Classification method and classification device for pancreatic neuroendocrine tumors

Abstract

The present application discloses a classification method and classification device for pancreatic neuroendocrine tumors. The classification method includes: using a pre-trained segmentation model to segment multiple HE whole-slice images from multiple patients; quantifying each segmented HE whole-slice image to determine multiple first feature parameters; extracting multiple second feature parameters from each HE whole-slice image based on the cell morphology and topological features of each HE whole-slice image; for each HE whole-slice image, screening target features from the multiple first feature parameters and the multiple second feature parameters, and calculating a pathological omics score; inputting the pathological omics scores and conventional pathological features of the multiple HE whole-slice images into a logistic regression model for training to obtain a trained logistic regression model; and using the logistic regression model to classify the HE whole-slice images to be classified. The present invention can quickly, accurately, and cost-effectively implement G classification of pancreatic neuroendocrine tumors.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a classification method, classification device, medium, electronic device, and computer program product for pancreatic neuroendocrine tumors. Background Art

[0002] Pancreatic neuroendocrine tumors (PNETs) are rare tumors originating from peptidergic neurons and neuroendocrine cells in the pancreas. Their incidence has increased significantly in recent years, posing a serious threat to patients' health.

[0003] Based on the mitotic figure and Ki-67 index, PNETs are subdivided into three grades: G1, G2, and G3. Pathological classification is crucial in patient management because it directly affects treatment strategies and is closely related to survival. The European Neuroendocrine Tumor Society (ENETS) guidelines recommend radical resection for all PNETs larger than 2 cm and functional PNETs. G1 PNETs can achieve a good survival prognosis through surgeries such as central pancreatectomy and enucleation. However, G3 PNETs require adjuvant chemotherapy after resection due to the high risk of recurrence.

[0004] The World Health Organization classification stipulates that accurate classification of PNETs relies on Ki-67 (MIB-1) immunohistochemistry. Accurate assessment of the tumor proliferation index requires manual counting of at least 500-2000 tumor cells. This method is labor-intensive and costly, and due to the variability of IHC (immunohistochemistry) preparation and the subjectivity of pathologists, inconsistent counting results may be produced. Especially in well-differentiated PNETs, ​​very small differences (1-5%) may significantly affect the tumor classification, thereby leading to changes in treatment plans.

[0005] Therefore, current methods are not only highly subjective but also time-consuming and labor-intensive, and are susceptible to differences in pathologists' experience and judgment, leading to inconsistency and inaccuracy in classification results. Summary of the Invention

[0006] The embodiments of the present application provide a method for classifying pancreatic neuroendocrine tumors, a device for classifying pancreatic neuroendocrine tumors, a medium, an electronic device, and a computer program product.

[0007] In a first aspect, embodiments of the present application provide a classification method for pancreatic neuroendocrine tumors, which is used in electronic devices. The classification method includes:

[0008] In the segmentation step, a pre-trained segmentation model is used to segment multiple HE whole-slice images from multiple patients to separate the tumor glands and tumor stroma in each HE whole-slice image;

[0009] a quantification step of quantifying each segmented HE whole-slice image to determine a plurality of first characteristic parameters, wherein the plurality of first characteristic parameters include a plurality of tumor gland-related parameters, a plurality of tumor bed-related parameters, and a plurality of tumor-stroma ratio-related parameters;

[0010] an extraction step of extracting a plurality of second feature parameters from each HE whole-slice image based on the cell morphology and topological features of each HE whole-slice image, wherein the plurality of second feature parameters include a plurality of morphological parameters, a plurality of texture feature parameters, and a plurality of topological feature parameters;

[0011] a screening step of screening target features from the plurality of first feature parameters and the plurality of second feature parameters for each HE whole-slice image, and calculating a pathological omics score for each HE whole-slice image;

[0012] a training step of inputting the pathological omics scores of the plurality of HE whole-slice images and the conventional pathological features of the plurality of HE whole-slice images into a logistic regression model for training to obtain a trained logistic regression model;

[0013] In the classification step, the trained logistic regression model is used to classify the HE whole-slice images to be classified.

[0014] In a second aspect, the present invention provides a classification device for pancreatic neuroendocrine tumors, the classification device comprising:

[0015] A segmentation unit, which uses a pre-trained segmentation model to segment multiple HE whole-slice images from multiple patients to separate the tumor glands and tumor stroma in each HE whole-slice image;

[0016] a quantization unit, configured to quantify each segmented HE whole-slice image to determine a plurality of first characteristic parameters, wherein the plurality of first characteristic parameters include a plurality of tumor gland-related parameters, a plurality of tumor bed-related parameters, and a plurality of tumor-stroma ratio-related parameters;

[0017] an extraction unit, which extracts a plurality of second feature parameters from each HE whole-slice image based on the cell morphology and topological features of each HE whole-slice image, wherein the plurality of second feature parameters include a plurality of morphological parameters, a plurality of texture feature parameters, and a plurality of topological feature parameters;

[0018] a screening unit, for each HE whole-slice image, screening a target feature from the plurality of first feature parameters and the plurality of second feature parameters, and calculating a pathological omics score for each HE whole-slice image;

[0019] a training unit, inputting the pathological omics scores of the plurality of HE whole-slice images and the conventional pathological features of the plurality of HE whole-slice images into a logistic regression model for training, thereby obtaining a trained logistic regression model;

[0020] The classification unit uses the trained logistic regression model to classify the HE whole-slice image to be classified.

[0021] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, causes the computer to execute the method for classifying pancreatic neuroendocrine tumors as described in any one of the first aspects.

[0022] In a fourth aspect, an embodiment of the present invention provides an electronic device comprising: one or more processors; one or more memories; the one or more memories storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device executes the classification method for pancreatic neuroendocrine tumors described in the first aspect.

[0023] In a fifth aspect, an embodiment of the present application provides a computer program product comprising computer-executable instructions, wherein the instructions are executed by a processor to implement the classification method for pancreatic neuroendocrine tumors described in the first aspect.

[0024] In this method, multiple first feature parameters related to tumor glands and tumor stroma, as well as multiple second feature parameters related to cell morphology and topology, are extracted from HE whole-slice images. Significantly correlated features are screened from these first and second feature parameters to calculate a pathomic score. This pathomic score and conventional pathological features derived from HE whole-slice images are then used to train (construct) a classification model. Based on the output of the classification model, G classification of pancreatic neuroendocrine tumors can be achieved quickly, accurately, and cost-effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 According to an embodiment of the present application, a flow chart of a method for classifying pancreatic neuroendocrine tumors is shown;

[0026] Figure 2 According to an embodiment of the present application, a structural diagram of a classification device for pancreatic neuroendocrine tumors is shown;

[0027] Figure 3According to an embodiment of the present application, a block diagram of an electronic device is shown. DETAILED DESCRIPTION

[0028] Illustrative embodiments of the present application include, but are not limited to, a method for classifying pancreatic neuroendocrine tumors, an apparatus, a medium, an electronic device, and a computer program product for classifying pancreatic neuroendocrine tumors.

[0029] The embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

[0030] Figure 1 A method for classifying pancreatic neuroendocrine tumors according to an embodiment of the present application is shown for use in an electronic device. Specifically, in segmentation step S11, a pre-trained segmentation model is used to segment multiple HE whole-slice images from multiple patients to separate the tumor glands and tumor stroma in each HE whole-slice image.

[0031] Hematoxylin and eosin (HE)-stained histopathological sections of surgically resected tumors of multiple patients were obtained and scanned into HE whole slide images (WSIs) at ×40 magnification using a scanner, thereby obtaining multiple HE whole slide images.

[0032] Each HE whole-slice image is cropped into multiple small image blocks, and each small image block is segmented using a pre-trained segmentation model to separate the tumor glands and tumor stroma in each small image block. Then, multiple segmented small image blocks are integrated together to form a segmented HE whole-slice image.

[0033] Specifically, due to the enormous size and resolution of HE whole-slice images, inputting the entire image would pose a significant challenge to the processor. Therefore, the high-resolution HE whole-slice images were cropped into smaller patches, such as 256×256 pixels, matching the input size of the segmentation model. To optimize model performance, image enhancement techniques such as normalization, denoising, and histogram equalization were applied. Furthermore, rigorous data validation was performed to ensure consistency in the number of labels and precise alignment between the mask and image size.

[0034] After segmenting each small image block using the pre-trained segmentation model, multiple segmented small image blocks are integrated together to form a segmented HE full-slice image. That is, a unified and complete segmentation map of the full-frame HE full-slice image is formed. The specific steps are as follows:

[0035] (1) Obtain the location information of each small image block by recording the starting coordinates.

[0036] (2) Extract metadata from the HE whole-slice image using a software package such as OpenSlicer, and then create a blank matrix that matches the size of the HE whole-slice image. This matrix will be used to store the processing results of each small image block, ultimately constructing a comprehensive view of the entire HE whole-slice image.

[0037] (3) Map the small blocks to the HE full-slice image matrix based on the coordinate information. Each small image block is accurately aligned to ensure no overlap or omission.

[0038] (4) All small image blocks are integrated together to achieve overall segmentation of the target tissue components. The segmentation results from different small image blocks are merged to identify specific tissue structures, and finally form a complete segmentation map of the HE whole slice image.

[0039] The pre-trained segmentation model is, for example, the pre-trained semantic segmentation model DeepLabV3+. The training process is as follows:

[0040] Hematoxylin and eosin (HE) whole-slide images of randomly selected patients from the training set are segmented into multiple small image patches. A pathologist, for example, then labels the tumor glands and tumor stroma. After labeling, a multi-class mask is generated, assigning each pixel a class value: 1 for tumor glands, 0 for background, and 2 for tumor stroma. The labeled patches and their corresponding masks are exported and stored in PNG format.

[0041] The labeled small image blocks are input into the semantic segmentation model DeepLabV3+ for training to obtain a pre-trained segmentation model.

[0042] In the quantification step S12 , each segmented HE whole slice image is quantified to determine a plurality of first characteristic parameters, which include a plurality of tumor gland-related parameters, a plurality of tumor bed-related parameters, and a plurality of tumor-stroma ratio-related parameters.

[0043] Here, each segmented HE whole-slice image was quantified using image processing tools (e.g., OpenCV 4.8.0).

[0044] Specifically, to obtain the true area of ​​a specific tissue component, the image processing tool OpenCV 4.8.0 was used to first count the total number of pixels (Pi) corresponding to that component in the segmented HE whole-slice image (i.e., the segmented image). Then, based on the image metadata, the actual length (Sx and Sy) of each pixel in the horizontal (x) and vertical (y) directions was obtained. Finally, the total number of pixels was multiplied by the pixel spacing in these two directions to calculate the true area of ​​the component. The specific formula is: S = Pi * Sx * Sy. Ultimately, three sets of quantifiable first characteristic parameters were obtained, including multiple tumor gland-related parameters (e.g., 8), multiple tumor bed-related parameters (e.g., 26), and multiple tumor-stroma ratio (the ratio of tumor glands to stroma within the tumor bed)-related parameters (e.g., 15).

[0045] In the extraction step S13, a plurality of second feature parameters are extracted from each HE whole slice image based on the cell morphology and topological features of each HE whole slice image. The plurality of second feature parameters include a plurality of morphological parameters, a plurality of texture feature parameters, and a plurality of topological feature parameters.

[0046] First, tumor cells, stromal cells, and lymphocytes are segmented and classified in each HE whole-slide image. Specifically, a pretrained HoVer-Net model is used to simultaneously segment and classify cell nuclei, including tumor cells, stromal cells, and lymphocytes. This model, pretrained on the PanNuke dataset, separates clustered units by using the horizontal and vertical distances from nucleus pixels to their centroids. Given a HE whole-slide image as input, the model outputs a corresponding .json file containing all information regarding nucleus segmentation and classification for each sample.

[0047] Secondly, cell-level feature extraction is performed on tumor cells, stromal cells, and lymphocytes to extract multiple second feature parameters.

[0048] Specifically, the pathologist outlined the region of interest (ROI) and generated the corresponding .xml file. Then, the HE whole-slice image, .xml file, and the corresponding .json file were used as input. For each sample, feature extraction was performed using WSI Graph (graphical representation) to obtain a folder containing four .csv data files. For each cell type (tumor cells, lymphocytes, and stromal cells), three .csv files store the properties of all cells of that type, and each cell is identified by a unique cell ID (identifier) ​​and its center of mass coordinates. Another .csv file stores the edge information of the sample, that is, each edge represented by a connected cell ID.

[0049] Finally, multiple secondary feature parameters (e.g., 378) were extracted from each HE whole-slice image. These feature parameters were divided into three categories: (1) morphological feature parameters, which describe the shape and outline of the cell nucleus; (2) texture feature parameters, which characterize the local pixel distribution pattern within the cell nucleus outline; and (3) topological feature parameters, which describe the relative positions, interaction patterns, and resulting spatial organization of cells, with a specific focus on the interactions between tumor cells, inflammatory cells, and stromal cells. For each cell type, three types of topological features were extracted: cell-to-cell edge length (e.g., T-I_MinEdgeLength and T-I_MeanEdgeLength, representing the minimum and average edge lengths between tumor cells and inflammatory cells), number of subgraphs (e.g., I-S_Nsubgraph, representing the number of subgraphs between inflammatory cells and stromal cells), centrality and other network properties (e.g., I-S_Closeness and I-S_Betweenness, representing the closeness centrality and betweenness centrality between inflammatory cells and stromal cells).

[0050] In the screening step S14 , for each HE whole-slice image, target features are screened out from the plurality of first feature parameters and the plurality of second feature parameters, and a pathological omics score of each HE whole-slice image is calculated.

[0051] For each HE whole-slice image, LASSO regression was used to screen target features from multiple first feature parameters and multiple second feature parameters, and the pathomic score of each HE whole-slice image was calculated using the LASSO regression equation. The target feature was a feature with significant correlation.

[0052] Specifically, for example, for each HE whole-slice image, multiple first feature parameters (49) and multiple second feature parameters (e.g., 378) as described above can be obtained, for a total of 427 feature parameters. Correlation analysis is performed on the 427 feature parameters, and LASS regression is used to further screen out features with significant correlation as target features. For example, 6 target features are screened out. Finally, a pathological omics score is generated using the LASSO regression equation. There is a significant difference in the pathological omics scores between G1 and G2 / 3 grades.

[0053] It can be understood that a corresponding pathological omics score can be calculated for each HE whole-slice image.

[0054] In the training step S15 , the pathological omics scores of the plurality of HE whole-slice images and the conventional pathological features of the plurality of HE whole-slice images are input into a logistic regression model for training to obtain a trained logistic regression model.

[0055] Pathology reports can be generated from HE whole-slide images and include routine pathological features. These include tumor size, tumor location, tumor number, tumor burden score (TBS), T stage, N stage, M stage (American Joint Committee on Cancer TNM Staging Manual, 9th edition), and tumor texture (solid / cystic, with cystic defined as any proportion of cystic components). TBS² is calculated based on the method proposed in previous studies as follows: (maximum tumor diameter)² + (number of tumors)².

[0056] In this embodiment, tumor size, T stage, N stage, M stage, and TBS were selected as parameters for training the logistic regression model.

[0057] In the classification step S16 , the trained logistic regression model is used to classify the HE whole-slice images to be classified.

[0058] It is understandable that the trained logistic regression model can be used as a classification model to classify HE whole-slice images to be classified. In this embodiment, the classification model divides the HE whole-slice images into two categories, one is G1 level and the other is G2 / G3 level.

[0059] In addition, in this embodiment, the performance of the classification model was comprehensively verified and its clinical practicality was evaluated through multiple methods such as ROC curve, Kaplan-Meier survival analysis, and decision curve analysis.

[0060] In this method, multiple first feature parameters related to tumor glands and tumor stroma, as well as multiple second feature parameters related to cell morphology and topology, are extracted from HE whole-slice images. Significantly correlated features are screened from these first and second feature parameters to calculate a pathomic score. This pathomic score and conventional pathological features derived from HE whole-slice images are then used to train (construct) a classification model. Based on the output of the classification model, G classification of pancreatic neuroendocrine tumors can be achieved quickly, accurately, and cost-effectively.

[0061] The present invention further provides a classification device 20 for pancreatic neuroendocrine tumors, the classification device 20 comprising:

[0062] a segmentation unit 201 , using a pre-trained segmentation model to segment a plurality of HE whole-slice images from a plurality of patients, so as to segment the tumor glands and tumor stroma in each HE whole-slice image;

[0063] a quantization unit 202 that quantifies each segmented HE whole-slice image to determine a plurality of first characteristic parameters, wherein the plurality of first characteristic parameters include a plurality of tumor gland-related parameters, a plurality of tumor bed-related parameters, and a plurality of tumor-stroma ratio-related parameters;

[0064] An extraction unit 203 extracts a plurality of second feature parameters from each HE whole-slice image based on the cell morphology and topological features of each HE whole-slice image, wherein the plurality of second feature parameters include a plurality of morphological feature parameters, a plurality of texture feature parameters, and a plurality of topological feature parameters;

[0065] a screening unit 204 , for each HE whole-slice image, screening target features from the plurality of first feature parameters and the plurality of second feature parameters, and calculating a pathological omics score for each HE whole-slice image;

[0066] A training unit 205 inputs the pathological omics scores of the plurality of HE whole-slice images and the conventional pathological features of the plurality of HE whole-slice images into a logistic regression model for training to obtain a trained logistic regression model;

[0067] The classification unit 206 uses the trained logistic regression model to classify the HE whole-slice image to be classified.

[0068] It is understandable that the segmentation unit 201, the quantization unit 202, the extraction unit 203, the screening unit 204, the training unit 205, and the classification unit 206 can be Figure 3 The processor 102 in the electronic device 100 having the functions of these modules or units is implemented.

[0069] The present invention also provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute Figure 1 The method shown in .

[0070] The present invention also provides a computer program product comprising computer executable instructions, which are executed by the processor 102 to implement Figure 1 The method shown in .

[0071] Now refer to Figure 3 , Figure 3 An example electronic device 1400 according to an embodiment of the present invention is schematically shown. In one embodiment, the electronic device 1400 may include one or more processors 1404, a system control logic unit 1408 coupled to at least one of the processors 1404, a system memory 1412 coupled to the system control logic unit 1408, a non-volatile memory (NVM) 1416 coupled to the system control logic unit 1408, and a network interface 1420 coupled to the system control logic unit 1408.

[0072] In some embodiments, the processor 1404 may include one or more single-core or multi-core processors. In some embodiments, the processor 1404 may include any combination of general-purpose processors and special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In embodiments where the electronic device 1400 employs an eNB (Evolved Node B, enhanced base station) or a RAN (Radio Access Network, radio access network) controller, the processor 1404 may be configured to execute various embodiments, such as Figure 1 The embodiment shown.

[0073] In some embodiments, system control logic unit 1408 may include any suitable interface controller to provide any suitable interface to at least one of processors 1404 and / or any suitable device or component in communication with system control logic unit 1408 .

[0074] In some embodiments, the system control logic unit 1408 may include one or more memory controllers to provide an interface to the system memory 1412. The system memory 1412 may be used to load and store data and / or instructions. In some embodiments, the system memory 1412 of the electronic device 1400 may include any suitable volatile memory, such as a suitable dynamic random access memory (DRAM).

[0075] The non-volatile memory 1416 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, the non-volatile memory 1416 may include any suitable non-volatile memory such as flash memory and / or any suitable non-volatile storage device, such as at least one of an HDD (Hard Disk Drive), a CD (Compact Disc) drive, and a DVD (Digital Versatile Disc) drive.

[0076] The non-volatile memory 1416 may include a portion of storage resources on the device on which the electronic device 1400 is installed, or it may be accessible to the electronic device but not necessarily a portion of the electronic device. For example, the non-volatile memory 1416 may be accessed via the network interface 1420 over a network.

[0077] In particular, the system memory 1412 and the non-volatile memory 1416 may each include a temporary copy and a permanent copy of the instructions 1424. The instructions 1424 may include instructions that, when executed by at least one of the processors 1404, cause the electronic device 1400 to perform the following operations: Figure 1In some embodiments, instructions 1424 , hardware, firmware, and / or software components thereof may additionally or alternatively reside in system control logic 1408 , network interface 1420 , and / or processor 1404 .

[0078] The network interface 1420 may include a transceiver for providing a radio interface for the electronic device 1400, thereby communicating with any other suitable devices (such as a front-end module, an antenna, etc.) through one or more networks. In some embodiments, the network interface 1420 may be integrated with other components of the electronic device 1400. For example, the network interface 1420 may be integrated with at least one of the processor 1404, the system memory 1412, the non-volatile memory 1416, and a firmware device (not shown) having instructions. When at least one of the processors 1404 executes the instructions, the electronic device 1400 implements the following. Figure 1 The method shown.

[0079] The network interface 1420 may further include any suitable hardware and / or firmware to provide a multiple-input multiple-output radio interface. For example, the network interface 1420 may be a network adapter, a wireless network adapter, a telephone modem, and / or a wireless modem.

[0080] In one embodiment, at least one of the processors 1404 may be packaged together with logic for one or more controllers of the system control logic unit 1408 to form a system-in-package (SiP). In one embodiment, at least one of the processors 1404 may be integrated on the same die with logic for one or more controllers of the system control logic unit 1408 to form a system-on-chip (SoC).

[0081] Electronic device 1400 may further include an input / output (I / O) device 1432. I / O device 1432 may include a user interface that enables a user to interact with electronic device 1400; peripheral component interfaces may also be designed to enable peripheral components to interact with electronic device 1400. In some embodiments, electronic device 1400 may further include a sensor for determining at least one of environmental conditions and location information related to electronic device 1400.

[0082] In some embodiments, the user interface may include, but is not limited to, a display (e.g., an LCD display, a touch screen display, etc.), a speaker, a microphone, one or more cameras (e.g., a still image camera and / or a video camera), a flashlight (e.g., an LED flash), and a keyboard.

[0083] The various embodiments of the mechanisms disclosed in this application can be implemented in hardware, software, firmware, or a combination of these implementation methods. The embodiments of the present application can be implemented as a computer program or program code executed on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0084] Program code can be applied to input instructions to perform the functions described herein and generate output information. The output information can be applied to one or more output devices in a known manner. For purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0085] Program code can be implemented with a high-level programming language or an object-oriented programming language to communicate with the processing system. Where necessary, program code can also be implemented in assembly language or machine language. In fact, the mechanism described in this application is not limited to the scope of any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0086] In some cases, the disclosed embodiments can be implemented in hardware, firmware, software or any combination thereof. The disclosed embodiments can also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which can be read and executed by one or more processors. For example, instructions can be distributed over a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer), including but not limited to, floppy disks, optical disks, optical discs, read-only memories (CD-ROMs), magneto-optical disks, read-only memories (ROMs), random access memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic or optical cards, flash memories, or tangible machine-readable memories for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in electrical, optical, acoustic or other forms of propagation signals. Therefore, machine-readable media include any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a form readable by a machine (e.g., a computer).

[0087] In the accompanying drawings, some structural or method features may be shown in a particular arrangement and / or order. However, it should be understood that such a particular arrangement and / or order may not be required. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of a structural or method feature in a particular figure does not imply that such feature is required in all embodiments, and in some embodiments, such features may not be included or may be combined with other features.

[0088] It should be noted that the units / modules mentioned in the various device embodiments of the present application are all logical units / modules. Physically, a logical unit / module can be a physical unit / module, or a part of a physical unit / module, or can be implemented as a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not the most important. The combination of functions implemented by these logical units / modules is the key to solving the technical problems raised by this application. In addition, in order to highlight the innovative part of this application, the above-mentioned device embodiments of this application do not introduce units / modules that are not closely related to solving the technical problems raised by this application. This does not mean that other units / modules do not exist in the above-mentioned device embodiments.

[0089] It should be noted that in the examples and description of this patent, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "including a" does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0090] Although the present application has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the application.

Claims

1. A method for classifying pancreatic neuroendocrine tumors, for use in electronic devices, characterized in that: The classification method includes: In the segmentation step, a pre-trained segmentation model is used to segment multiple HE whole-slice images from multiple patients to separate the tumor glands and tumor stroma in each HE whole-slice image; a quantification step of quantifying each segmented HE whole-slice image to determine a plurality of first characteristic parameters, wherein the plurality of first characteristic parameters include a plurality of tumor gland-related parameters, a plurality of tumor bed-related parameters, and a plurality of tumor-stroma ratio-related parameters; an extraction step of extracting a plurality of second feature parameters from each HE whole-slice image based on the cell morphology and topological features of each HE whole-slice image, wherein the plurality of second feature parameters include a plurality of morphological feature parameters, a plurality of texture feature parameters, and a plurality of topological feature parameters; a screening step of screening target features from the plurality of first feature parameters and the plurality of second feature parameters for each HE whole-slice image, and calculating a pathological omics score for each HE whole-slice image; a training step of inputting the pathological omics scores of the plurality of HE whole-slice images and the conventional pathological features of the plurality of HE whole-slice images into a logistic regression model for training to obtain a trained logistic regression model; In the classification step, the trained logistic regression model is used to classify the HE whole-slice images to be classified.

2. The classification method according to claim 1, characterized in that In the segmentation step, each HE full-slice image is cropped into multiple small image blocks, and each small image block is segmented using the segmentation model to segment out the tumor glands and tumor stroma in each small image block. The multiple segmented small image blocks are integrated together to form a segmented HE full-slice image.

3. The classification method according to claim 1, characterized in that In the quantification step, each segmented HE whole-slice image is quantified using an image processing tool.

4. The classification method according to claim 1, characterized in that In the extraction step, the tumor cells, stromal cells, and lymphocytes in each HE whole-slice image are segmented and classified, and cell-level feature extraction is performed on the tumor cells, the stromal cells, and the lymphocytes to extract the multiple second feature parameters.

5. The classification method according to claim 1, characterized in that In the screening step, for each HE whole-slice image, the target feature is screened out from the multiple first feature parameters and the multiple second feature parameters using LASS regression, and the pathological omics score of each HE whole-slice image is calculated using the LASSO regression equation. The target feature is a feature with significant correlation.

6. The classification method according to claim 1, characterized in that A pathology report is obtained from the HE whole-slice image, wherein the pathology report includes the conventional pathology features.

7. A classification device for pancreatic neuroendocrine tumors, characterized in that: The classification device comprises: A segmentation unit, which uses a pre-trained segmentation model to segment multiple HE whole-slice images from multiple patients to separate the tumor glands and tumor stroma in each HE whole-slice image; a quantization unit, configured to quantify each segmented HE whole-slice image to determine a plurality of first characteristic parameters, wherein the plurality of first characteristic parameters include a plurality of tumor gland-related parameters, a plurality of tumor bed-related parameters, and a plurality of tumor-stroma ratio-related parameters; an extraction unit, which extracts a plurality of second feature parameters from each HE whole-slice image based on the cell morphology and topological features of each HE whole-slice image, wherein the plurality of second feature parameters include a plurality of morphological feature parameters, a plurality of texture feature parameters, and a plurality of topological feature parameters; a screening unit, for each HE whole-slice image, screening a target feature from the plurality of first feature parameters and the plurality of second feature parameters, and calculating a pathological omics score for each HE whole-slice image; a training unit, inputting the pathological omics scores of the plurality of HE whole-slice images and the conventional pathological features of the plurality of HE whole-slice images into a logistic regression model for training, thereby obtaining a trained logistic regression model; The classification unit uses the trained logistic regression model to classify the HE whole-slice image to be classified.

8. A computer-readable storage medium, characterized in that The storage medium stores instructions, which, when executed on a computer, cause the computer to execute the method for classifying pancreatic neuroendocrine tumors according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: one or more processors; One or more memories; the one or more memories store one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device executes the classification method for pancreatic neuroendocrine tumors according to any one of claims 1 to 6.

10. A computer program product comprising computer executable instructions, characterized in that: The instructions are executed by a processor to implement the method for classifying pancreatic neuroendocrine tumors according to any one of claims 1 to 6.

Images