Method and system for realizing head and neck tumor immunohistochemical classification by using hyperspectrum

Abstract

The application discloses a method and system for realizing head and neck tumor immunohistochemical classification by using hyperspectrum, and relates to the field of image processing.The method comprises the following steps: labeling a hyperspectrum image corresponding to a head and neck tumor pathological section sample to obtain pixel-level immunohistochemical indexes, including epithelium, interstitial, negative, weak positive and strong positive; inputting the hyperspectrum image corresponding to the head and neck tumor pathological section sample into a preset deep learning classification framework, training an immunohistochemical index prediction model by using corresponding immunohistochemical indexes as labels; the preset deep learning classification framework is a lightweight encoder-decoder network architecture integrated with a wave band selection strategy, an adaptive local and global feature fusion strategy and an adaptive channel fusion strategy; inputting a hyperspectrum image corresponding to a head and neck tumor pathological section to be detected into the immunohistochemical index prediction model to obtain corresponding pixel-level immunohistochemical indexes.The application can realize rapid and accurate immunohistochemical index prediction.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image processing, in particular to a method and system for realizing head and neck tumor immunohistochemical classification by using hyperspectral. BACKGROUND

[0002] Head and neck cancer is a malignant tumor that occurs in the mucosal surface of the oral cavity, nasopharyngeal cavity, pharynx (nasopharynx, oropharynx and hypopharynx) and larynx. In the past few decades, the five-year survival rate of patients with advanced head and neck cancer is still very low, about 40%-50%. In order to improve the prognosis of these patients, early diagnosis and effective treatment are crucial. Pathohistology is the "gold standard" for clinical diagnosis of cancer. In head and neck cancer, the expression of some immunohistochemical marker proteins has been proven to be a marker reflecting prognosis. However, immunohistochemical markers are easily affected by the depth of background staining, and the presence, expression and distribution of target molecules are also easily affected by the experience of pathologists in reading slides. Therefore, an auxiliary tool is urgently needed to help pathologists improve the quality and efficiency of their work. SUMMARY

[0003] The purpose of the present application is to provide a method and system for realizing head and neck tumor immunohistochemical classification by using hyperspectral, which can realize rapid and accurate immunohistochemical index prediction.

[0004] To achieve the above-mentioned purpose, the present application provides the following scheme:

[0005] In a first aspect, the present application provides a method for realizing head and neck tumor immunohistochemical classification by using hyperspectral, comprising the following steps.

[0006] Obtain a plurality of head and neck tumor pathological section samples and corresponding hyperspectral images.

[0007] Label the hyperspectral image corresponding to each head and neck tumor pathological section sample to obtain the corresponding pixel-level immunohistochemical index; the pixel-level immunohistochemical index includes epithelium, stroma, negative, weak positive and strong positive.

[0008] Input the hyperspectral image corresponding to each head and neck tumor pathological section sample into a preset deep learning classification framework, train with the immunohistochemical index corresponding to the head and neck tumor pathological section sample as the label, to obtain an immunohistochemical index prediction model; wherein the preset deep learning classification framework is a lightweight encoder-decoder network architecture integrated with a band selection strategy, an adaptive local and global feature fusion strategy and an adaptive channel fusion strategy.

[0009] Input the hyperspectral image corresponding to the head and neck tumor pathological section to be detected into the immunohistochemical index prediction model for prediction to obtain the corresponding pixel-level immunohistochemical index.

[0010] In a second aspect, the present application provides a system for realizing head and neck tumor immunohistochemical classification by using hyperspectral imaging, comprising the following modules.

[0011] An acquisition module is configured to acquire a plurality of head and neck tumor pathological section samples and corresponding hyperspectral images.

[0012] A labeling module is configured to label the hyperspectral image corresponding to each head and neck tumor pathological section sample to obtain a corresponding pixel-level immunohistochemical index, wherein the pixel-level immunohistochemical index comprises epithelium, stroma, negative, weakly positive, and strongly positive.

[0013] A training module is configured to input the hyperspectral image corresponding to each head and neck tumor pathological section sample into a preset deep learning classification framework, and train the immunohistochemical index corresponding to the head and neck tumor pathological section sample as a label to obtain an immunohistochemical index prediction model, wherein the preset deep learning classification framework is a lightweight encoder-decoder network architecture integrated with a band selection strategy, an adaptive local and global feature fusion strategy, and an adaptive channel fusion strategy.

[0014] A prediction module is configured to input the hyperspectral image corresponding to a head and neck tumor pathological section to be detected into the immunohistochemical index prediction model for prediction to obtain a corresponding pixel-level immunohistochemical index.

[0015] According to the embodiments provided in the present application, the present application has the following technical effects: the present application provides a method and system for realizing head and neck tumor immunohistochemical classification by using hyperspectral imaging, and inputs the hyperspectral image corresponding to the head and neck tumor pathological section sample into a preset deep learning classification framework for training with the immunohistochemical index as a label. In the present application, the preset deep learning classification framework is a lightweight encoder-decoder network architecture integrated with a band selection strategy, an adaptive local and global feature fusion strategy, and an adaptive channel fusion strategy, which can realize training of sparse pixel annotation. The band selection strategy used in the framework can identify a subset of bands with significant discriminative power; then, through the setting of the adaptive local and global feature fusion strategy, the connection between pixels is enhanced, and the classification performance is effectively improved; at the same time, the adaptive channel fusion strategy is adopted to combine local and global features, thereby realizing high-precision classification. Thus, the immunohistochemical index prediction model trained by the present application can quickly and accurately predict the immunohistochemical index of the hyperspectral image corresponding to the head and neck tumor pathological section to be detected. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0017] Figure 1 An application environment diagram of a method for realizing immunohistochemical classification of head and neck tumor by using hyperspectral imaging according to an embodiment of the present application.

[0018] Figure 2 A flowchart of a method for realizing immunohistochemical classification of head and neck tumor by using hyperspectral imaging according to an embodiment of the present application.

[0019] Figure 3 A schematic diagram of a preset deep learning classification framework according to an embodiment of the present application.

[0020] Figure 4 A structural schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0022] The spatial resolution spectral imaging obtained by hyperspectral imaging can provide diagnostic information about tissue physiology, morphology and composition. The hyperspectral imaging system can use narrow-band filters to accurately capture color information and is not affected by the super-resolution phenomenon similar to RGB images. Therefore, applying hyperspectral imaging technology to evaluate immunohistochemically stained tissue sections to improve the quantification of markers that may be relevant in diagnosis or prognosis can be a new detection method.

[0023] Based on this, the present application provides a method for predicting immunohistochemical indicators of head and neck tumor pathological sections by using hyperspectral imaging technology, to solve the problem of insufficient accuracy of current immunohistochemical diagnosis.

[0024] In order to make the above purposes, features and advantages of the present application more apparent and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0025] The method for realizing immunohistochemical classification of head and neck tumor by using hyperspectral imaging provided in the embodiments of the present application can be applied to, for example, Figure 1The application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data required by the server 104 to process. The data storage system can be set up separately, or integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the hyperspectral image corresponding to the head and neck tumor pathological section to be detected to the server 104, and after the server 104 receives it, it is input into the immunohistochemical index prediction model for prediction to obtain the corresponding pixel-level immunohistochemical index. The server 104 can feed back the obtained pixel-level immunohistochemical index to the terminal 102.

[0026] In one exemplary embodiment, as Figure 2 shown, a method for realizing head and neck tumor immunohistochemical classification by hyperspectral is provided, which is executed by a computer device, specifically by a terminal or a server, etc. Computer device alone, or by a terminal and a server together, in the embodiment of the present application, taking the server 104 in the as an example, the method includes the following steps 201 to 204. Figure 1

[0027] Step 201, obtaining a plurality of head and neck tumor pathological section samples and corresponding hyperspectral images.

[0028] In one application example, the process of obtaining a plurality of head and neck tumor pathological section samples includes: obtaining a plurality of head and neck tumor pathological sections of different immunohistochemistry and screening to obtain a plurality of head and neck tumor pathological section samples.

[0029] Specifically, the pathological tissue sections of the head and neck tumor multi-immunohistochemical label (P16, EGFR, P63, P53, EGFR) patients treated by radical surgery in a hospital within a predetermined period of time (such as half a year, three years, five years, etc.) can be obtained. A total of 53 cases. Among them, 43 cases can be used as a training sample set for extracting hyperspectral information and constructing an artificial intelligence classification model in the subsequent steps, and the remaining 10 cases can be used as a test sample set for evaluation. Thus, a plurality of head and neck tumor pathological sections of different immunohistochemistry are obtained. Then, the head and neck tumor pathological sections in the training sample set are evaluated by experienced pathologists without knowing the basic information and clinical related data of the patients, and the head and neck tumor pathological sections are screened according to the obtained reaction results, and a plurality of head and neck tumor pathological section samples in the training sample set are obtained.

[0030] In another application example, the process of obtaining the hyperspectral image corresponding to the head and neck tumor pathological section sample includes:

[0031] ​(11) Assemble a hyperspectral microscopic imaging system; the hyperspectral microscopic imaging system comprises a microscope, a scanning acquisition assembly and a halogen illumination source; wherein the microscope is an upright imaging microscope, the halogen illumination source is a 12V / 100W halogen illumination source, the scanning acquisition assembly is obtained by integrating a liquid crystal tunable filter and a CCD (charge-coupled device) camera, and the CCD camera is a 12-bit CCD camera. In addition, the hyperspectral microscopic imaging system can further comprise a hyperspectral data processing terminal.

[0032] (12) Place the head and neck tumor pathological section sample on the object table of the microscope, irradiate the head and neck tumor pathological section sample using the halogen illumination source, the microscope automatically focuses and simultaneously collects multi-band spectral information through the scanning acquisition assembly to obtain an initial hyperspectral image. Specifically, after the microscope automatically focuses, the entire head and neck tumor pathological section sample is scanned, and during the scanning process, the CCD camera collects uniform 260 bands of spectral information in the 400nm-1000nm spectral range of the head and neck tumor pathological section sample through the CCD sensor with a resolution of 2.3nm.

[0033] (13) Perform black and white calibration normalization processing on the initial hyperspectral image to obtain a hyperspectral image corresponding to the head and neck tumor pathological section sample. Wherein, in order to avoid the interference of ambient light, when performing black and white calibration normalization processing on the initial hyperspectral image, the following formula is used:

[0034] .

[0035] Wherein, I ref is the reflected spectral intensity value obtained after black and white calibration normalization processing, I raw is the reflected spectral intensity value in the initial hyperspectral image, I dark is the dark current reference intensity, I white is the full reflection reference intensity.

[0036] Step 202, label each hyperspectral image corresponding to the head and neck tumor pathological section sample to obtain a corresponding pixel-level immunohistochemical index; the pixel-level immunohistochemical index includes epithelium, stroma, negative, weak positive and strong positive.

[0037] In an application example, the step of labeling the hyperspectral image corresponding to each of the head and neck tumor pathological section samples comprises: 1) using ENVI5.6 to label each pixel in the hyperspectral image corresponding to the head and neck tumor pathological section sample to obtain a pixel-level immunohistochemical index corresponding to each pixel; wherein the labeling process is as follows: after being manually labeled by two head and neck surgeons with more than five years of experience, the labeling is evaluated and corrected by a pathologist. 2) Statistics of the number of pixels corresponding to different categories of pixel-level immunohistochemical indicators, such as the number of pixels of the category of epithelium, the number of pixels of the category of stroma, the number of pixels of the category of negative, the number of pixels of the category of weak positive, and the number of pixels of the category of strong positive. In order to facilitate statistics, different colors are used to represent different categories, such as the hyperspectral images of five immunohistochemical indicators p16, p53, p63, egfr, and Eber, which are all represented by cyan for epithelium EPI, blue for mesenchyme MEM, yellow for negative, green for weak positive, and red for strong positive. As shown in Table 1 below, it is a part of pixel number statistics table.

[0038] Table 1

[0039]

[0040] In the labeling process, the staining intensity of any pixel in the negative image is within a first preset range; the staining intensity of any pixel in the weak positive image is within a second preset range; the staining intensity of any pixel in the strong positive image is within a third preset range; the stroma and the epithelium refer to the tissue category of the pixels in the image that are different from the pixels stained by immunohistochemistry.

[0041] Wherein, the first preset range, the second preset range and the third preset range are all represented in the form of proportion relative to the maximum staining intensity, such as for a head and neck tumor pathological section sample, the color area indicated by the staining indicator is the positive control area, the area without staining indicator is the negative control area, and the whole section containing tissue area is the overall control area. According to the average percentage of immunostained cells and the immunostaining intensity, the global 0-20% (first preset range) staining intensity is defined as immunohistochemical index negative (marked as -), 20-50% (second preset range) staining intensity is defined as immunohistochemical index weak positive (marked as +), and more than 50% staining intensity (third preset range) is defined as immunohistochemical index strong positive (marked as ++).

[0042] Step 203, inputting each of the head and neck tumor pathology section sample corresponding hyperspectral image into a preset deep learning classification framework, training with the immunohistochemical index corresponding to the head and neck tumor pathology section sample as a label to obtain an immunohistochemical index prediction model; wherein the preset deep learning classification framework is a lightweight encoder-decoder network architecture integrated with a band selection strategy, an adaptive local and global feature fusion strategy, and an adaptive channel fusion strategy.

[0043] As shown in Figure 3 The preset deep learning classification framework includes an encoder network architecture, an adaptive local and global feature fusion layer, and a decoder network architecture arranged in sequence, which can realize effective classification of microscopic hyperspectral images.

[0044] Specifically, the encoder network architecture includes a band selection layer, a first encoding layer, a second encoding layer, and a third encoding layer arranged in sequence; the decoder network architecture includes a third decoding layer, a second decoding layer, a first decoding layer, and an output layer arranged in sequence; the first encoding layer and the first decoding layer are connected by jumping, the second encoding layer and the second decoding layer are connected by jumping; the third encoding layer and the third decoding layer are connected by jumping.

[0045] The first encoding layer, the second encoding layer, and the third encoding layer each include a spatial-spectral attention layer and a first convolutional layer arranged in sequence; the first decoding layer, the second decoding layer, and the third decoding layer each include a second convolutional layer and a spatial-semantic fusion layer arranged in sequence. The first convolutional layer is an integration of a convolutional layer, a group normalization layer, and a ReLu activation layer, and the second convolutional layer is a 3 3 convolutional layer. The output layer includes a second convolutional layer and a sub-output layer arranged in sequence; the sub-output layer is an integration of a 1 1 convolutional layer and a softmax classification layer.

[0046] The band selection layer is used to: for the received hyperspectral image, a band selection algorithm based on maximum quality is used to select bands to obtain a significant band subset, and then convolution processing is performed to obtain spectral features. And the convolution processing in it can use the same structure as the first convolutional layer.

[0047] According to the above-mentioned preset deep learning classification framework setting, the framework is a new type of weakly supervised learning framework based on sparse pixel annotation for training. Firstly, based on the maximum quality band selection strategy, a subset of bands with significant discriminability is identified. Then, the classification process is completed in a lightweight encoder-decoder network architecture, which integrates an adaptive local and global feature fusion layer, effectively improving the classification performance by enhancing the connection between pixels. At the same time, an adaptive channel fusion strategy is adopted, which skillfully combines local and global features to achieve high-precision classification. After the above framework is constructed, the spatial and spectral features of the samples in the training set are trained, and then the test sample set is used to test the trained immunohistochemical index prediction model.

[0048] In actual testing, to ensure the comprehensiveness of the evaluation, 1-3 instances were selected from the test sample set corresponding to different immunohistochemical microscopic hyperspectral images, a total of 10 immunohistochemical hyperspectral images were selected for testing. Table 2 lists the selected immunohistochemical types of the test data set.

[0049] Table 2

[0050]

[0051] During testing, the overall classification accuracy (OA), average classification accuracy (AA), and Kappa coefficient were calculated using the confusion matrix to evaluate the true effect of immunohistochemical index classification. The prediction results obtained after the above testing are summarized in Table 3 as follows.

[0052] Table 3

[0053]

[0054] Step 204, input the hyperspectral image corresponding to the head and neck tumor pathological section to be detected into the immunohistochemical index prediction model for prediction to obtain the corresponding pixel-level immunohistochemical index.

[0055] In summary, the present application realizes the combination of hyperspectral imaging technology and artificial intelligence classification algorithm to predict the immunohistochemical index of head and neck tumor pathological sections. The presence or absence and intensity of 5 immunohistochemical indexes related to head and neck tumor prognosis are predicted to improve the diagnostic accuracy of head and neck tumor immunohistochemical indexes, which is of great significance for precise classification, individualization, and decision-making of head and neck tumor diagnosis and treatment.

[0056] Based on the same inventive concept, the application further provides a system for realizing immunohistochemical classification of head and neck tumors by using hyperspectral imaging. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme described in the above method, so the specific limitations in one or more system embodiments provided below can refer to the limitations of the method described above, which will not be repeated here. The system for realizing immunohistochemical classification of head and neck tumors by using hyperspectral imaging includes an acquisition module, a labeling module, a training module, and a prediction module.

[0057] The acquisition module is configured to acquire a plurality of head and neck tumor pathological section samples and corresponding hyperspectral images.

[0058] The labeling module is configured to label the hyperspectral image corresponding to each head and neck tumor pathological section sample to obtain a corresponding pixel-level immunohistochemical index. The pixel-level immunohistochemical index includes epithelium, stroma, negative, weakly positive, and strongly positive.

[0059] The training module is configured to input the hyperspectral image corresponding to each head and neck tumor pathological section sample into a preset deep learning classification framework, train the head and neck tumor pathological section sample corresponding to the immunohistochemical index as a label, and obtain an immunohistochemical index prediction model. The preset deep learning classification framework is a lightweight encoder-decoder network architecture integrated with a band selection strategy, an adaptive local and global feature fusion strategy, and an adaptive channel fusion strategy.

[0060] The prediction module is configured to input the hyperspectral image corresponding to the head and neck tumor pathological section to be detected into the immunohistochemical index prediction model for prediction to obtain a corresponding pixel-level immunohistochemical index.

[0061] In an exemplary embodiment, a computer device, which can be a server or a terminal, has an internal structure as shown in Figure 4 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured 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, a computer program, and a database. 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 configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement the method for realizing immunohistochemical classification of head and neck tumors by using hyperspectral imaging.

[0062] Those skilled in the art can understand that, Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above method embodiments.

[0063] In an exemplary embodiment, a computer readable storage medium is provided, storing a computer program, which is executed by a processor to implement the steps in the above method embodiments.

[0064] In an exemplary embodiment, a computer program product is provided, including a computer program, which is executed by a processor to implement the steps in the above method embodiments.

[0065] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0066] 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. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to a memory, a database or other medium used in the embodiments provided in the present application can include at least one of a non-volatile and a volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive random access memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric random access memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0067] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0068] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0069] The principles and implementation modes of the present application are described by using specific examples in the present application. The above embodiments are only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range can be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A method for immunohistochemical classification of head and neck tumors using hyperspectral imaging, characterized in that: The method for realizing immunohistochemical classification of head and neck tumors using hyperspectral imaging comprises: Acquire multiple head and neck tumor pathology slide samples and corresponding hyperspectral images; Annotating the hyperspectral image corresponding to each head and neck tumor pathology section sample to obtain corresponding pixel-level immunohistochemical indicators; the pixel-level immunohistochemical indicators include epithelial, stromal, negative, weakly positive, and strongly positive; The hyperspectral image corresponding to each head and neck tumor pathology section sample is input into a preset deep learning classification framework, and the pixel-level immunohistochemical index corresponding to the head and neck tumor pathology section sample is used as a label for training to obtain an immunohistochemical index prediction model; wherein the preset deep learning classification framework is a lightweight encoder-decoder network architecture that integrates a band selection strategy, an adaptive local and global feature fusion strategy, and an adaptive channel fusion strategy; The preset deep learning classification framework includes an encoder network architecture, an adaptive local and global feature fusion layer, and a decoder network architecture arranged in sequence; the encoder network architecture includes a band selection layer, a first encoding layer, a second encoding layer, and a third encoding layer arranged in sequence; the decoder network architecture includes a third decoding layer, a second decoding layer, a first decoding layer, and an output layer arranged in sequence; the first encoding layer is jump-connected to the first decoding layer, the second encoding layer is jump-connected to the second decoding layer, and the third encoding layer is jump-connected to the third decoding layer; the first encoding layer, the second encoding layer, and the third encoding layer each include a spatial spectrum attention layer and a first convolutional layer arranged in sequence; the first decoding layer, the second decoding layer, and the third decoding layer each include a second convolutional layer and a spatial semantic fusion layer arranged in sequence; wherein the band selection layer is used to: perform band screening on the received hyperspectral image using a band selection algorithm based on maximum quality to obtain a significant band subset, and then perform convolution processing to obtain spectral features; The hyperspectral image corresponding to the head and neck tumor pathological section to be detected is input into the immunohistochemical index prediction model for prediction to obtain the corresponding pixel-level immunohistochemical index.

2. The method for realizing immunohistochemical classification of head and neck tumors using hyperspectral analysis according to claim 1, characterized in that: The negative reference image indicates that the staining intensity of any pixel is within a first preset range; the weakly positive reference image indicates that the staining intensity of any pixel is within a second preset range; the strong positive reference image indicates that the staining intensity of any pixel is within a third preset range; the pixels in the stroma and the epithelium reference image are different from the tissue categories in which the pixels stained by immunohistochemistry are located.

3. The method for realizing immunohistochemical classification of head and neck tumors using hyperspectral analysis according to claim 1, characterized in that: The step of annotating the hyperspectral image corresponding to each head and neck tumor pathology section sample includes: ENVI5.6 was used to annotate each pixel in the hyperspectral image corresponding to the head and neck tumor pathological section sample to obtain the pixel-level immunohistochemical index corresponding to each pixel; the number of pixels corresponding to different categories of pixel-level immunohistochemical indexes was counted.

4. The method for realizing immunohistochemical classification of head and neck tumors using hyperspectral analysis according to claim 1, wherein: The process of obtaining multiple head and neck tumor pathology section samples includes: obtaining multiple head and neck tumor pathology sections with different immunohistochemical characteristics and screening them to obtain multiple head and neck tumor pathology section samples.

5. The method for realizing immunohistochemical classification of head and neck tumors using hyperspectral analysis according to claim 1, characterized in that: The process of acquiring the hyperspectral image corresponding to the head and neck tumor pathological section sample includes: Assembling a hyperspectral microscopic imaging system; the hyperspectral microscopic imaging system includes a microscope, a scanning acquisition component and a halogen illumination source; Placing the head and neck tumor pathology section sample on the stage of the microscope, irradiating the head and neck tumor pathology section sample with the halogen illumination source, and automatically focusing the microscope while collecting multi-band spectral information through the scanning and acquisition component to obtain an initial hyperspectral image; The initial hyperspectral image is subjected to black and white calibration and normalization processing to obtain a hyperspectral image corresponding to the head and neck tumor pathological section sample.

6. The method for realizing immunohistochemical classification of head and neck tumors using hyperspectral analysis according to claim 5, characterized in that: When performing black and white calibration normalization processing on the initial hyperspectral image, the following formula is used: Among them, Iref is the reflection spectrum intensity value obtained after black and white calibration normalization processing, Iraw is the reflection spectrum intensity value in the initial hyperspectral image, Idark is the dark current reference intensity, and Iwhite is the total reflection reference intensity.

7. A system for immunohistochemical classification of head and neck tumors using hyperspectral imaging, applied to the method for immunohistochemical classification of head and neck tumors using hyperspectral imaging according to any one of claims 1 to 6, characterized in that: The system for realizing immunohistochemical classification of head and neck tumors using hyperspectral imaging comprises: An acquisition module is used to: acquire multiple head and neck tumor pathology slice samples and corresponding hyperspectral images; A labeling module is used to label the hyperspectral image corresponding to each head and neck tumor pathology section sample to obtain corresponding pixel-level immunohistochemical indicators; the pixel-level immunohistochemical indicators include epithelial, interstitial, negative, weakly positive and strongly positive; A training module is configured to input the hyperspectral image corresponding to each head and neck tumor pathology section sample into a preset deep learning classification framework, and train the model using the immunohistochemical indices corresponding to the head and neck tumor pathology section sample as labels to obtain an immunohistochemical indices prediction model; wherein the preset deep learning classification framework is a lightweight encoder-decoder network architecture that integrates a band selection strategy, an adaptive local and global feature fusion strategy, and an adaptive channel fusion strategy; The prediction module is used to input the hyperspectral image corresponding to the head and neck tumor pathological section to be detected into the immunohistochemical index prediction model for prediction to obtain the corresponding pixel-level immunohistochemical index.

Images