically, the mask image of the orthopedic consumable to be identified is processed into grayscale to obtain a grayscale mask image; the grayscale mask image is binarized to obtain a binary mask image; starting from the edge of the binary mask image, pixels at the edge of the target object are gradually removed inward through an erosion operation; some pixels removed in the erosion operation are recovered through a dilation operation; the erosion and dilation operations are iteratively executed until the orthopedic consumable to be identified is simplified to a skeleton of one pixel width; the central axis is extracted from the skeleton of one pixel width. Based on the central axis, the specifications of the orthopedic consumable to be identified are obtained; specifically, the intersection points of the two ends of the central axis on the mask image of the orthopedic consumable to be identified are determined. Calculate the distance between the two intersection points to obtain the length of the orthopedic consumable to be identified; draw a perpendicular line on the central axis; sort the distances between the perpendicular line and the boundary of the mask image of the orthopedic consumable to be identified in descending order; take the distance ranked first as the diameter of the orthopedic consumable to be identified; Calculate the first difference between the length of the orthopedic consumable to be identified and the length of each specification in the preset orthopedic consumable specification library; calculate the second difference between the diameter of the orthopedic consumable to be identified and the diameter of each specification in the preset orthopedic consumable specification library; sum the absolute values ​​of the first difference and the second difference of the orthopedic consumable to be identified to obtain the comprehensive difference between the orthopedic consumable to be identified and each specification in the preset orthopedic consumable specification library; Sort the combined differences in ascending order; In the preset orthopedic consumables specification library, the specification with the highest comprehensive difference ranking is selected as the final specification of the orthopedic consumable to be identified.

2. The orthopedic consumable identification method according to claim 1, characterized in that, Before performing target detection on the tagged orthopedic consumable image to be identified, the method further includes performing random image enhancement processing on the orthopedic consumable image to be identified. The random image enhancement process includes randomly scaling the image, randomly cropping the image, randomly flipping the image, randomly rotating the image, and randomly adjusting the image's brightness, contrast, saturation, and chroma.

3. The orthopedic consumable identification method according to claim 2, characterized in that, Before performing target detection on the tagged orthopedic consumable image to be identified, the method further includes processing the tagged orthopedic consumable image to be identified into a preset pixel size and scaling the pixel values ​​to a preset range.

4. The orthopedic consumable identification method according to claim 3, characterized in that, The preset pixel size includes 416x416 or 640x640 pixels; The preset range is [0,1].

5. The method for identifying orthopedic consumables according to claim 1, characterized in that, The YOLOv8 object detection model is used to perform object detection on the labeled orthopedic consumable images to identify the category and location of the orthopedic consumables, including: Features are extracted from the labeled images of orthopedic consumables to be identified, resulting in a high-dimensional feature map that includes semantic information at different levels. The high-dimensional feature maps of the different levels of semantic information are fused to obtain a fused feature map. Based on the fused feature map, each potential target is predicted, and the target location, confidence level, and class probability are obtained; wherein, the target location is represented in the form of a rectangular box.

6. The method for identifying orthopedic consumables according to claim 5, characterized in that, Also includes: Non-maximum suppression is applied to the rectangular boxes to remove those with an overlap exceeding a preset overlap threshold.

7. The orthopedic consumable identification method according to claim 5, characterized in that, The step of segmenting the labeled orthopedic consumable image according to the target location to obtain a mask image of the orthopedic consumable includes: Features of the orthopedic consumables to be identified within the rectangular frame are extracted to obtain orthopedic consumables features at different scales; The features of orthopedic consumables at different scales are fused to obtain a fused orthopedic consumable feature map; Based on the fused orthopedic consumable feature map, a mask map of the orthopedic consumable to be identified is predicted; wherein, each pixel of the mask map of the orthopedic consumable to be identified is assigned a category label.

8. The method for identifying orthopedic consumables according to claim 7, characterized in that, It also includes inputting the mask image of the orthopedic consumable to be identified into a preset neural network for further segmentation.

9. The method for identifying orthopedic consumables according to claim 1, characterized in that, The binarization process involves dividing the pixel values ​​in the grayscale mask into pixel values ​​for the target object and pixel values ​​for the background, in order to highlight the outline and shape of the target object.

10. An orthopedic consumable identification system, characterized in that, A method for identifying orthopedic consumables according to any one of claims 1-9 includes a labeling module, a target detection module, a segmentation module, a central axis identification module, and an orthopedic consumables specification identification module; The annotation module is used to annotate the orthopedic consumable images to be identified, so as to obtain orthopedic consumable images with labels. The target detection module is used to perform target detection on the tagged image of the orthopedic consumable to be identified, so as to identify the target location of the orthopedic consumable to be identified. The segmentation module is used to segment the image of the labeled orthopedic consumable to be identified according to the target location to obtain a mask image of the orthopedic consumable to be identified. The central axis identification module is used to identify the central axis of the orthopedic consumable to be identified based on the mask image of the orthopedic consumable to be identified, using a skeleton algorithm. Specifically, the mask image of the orthopedic consumable to be identified is processed into grayscale to obtain a grayscale mask image; the grayscale mask image is binarized to obtain a binary mask image; starting from the edge of the binary mask image, pixels at the edge of the target object are gradually removed inward through an erosion operation; some pixels removed in the erosion operation are recovered through a dilation operation; the erosion and dilation operations are iteratively executed until the orthopedic consumable to be identified is simplified to a skeleton of one pixel width; the central axis is extracted from the skeleton of one pixel width. The orthopedic consumable specification identification module is used to identify the specifications of the orthopedic consumable to be identified based on the central axis; specifically, it determines the intersection points of the two ends of the central axis on the mask image of the orthopedic consumable to be identified. Calculate the distance between the two intersection points to obtain the length of the orthopedic consumable to be identified; draw a perpendicular line on the central axis; sort the distances between the perpendicular line and the boundary of the mask image of the orthopedic consumable to be identified in descending order; take the distance ranked first as the diameter of the orthopedic consumable to be identified; Calculate the first difference between the length of the orthopedic consumable to be identified and the length of each specification in the preset orthopedic consumable specification library; calculate the second difference between the diameter of the orthopedic consumable to be identified and the diameter of each specification in the preset orthopedic consumable specification library; sum the absolute values ​​of the first difference and the second difference of the orthopedic consumable to be identified to obtain the comprehensive difference between the orthopedic consumable to be identified and each specification in the preset orthopedic consumable specification library; Sort the combined differences in ascending order; In the preset orthopedic consumables specification library, the specification with the highest comprehensive difference ranking is selected as the final specification of the orthopedic consumable to be identified.

11. The orthopedic consumable identification system according to claim 10, characterized in that, It also includes an enhanced processing module; The enhancement processing module is used to perform random image enhancement processing on the orthopedic consumable image to be identified before performing target detection on the tagged orthopedic consumable image to be identified. The random image enhancement process includes randomly scaling the image, randomly cropping the image, randomly flipping the image, randomly rotating the image, and randomly adjusting the image's brightness, contrast, saturation, and chroma.

12. The orthopedic consumable identification system according to claim 10, characterized in that, It also includes a pixel processing module; The pixel processing module is used to process the labeled orthopedic consumable image to a preset pixel size and scale the pixel values ​​to a preset range before performing target detection on the image of the orthopedic consumable to be identified.

13. The orthopedic consumable identification system according to claim 10, characterized in that, The target detection module is specifically used for: The YOLOv8 object detection model is used to perform object detection on the labeled orthopedic consumable images to identify the category and location of the orthopedic consumables, including: Features are extracted from the labeled images of orthopedic consumables to be identified, resulting in a high-dimensional feature map that includes semantic information at different levels. The high-dimensional feature maps of the different levels of semantic information are fused to obtain a fused feature map. Based on the fused feature map, each potential target is predicted, and the target location, confidence level, and class probability are obtained; wherein, the target location is represented in the form of a rectangular box.

14. The orthopedic consumable identification system according to claim 13, characterized in that, The segmentation module is specifically used for: Features of the orthopedic consumables to be identified within the rectangular frame are extracted to obtain orthopedic consumables features at different scales; The features of orthopedic consumables at different scales are fused to obtain a fused orthopedic consumable feature map; Based on the fused orthopedic consumable feature map, a mask map of the orthopedic consumable to be identified is predicted; wherein, each pixel of the mask map of the orthopedic consumable to be identified is assigned a category label.

15. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores computer program instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform an orthopedic consumable identification method as described in any one of claims 1-9.

16. A computer-readable storage medium storing a program, characterized in that, When the program is executed by the processor, it implements the orthopedic consumable identification method according to any one of claims 1-9.

Images