Abnormal cell detection method and device, computer equipment and storage medium
By performing chromaticity processing and edge feature extraction of deep learning models on endoscopic cell images, combined with similarity comparison methods, the detection error of abnormal cells caused by uneven staining in endoscopic images is solved, and high accuracy is achieved abnormal cell detection.
Patent Information
- Application Number
- CN202411454619.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-17
- Publication Date
- 2025-02-07
AI Technical Summary
During the detection of abnormal cells, the images collected by the endoscopy are prone to uneven staining interference, which makes it impossible to accurately analyze the cell state of the uneven staining area, and thus cannot accurately detect abnormal cells in the uneven staining area.
By chromaticity processing on the endoscopic cell images, the endoscopic cell images after chromaticity processing were obtained, and edge features were extracted through a pre-constructed deep learning model to localize the cells. Then, the edge characteristics of each cell in the endoscopic cell image after chroma treatment were compared with the standard cell characteristics, and the cells with similarity less than the preset threshold were determined to be abnormal cells.
The detection of abnormal cells in uneven staining areas is achieved, which improves the accuracy of cell detection and avoids detection errors caused by uneven staining.
Smart Images
Figure CN119399758A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, and in particular to an abnormal cell detection method, device, computer equipment and storage medium. Background Art
[0002] An endoscope is a medical device that is mainly used to examine the internal organs and tissues of the human body. With the development of medical technology, endoscopes have gradually become an important tool in the fields of medicine and industry. Endoscopes can help staff observe areas that cannot be directly observed, thereby improving the staff's diagnostic efficiency and accuracy. For example, endoscopes can be used to detect abnormal cells. Abnormal cells refer to cell components that are different from normal cells in size, shape, etc.
[0003] During the abnormal cell detection process, since the target area needs to be sprayed with dye before using the endoscope, it is easy to cause uneven staining interference in the images collected by the endoscope, resulting in the inability to accurately analyze the cell status in the unevenly stained area, and therefore the inability to accurately detect abnormal cells in the unevenly stained area. Summary of the invention
[0004] Based on this, it is necessary to provide an abnormal cell detection method, device, computer equipment and storage medium that can accurately detect abnormal cells in unevenly stained areas in response to the above technical problems.
[0005] In a first aspect, the present application provides a method for detecting abnormal cells, comprising:
[0006] Performing colorimetric processing on the endoscopic cell image to obtain a colorimetrically processed endoscopic cell image; the endoscopic cell image is a fluorescent cell image;
[0007] Extract edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locate cells in the chromaticity-processed endoscopic cell image based on the edge features;
[0008] The edge features of each cell in the chromaticity-processed endoscopic cell image are compared with the standard cell features for similarity, and cells with similarity less than a preset threshold are identified as abnormal cells.
[0009] In one embodiment, performing chromaticity processing on the endoscopic cell image to obtain the chromaticity processed endoscopic cell image includes:
[0010] converting the endoscopic cell image and the preset cell image into dye matrices respectively;
[0011] The dye matrix corresponding to the endoscopic cell image is registered with the dye matrix corresponding to the preset cell image to obtain the endoscopic cell image after chromaticity processing.
[0012] In one of the embodiments, the pre-built deep learning model includes an object detection subnetwork and an enhancement module;
[0013] The pre-built deep learning model is used to extract the target edge features corresponding to the colorimetrically processed endoscopic cell image, including:
[0014] The object detection sub-network is used to extract features from the chromaticity-processed endoscopic cell image to obtain the original feature map;
[0015] The original feature map is enhanced by the enhancement module to obtain an enhanced feature map;
[0016] The edge features in the enhanced feature map are extracted through the object detection sub-network.
[0017] In one embodiment, the target detection subnetwork is determined as follows:
[0018] The residual network in the Mask R-CNN network is replaced with a lightweight network to obtain the object detection subnetwork.
[0019] In one embodiment, the target detection subnetwork is determined as follows:
[0020] Get the channel factor of each network channel in the lightweight network;
[0021] The network channels whose channel factors are smaller than the preset threshold are regarded as the channels to be pruned;
[0022] The channels to be cropped in the lightweight network are cropped, and the residual network in the Mask R-CNN network is replaced with the cropped lightweight network to obtain the object detection subnetwork.
[0023] In one embodiment, the method further comprises:
[0024] The deep features corresponding to the chromaticity-processed endoscopic cell images are extracted through a pre-built deep learning model; the deep features include texture features and morphological features;
[0025] The depth features are fused with the edge features, and the fused features are compared with the standard cell features for similarity.
[0026] In one embodiment, the method further comprises:
[0027] Endoscopic cytological images are obtained through the endoscope handle of the endoscope; the endoscope handle includes:
[0028] Lens module;
[0029] An optical fiber pressing plate, including a pressing plate groove body, is fixed to the outer wall of the lens module;
[0030] A lighting module including a fiber optic cable and a fiber optic connector;
[0031] Among them, the optical fiber cable is arranged inside the endoscope handle, passes through the pressure plate groove and is connected to one end of the optical fiber connector and extends to the other end; the other end of the optical fiber connector is fixedly connected to the lens module; the optical fiber cable and the optical fiber connector are used to provide incident light to the lens module so that the lens module generates an endoscopic cell image.
[0032] In a second aspect, the present application also provides an abnormal cell detection device, comprising:
[0033] A chromaticity processing module is used to perform chromaticity processing on the endoscopic cell image to obtain the chromaticity processed endoscopic cell image; the endoscopic cell image is a fluorescent image;
[0034] An edge extraction module, used to extract edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locate cells in the chromaticity-processed endoscopic cell image according to the edge features;
[0035] The feature comparison module is used to compare the edge features of each cell in the chromaticity-processed endoscopic cell image with the standard cell features, and determine the cells with similarity less than a preset threshold as abnormal cells.
[0036] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0037] Performing colorimetric processing on the endoscopic cell image to obtain a colorimetrically processed endoscopic cell image; the endoscopic cell image is a fluorescent cell image;
[0038] Extract edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locate cells in the chromaticity-processed endoscopic cell image based on the edge features;
[0039] The edge features of each cell in the chromaticity-processed endoscopic cell image are compared with the standard cell features for similarity, and cells with similarity less than a preset threshold are identified as abnormal cells.
[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:
[0041] Performing colorimetric processing on the endoscopic cell image to obtain a colorimetrically processed endoscopic cell image; the endoscopic cell image is a fluorescent cell image;
[0042] Extract edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locate cells in the chromaticity-processed endoscopic cell image based on the edge features;
[0043] The edge features of each cell in the chromaticity-processed endoscopic cell image are compared with the standard cell features for similarity, and cells with similarity less than a preset threshold are identified as abnormal cells.
[0044] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0045] Performing colorimetric processing on the endoscopic cell image to obtain a colorimetrically processed endoscopic cell image; the endoscopic cell image is a fluorescent cell image;
[0046] Extract edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locate cells in the chromaticity-processed endoscopic cell image based on the edge features;
[0047] The edge features of each cell in the chromaticity-processed endoscopic cell image are compared with the standard cell features for similarity, and cells with similarity less than a preset threshold are identified as abnormal cells.
[0048] The above-mentioned abnormal cell detection method, device, computer equipment, storage medium and computer program product can convert unevenly stained cell images into evenly stained cell images by performing colorimetric processing on endoscopic cell images, thereby avoiding the problem of inability to accurately detect abnormal cells due to uneven staining. The edge features corresponding to the chromaticity-processed endoscopic cell images are extracted through a deep learning model to locate the cells, and the boundaries between different cells can be accurately distinguished through the edge features. In addition, the edge features of each cell in the chromaticity-processed endoscopic cell image are compared with the standard cell features for similarity, so that abnormal cells can be detected according to the definition and characteristics of abnormal cells, thereby improving the accuracy of cell detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0050] FIG1 is a schematic diagram of a process for detecting abnormal cells in one embodiment;
[0051] FIG2 is a schematic diagram of a process of performing chromaticity processing on an endoscopic cell image to obtain a chromaticity-processed endoscopic cell image in one embodiment;
[0052] FIG3 is a schematic diagram of a process for extracting target edge features corresponding to an endoscopic cell image after chromaticity processing by using a pre-built deep learning model in one embodiment;
[0053] FIG4 is a block diagram of a structure of an abnormal cell detection device in one embodiment;
[0054] FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0056] In one embodiment, as shown in FIG. 1 , a method for detecting abnormal cells is provided. This embodiment is illustrated by applying the method to an endoscope. In this embodiment, the method includes the following steps:
[0057] Step 102, performing chromaticity processing on the endoscopic cell image to obtain a chromaticity processed endoscopic cell image; the endoscopic cell image is a fluorescent cell image.
[0058] The endoscopic cell image refers to the cell image of the region of interest collected by the endoscope. The endoscopic cell image is a fluorescent cell image. The fluorescent cell image refers to the cell image generated by irradiating the stained cells with an excitation light source when the cells are stained.
[0059] Specifically, the endoscope includes an endoscope handle and an image processing mechanism. The endoscope is inserted into the inspection cavity of the target object through the endoscope handle to find the region of interest of the target object. The target object refers to the target human body that needs to be biopsied. The region of interest can be a lesion site, for example, the region of interest is the brain. Abnormal cells in the brain are tumor cells, specifically atypical cells of brain media tumors. After the endoscope is positioned at the region of interest, the spraying device sprays the dye to the region of interest through the channel of the endoscope. After the dyeing is completed, the endoscope obtains the endoscopic cell image of the region of interest of the target object, and transmits the obtained endoscopic cell image to the image processing mechanism. The image processing mechanism is installed with image processing software, and the image processing software is used to locate and detect abnormal cells in the endoscopic cell image.
[0060] Since the endoscopic cell image obtained by the endoscope may have uneven dyeing, the endoscopic cell image can be subjected to colorimetric processing by image processing software to obtain the endoscopic cell image after colorimetric processing. Furthermore, the colorimetric processing method can be: obtaining a preset cell image, which refers to a cell image with uniform dyeing. The endoscopic cell image and the preset cell image are respectively converted into dye matrices. The dye matrix refers to a matrix subjected to colorimetric normalization processing. The dye matrix corresponding to the endoscopic cell image is aligned with the dye matrix corresponding to the preset cell image, thereby converting the endoscopic cell image into a cell image with uniform dyeing.
[0061] Step 104: extract edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locate cells in the chromaticity-processed endoscopic cell image according to the edge features.
[0062] A pre-built deep learning model is stored in the image processing software. The deep learning model is trained by a large number of cell images annotated with cell positions and cell annotation boxes. In the endoscopic field of view, not all areas of an endoscopic cell image are abnormal cells or normal cells, especially at the edge of abnormal cells, where normal cells and abnormal cells often coexist. Therefore, in order to accurately determine the boundary between normal cells and abnormal cells, it can be achieved by identifying the boundaries of all cells. After obtaining the chromaticity-processed endoscopic cell image, the pre-built deep learning model is called to extract edge features of the chromaticity-processed endoscopic cell image. Edge features are used to characterize the boundaries, size, morphology, etc. of cells in the image.
[0063] The position and cell boundaries of each cell in the chromatically processed endoscopic cell image are determined based on edge features through a deep learning model.
[0064] Step 106 , the edge features of each cell in the chromaticity-processed endoscopic cell image are compared with the standard cell features for similarity, and cells with similarity less than a preset threshold are determined as abnormal cells.
[0065] After locating each cell in the chromaticity-processed endoscopic cell image, the cell features of normal cells can be obtained as standard cell features. Standard cell features include edge features of normal cells. The edge features of each cell are compared with the edge features of normal cells for similarity. When the similarity is less than a preset threshold, it indicates that the cell is an abnormal cell. When the similarity is greater than or equal to the preset threshold, it indicates that the cell is a normal cell.
[0066] Optionally, the method of comparing the edge features of each cell in the chromaticity-processed endoscopic cell image with the standard cell features can use distance measurement methods such as Euclidean distance, cosine similarity, and Hamming distance, or nonlinear feature comparison methods such as kernel methods and manifold learning can be used to better capture the nonlinear relationship between data.
[0067] In the above abnormal cell detection method, by performing colorimetric processing on the endoscopic cell image, the unevenly stained cell image can be converted into an evenly stained cell image, thereby avoiding the problem of inability to accurately detect abnormal cells due to uneven staining. The edge features corresponding to the colorimetrically processed endoscopic cell image are extracted through a deep learning model to locate the cells, and the boundaries between different cells can be accurately distinguished through the edge features. In addition, the edge features of each cell in the colorimetrically processed endoscopic cell image are compared with the standard cell features for similarity, so that abnormal cells can be detected according to the definition and features of abnormal cells, thereby improving the accuracy of cell detection.
[0068] In an exemplary embodiment, as shown in FIG2 , performing chromaticity processing on an endoscopic cell image to obtain a chromaticity processed endoscopic cell image includes:
[0069] Step 202: Convert the endoscopic cell image and the preset cell image into dye matrices respectively.
[0070] Step 204 , aligning the dye matrix corresponding to the endoscopic cell image with the dye matrix corresponding to the preset cell image to obtain the endoscopic cell image after colorimetric processing.
[0071] Specifically, a preset cell image is obtained, and the preset cell image refers to a cell image with uniform dyeing. The chromaticity of the endoscopic cell image needs to be converted into the chromaticity corresponding to the preset cell image. The endoscopic cell image and the preset cell image are converted into the optical density of each image respectively, and then the optical density of each image is decomposed by a non-negative matrix to obtain two dye matrices. The two dye matrices include a color appearance matrix and a dye density matrix.
[0072] The endoscopic cell image is converted into a dye matrix according to the following formula:
[0073] (1);
[0074] V1=W1H1(2).
[0075] Among them, I1 represents the endoscopic cell image, I0 represents the incident light intensity of the endoscopic cell image, V1 represents the optical density of the endoscopic cell image, W1 represents the color appearance matrix corresponding to the endoscopic cell image, and H1 represents the staining density matrix corresponding to the endoscopic cell image.
[0076] The endoscopic cell image is converted into a dye matrix according to the following formula:
[0077] (3);
[0078] V2=W2H2(4).
[0079] Among them, I1' represents the preset cell image, I0' represents the incident light intensity of the preset cell image, V2 represents the optical density of the preset cell image, W2 represents the color appearance matrix corresponding to the preset cell image, and H2 represents the staining density matrix corresponding to the preset cell image.
[0080] The endoscopic cell image can be registered by aligning the staining density matrix of the endoscopic cell image with the staining density matrix of the preset cell image based on the structure-preserving color migration algorithm to obtain the registered staining density matrix of the endoscopic cell image. The staining density matrix of the endoscopic cell image and the staining density matrix of the preset cell image can be registered using the following formula:
[0081] (5).
[0082] in, is the staining density matrix after endoscopic cell image registration, is the staining density matrix before endoscopic cell image registration, is the staining density matrix before preset cell image registration, j is the r staining agent index, and RM(·) is used to calculate the robust pseudo maximum value of each row vector at 99%.
[0083] The staining density matrix of the registered endoscopic cell image is multiplied by the color appearance matrix of the preset cell image before registration to obtain the endoscopic cell image after chromaticity processing, which can be specifically described in the following formula:
[0084] (6).
[0085] in, is the endoscopic cell image after chromaticity processing, W2 is the color appearance matrix of the preset cell image before registration, Staining density matrix after registration of endoscopic cell images.
[0086] In this embodiment, by converting the endoscopic cell image and the preset cell image into dye matrices respectively, and aligning the dye matrix corresponding to the endoscopic cell image with the dye matrix corresponding to the preset cell image, the chromaticity of the endoscopic cell image is converted into the chromaticity corresponding to the preset cell image, and the unevenly stained endoscopic cell image can be chromatically normalized, so that the color information distribution of the endoscopic cell image is kept as consistent as possible, which is beneficial to improving the target detection accuracy of the subsequent model.
[0087] In an exemplary embodiment, as shown in FIG3 , the pre-built deep learning model includes a target detection subnetwork and an enhancement module; extracting target edge features corresponding to the chromaticity-processed endoscopic cell image through the pre-built deep learning model includes:
[0088] Step 302: extract features from the chromaticity-processed endoscopic cell image through the target detection subnetwork to obtain an original feature map.
[0089] Step 304: Perform channel and pixel enhancement on the original feature map through an enhancement module to obtain an enhanced feature map.
[0090] Step 306: extract edge features in the enhanced feature map through the object detection sub-network.
[0091] Specifically, the pre-built deep learning model includes a target detection subnetwork and an enhancement module. The target detection subnetwork can be Mask R-CNN (Mask Region-based Convolutional Neural Network). The enhancement module can be an attention module or an Enhance-Block module. The target detection subnetwork includes Resnet (Residual Network), FPN (Feature Pyramid Networks), and RPN (Region Proposal Network).
[0092] The chromaticity-processed endoscopic cell image is input into the target detection subnetwork in the pre-built deep learning model. The Resnet network and FPN network in the target detection subnetwork are used to extract the features of the chromaticity-processed endoscopic cell image to obtain the original feature map. The original feature map is input into the enhancement module, and the original feature map is enhanced by the enhancement module. The enhanced feature map is then sent to the RPN network to obtain the edge features in the enhanced feature map.
[0093] Furthermore, the method of enhancing the pixels of the original feature map by the enhancement module includes: performing global average pooling on each channel of the original feature map to obtain the pooling mean corresponding to each channel, thereby obtaining a first vector. The first vector is mapped to the (0,1) interval using a sigmoid function after passing through two fully connected layers to obtain multiple channel mapping values, each of which corresponds to a channel. The pixel points of each channel are multiplied by the channel mapping value of each channel to obtain an intermediate feature map.
[0094] For each pixel in the intermediate feature map, calculate the mean of all channel mapping values of each pixel to obtain the channel mean corresponding to each pixel. The channel mean of all pixels in the intermediate feature map forms the second vector. After the second vector is expanded and sent to the two-layer full connection, it is mapped to the (0,1) interval using the sigmoid function to obtain multiple pixel mapping values, each of which corresponds to a pixel position. The pixel mapping value of each pixel is multiplied by the corresponding pixel of the intermediate feature map according to the position correspondence to obtain the enhanced feature map.
[0095] In this embodiment, the pixel points of the original feature map are enhanced by the enhancement module to enhance the spatial information, which is beneficial to the regression of the bounding box and thus to the extraction of edge features.
[0096] In an exemplary embodiment, the target detection subnetwork is determined by replacing the residual network in the Mask R-CNN network with a lightweight network to obtain the target detection subnetwork.
[0097] Since the network structure of the residual network in the Mask R-CNN network is relatively complex, the residual network can be replaced by a lightweight network.
[0098] In this embodiment, the residual network in the Mask R-CNN network is replaced with a lightweight network, which can reduce calculation parameters, reduce the amount of calculation, and improve the inference time, and is more suitable for scenarios with limited storage space and power consumption.
[0099] In an exemplary embodiment, the target detection subnetwork is determined in the following manner: obtaining the channel factor of each network channel in the lightweight network; taking the network channel whose channel factor is less than a preset threshold as the channel to be cropped; cropping the channel to be cropped in the lightweight network, replacing the residual network in the Mask R-CNN network with the lightweight network after the cropping process, and obtaining the target detection subnetwork.
[0100] Among them, the channel factor of each network channel can be a scale factor of each network channel, which is a dynamically changing weight used to indicate the importance of the network channel corresponding to the scale factor to the network output. The lightweight network includes a starting part, a middle part and a final part, each of which includes multiple network channels. Each network channel is used for feature extraction.
[0101] Specifically, the original neural network is obtained. The original neural network is a traditional lightweight network and does not introduce a scaling factor. A scaling factor is introduced for each network channel of the original neural network. For example, the initial value of the introduced scaling factor can be 0.6. A loss function containing the scaling factor of each network channel is obtained, and the loss function is trained by multiple back propagation. When the number of training iterations reaches a preset number or the loss value of the loss function no longer decreases, the network training is stopped to obtain a lightweight network. Since the scaling factor contained in the loss function will also change dynamically during the network training process, when the network training stops, the scaling factor of each network channel in the lightweight network can be obtained.
[0102] Compare the scaling factor with the preset threshold to determine the network channel whose scaling factor is less than the preset threshold. The preset threshold can be a value close to zero. If the scaling factor of a channel is less than the preset threshold, it means that the channel is less important to the network output, the feature map output by the channel can be ignored, and pruning the channel will not affect the network performance. The network channel whose scaling factor is less than the preset threshold is regarded as the channel to be pruned, and pruned, so as to obtain a lightweight network after pruning.
[0103] Then, the pruned lightweight network is used to replace the residual network in the Mask R-CNN network to obtain the target detection subnetwork. By pruning unimportant network channels and reducing the number of network channels, the computational complexity of target detection can be reduced.
[0104] In this embodiment, by further lightweighting the lightweight network, the model complexity can be further reduced, thereby greatly improving the model reasoning speed.
[0105] In an exemplary embodiment, the method also includes: extracting depth features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model; the depth features include texture features and morphological features; fusing the depth features with edge features, and comparing the fused features with standard cell features for similarity.
[0106] The pre-built deep learning model can also extract the depth features corresponding to the endoscopic cell images after colorimetric processing. Deep features include texture features and morphological features, which are used to characterize and identify cell structure and morphology. Using dimensionality reduction techniques, such as principal component analysis, to map the deep features and edge features to a unified space and fuse the mapped features, can reduce feature dimensions, remove redundant information, and improve the efficiency of the deep learning model. Edge features characterize the size and morphology of cells, while deep features can characterize both the morphology and structure of cells. The fused features are compared with the standard cell features for similarity, and multiple features such as cell size, morphology, and structure are compared, which can further accurately distinguish normal cells from abnormal cells.
[0107] Furthermore, the depth features and edge features may be weightedly fused to obtain fused features.
[0108] In this embodiment, the depth features are fused with the edge features, and the fused features are compared with the standard cell features for similarity, so as to achieve comparison of multiple features such as cell size, morphology, structure, etc., which can further accurately distinguish normal cells from abnormal cells.
[0109] In an exemplary embodiment, the method also includes: acquiring an endoscopic cell image through an endoscope handle of the endoscope; the endoscope handle includes: a lens module; an optical fiber pressure plate, including a pressure plate groove, fixed to the outer wall of the lens module; an illumination module, including an optical fiber cable and an optical fiber connector; wherein the optical fiber cable is arranged inside the endoscope handle, passes through the pressure plate groove, is connected to one end of the optical fiber connector and extends to the other end; the other end of the optical fiber connector is fixedly connected to the lens module; the optical fiber cable and the optical fiber connector are used to provide incident light to the lens module so that the lens module generates an endoscopic cell image.
[0110] Specifically, the endoscope can also generate endoscopic cell images through the endoscope handle. The optical fiber cable is arranged inside the handle, and the optical fiber cable enters the handle from the tail of the handle, passes through the pressing plate groove of the optical fiber pressing plate, and is connected to one end of the optical fiber connector to guide the light emitted by the light source into the lens module. The middle end of the optical fiber pressing plate is a pressing plate groove, and both sides of the optical fiber pressing plate are fixedly connected to the lens module.
[0111] The optical fiber cable passes through the interior of the optical fiber connector and comes out from the other end. The interior of the optical fiber connector is set as a multi-corner cavity, which can bend the optical fiber cable 90 degrees at a small angle and multiple times, so that the optical fiber cable can guide the light emitted by the light source into the lens module. The other end of the optical fiber connector is connected to the lens module. After the optical fiber cable is bent 90 degrees in the optical fiber connector, the illumination light emitted by the transmitted light source is also bent 90 degrees and enters the lens module to provide incident light for the endoscope to generate endoscopic cell images.
[0112] In this embodiment, by setting a fiber optic pressure plate, the routing position of the fiber optic cable is limited, which prevents the fiber optic cable from shaking inside the handle, affecting the transmission and incident angle of light, and improving the stability of the lighting function of the endoscope handle. The fiber optic connector uses the multi-corner cavity inside it to bend the optical fiber to 90 degrees without loss, which solves the light loss caused by long-term large-angle bending of the optical fiber cable and avoids damage to the optical fiber caused by the inner wall corner. The multi-corner cavity can effectively alleviate the angle and reduce light loss. By arranging the lens module and the lighting module as a whole, the overall volume of the endoscope handle is reduced, the orderliness of the internal arrangement of the endoscope handle is improved, and the positional relationship of the optical fiber cable inside the endoscope handle is optimized, which improves the convenience of using the endoscope and the stability of its function.
[0113] Furthermore, the endoscope handle also includes a shell, which includes a handle middle shell and a handle rear shell; a fixing part is arranged on the inner wall of the handle middle shell, and the fixing part includes a fixing groove, a first screw hole of the fixing part and a second screw hole of the fixing part; the fixing groove is used to fix the circuit module; the handle rear shell includes a first screw hole of the rear shell, and the first screw hole of the rear shell and the second screw hole of the fixing part are fixedly connected by a first screw, the handle middle shell abuts against the handle rear shell, and the nut of the first screw abuts against the handle rear shell.
[0114] A fixing piece is disposed on the inner wall of the handle middle shell, and the fixing piece is disposed on the inner wall of the second end of the handle middle shell. The fixing piece includes a first fixing piece and a second fixing piece, and the first fixing piece and the second fixing piece are respectively located on both sides of the second end of the handle middle shell. Exemplarily, the first fixing piece includes a fixing groove, a first screw hole of the fixing piece, and a second screw hole of the fixing piece. The two ends of the circuit board in the circuit module are respectively connected to the fixing grooves in the first fixing piece and the second fixing piece, and the circuit module is fixed in the handle middle shell, so that the circuit module is fixed in the middle, and space is left at the upper and lower ends of the handle middle shell.
[0115] The handle rear shell includes a rear shell first screw hole, and the handle middle shell and the handle rear shell are abutted by the rear shell first screw hole. Exemplarily, the second screw hole of the first fixing member is fixedly connected to the first screw hole of the rear shell by a first screw, the handle middle shell abuts against the handle rear shell, the nut of the first screw abuts against the handle rear shell, and the second fixing member fixes the handle middle shell and the handle rear shell in the same way.
[0116] The endoscope handle shell also includes a handle front shell and a handle sheath. The second end of the handle front shell abuts against the first end of the handle middle shell, the first end of the handle front shell is connected to the scope sheath, and a lens module is arranged in the handle front shell; the handle sheath is connected to the handle rear shell, and is used to gather the optical fiber cable, electrical signal cable and ground wire into the endoscope handle.
[0117] In this embodiment, a fixing piece is provided in the handle middle shell to fix the circuit module in the middle, so that there is space between the upper and lower parts of the handle middle shell, which provides reserved space for the optical fiber cable to be routed inside the handle, avoiding direct contact between the optical fiber cable and the circuit module, which affects the transmission of light. The optical fiber cable, the electrical signal cable and the grounding wire are bundled into the handle through the handle sheath, which further limits the routing of the optical fiber cable inside the handle, effectively ensuring the stability of the internal structure of the handle and the transmission quality of light.
[0118] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0119] Based on the same inventive concept, the embodiment of the present application also provides an abnormal cell detection device for implementing the abnormal cell detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more abnormal cell detection device embodiments provided below can refer to the limitations of the abnormal cell detection method above, and will not be repeated here.
[0120] In an exemplary embodiment, as shown in FIG4 , an abnormal cell detection device is provided, comprising: a chromaticity processing module 402, an edge extraction module 404 and a feature comparison module 406, wherein:
[0121] The chromaticity processing module 402 is used to perform chromaticity processing on the endoscopic cell image to obtain the endoscopic cell image after chromaticity processing; the endoscopic cell image is a fluorescent image.
[0122] The edge extraction module 404 is used to extract edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locate cells in the chromaticity-processed endoscopic cell image according to the edge features.
[0123] The feature comparison module 406 is used to compare the edge features of each cell in the chromaticity-processed endoscopic cell image with the standard cell features, and determine the cells with similarity less than a preset threshold as abnormal cells.
[0124] In an exemplary embodiment, the chromaticity processing module 402 is also used to convert the endoscopic cell image and the preset cell image into dye matrices respectively; the dye matrix corresponding to the endoscopic cell image is aligned with the dye matrix corresponding to the preset cell image to obtain the chromaticity processed endoscopic cell image.
[0125] In an exemplary embodiment, the pre-built deep learning model includes a target detection subnetwork and an enhancement module; the edge extraction module 404 is also used to perform feature extraction on the chromaticity-processed endoscopic cell image through the target detection subnetwork to obtain an original feature map; perform pixel enhancement on the original feature map through the enhancement module to obtain an enhanced feature map; and extract edge features in the enhanced feature map through the target detection subnetwork.
[0126] In an exemplary embodiment, the apparatus further comprises:
[0127] The model building module is used to replace the residual network in the Mask R-CNN network with a lightweight network to obtain the object detection subnetwork.
[0128] In an exemplary embodiment, the apparatus further comprises:
[0129] The model building module is used to obtain the channel factor of each network channel in the lightweight network; the network channel whose channel factor is less than the preset threshold is used as the channel to be pruned; the channel to be pruned in the lightweight network is pruned, and the residual network in the Mask R-CNN network is replaced by the pruned lightweight network to obtain the target detection subnetwork.
[0130] In an exemplary embodiment, the apparatus further comprises:
[0131] A deep feature extraction module is used to extract deep features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model; the deep features include texture features and morphological features;
[0132] Feature fusion module, used to fuse deep features with edge features;
[0133] The feature comparison module 406 is also used to compare the fused features with the standard cell features for similarity.
[0134] In an exemplary embodiment, the apparatus further comprises:
[0135] An image acquisition module is used to acquire an endoscopic cell image through an endoscope handle of an endoscope; the endoscope handle comprises: a lens module; an optical fiber pressure plate, comprising a pressure plate groove, fixed to the outer wall of the lens module; an illumination module, comprising an optical fiber cable and an optical fiber connector; wherein the optical fiber cable is arranged inside the endoscope handle, passes through the pressure plate groove, is connected to one end of the optical fiber connector and extends to the other end; the other end of the optical fiber connector is fixedly connected to the lens module; the optical fiber cable and the optical fiber connector are used to provide incident light to the lens module so that the lens module generates an endoscopic cell image.
[0136] Each module in the abnormal cell detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.
[0137] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an abnormal cell detection method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0138] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0139] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0141] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0142] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0143] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0144] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for detecting abnormal cells, characterized in that: The method comprises: Performing chromaticity processing on the endoscopic cell image to obtain a chromaticity-processed endoscopic cell image; the endoscopic cell image is a fluorescent cell image; Extracting edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locating cells in the chromaticity-processed endoscopic cell image according to the edge features; The edge features of each cell in the chromaticity-processed endoscopic cell image are compared with the standard cell features for similarity, and cells with similarity less than a preset threshold are determined as abnormal cells.
2. The method according to claim 1, characterized in that: The step of performing chromaticity processing on the endoscopic cell image to obtain the chromaticity processed endoscopic cell image includes: converting the endoscopic cell image and the preset cell image into dye matrices respectively; The dye matrix corresponding to the endoscopic cell image is registered with the dye matrix corresponding to the preset cell image to obtain the endoscopic cell image after chromaticity processing.
3. The method according to claim 1, characterized in that The pre-built deep learning model includes a target detection subnetwork and an enhancement module; The extracting target edge features corresponding to the chromaticity-processed endoscopic cell image by a pre-built deep learning model includes: Performing feature extraction on the chromaticity-processed endoscopic cell image through the target detection subnetwork to obtain an original feature map; Performing pixel enhancement on the original feature map by the enhancement module to obtain an enhanced feature map; The edge features in the enhanced feature map are extracted by the target detection sub-network.
4. The method according to claim 3, characterized in that The target detection subnetwork is determined by: The residual network in the Mask R-CNN network is replaced with a lightweight network to obtain the object detection subnetwork.
5. The method according to claim 3, characterized in that: The target detection subnetwork is determined by: Get the channel factor of each network channel in the lightweight network; The network channels whose channel factors are smaller than the preset threshold are regarded as the channels to be pruned; The to-be-cropped channels in the lightweight network are cropped, and the residual network in the Mask R-CNN network is replaced with the cropped lightweight network to obtain a target detection subnetwork.
6. The method according to claim 1, characterized in that The method further comprises: Extracting the depth features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model; the depth features include texture features and morphological features; The depth feature is fused with the edge feature, and the fused feature is compared with the standard cell feature for similarity.
7. The method according to any one of claims 1 to 6, characterized in that: The method further includes: acquiring an endoscopic cell image through an endoscope handle of the endoscope; the endoscope handle includes: Lens module; An optical fiber pressing plate, including a pressing plate groove body, fixed to the outer wall of the lens module; A lighting module including a fiber optic cable and a fiber optic connector; Wherein, the optical fiber cable is arranged inside the endoscope handle, passes through the pressure plate groove to be connected to one end of the optical fiber connector and extends to the other end; the other end of the optical fiber connector is fixedly connected to the lens module; the optical fiber cable and the optical fiber connector are used to provide incident light to the lens module so that the lens module generates an endoscopic cell image.
8. An abnormal cell detection device, characterized in that: The device comprises: A chromaticity processing module, used for performing chromaticity processing on the endoscopic cell image to obtain the chromaticity processed endoscopic cell image; the endoscopic cell image is a fluorescent image; An edge extraction module, used to extract edge features corresponding to the chromaticity-processed endoscopic cell image through a pre-built deep learning model, and locate cells in the chromaticity-processed endoscopic cell image according to the edge features; The feature comparison module is used to compare the edge features of each cell in the chromaticity-processed endoscopic cell image with the standard cell features for similarity, and to determine the cells with similarity less than a preset threshold as abnormal cells.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.