CN118279273A - Three-level lymphatic structure recognition model construction and recognition method based on image registration - Google Patents

Abstract

The embodiment of the present invention discloses a method for constructing a three-level lymphatic structure recognition model based on image registration, wherein the construction method comprises: using an edge detection algorithm to detect the edges of each HE image and fluorescence image, and performing coarse registration according to the detected edge information; dividing each coarsely registered HE image and fluorescence image into a plurality of image blocks, performing fine registration on each image block and solving the fine registration matrix of the HE image; cascading the coarse registration matrix and the fine registration matrix of each HE image into a total registration matrix, and registering the three-level lymphatic structure mask of each fluorescence image according to each total registration matrix to obtain the three-level lymphatic structure mask of each HE image; taking each HE image as input and the three-level lymphatic structure mask of each HE image as output, training a target detection model based on a neural network, and using the trained target detection model as a three-level lymphatic structure recognition model.

Description

Construction of three-level lymphatic structure recognition model and recognition method based on image registration

Technical Field

The embodiments of the present invention relate to the technical field of medical image processing, and in particular to a three-level lymphatic structure recognition model construction and recognition method based on image registration.

Background technique

In immunology, tertiary lymphatic structures are closely related to the formulation of treatment plans for patients and the prognosis of treatment. At present, it is very difficult to identify tertiary lymphatic structures in HE images. The gold standard is obtained by manual identification of immunofluorescence images. Immunofluorescence imaging itself has high processing costs, while HE imaging is low-cost and easy to obtain. Therefore, an image processing method is needed to identify tertiary lymphatic structures in HE images.

Summary of the invention

The embodiment of the present invention provides a three-level lymphatic structure recognition model construction and recognition method based on image registration to solve the above technical problems.

In a first aspect, an embodiment of the present invention provides a method for constructing a three-level lymphatic structure recognition model based on image registration, comprising:

Acquire multiple HE images including the third-level lymphatic structures and corresponding fluorescence images;

An edge detection algorithm is used to detect the edges of each HE image and the fluorescence image, and each HE image and the corresponding fluorescence image are roughly registered according to the detected edge information;

The HE images and the fluorescence images after the rough registration are divided into a plurality of image blocks respectively, each HE image block is finely registered with the corresponding fluorescence image block, and a fine registration matrix of the HE image is solved according to the fine registration matrix of each HE image block in the same HE image;

The coarse registration matrix and the fine registration matrix of each HE image are cascaded into a total registration matrix, and the three-level lymphatic structure mask of each fluorescence image is registered according to each total registration matrix to obtain the three-level lymphatic structure mask of each HE image;

With each HE image as input and the three-level lymphatic structure mask of each HE image as output, a neural network-based object detection model is trained, and the trained object detection model is used as a three-level lymphatic structure recognition model.

In a second aspect, an embodiment of the present invention provides a three-level lymphatic structure recognition method based on image registration, comprising:

Acquire a HE image to be identified;

Using the three-level lymphatic structure recognition model constructed by the above method, the HE image to be recognized is processed to obtain a three-level lymphatic structure mask of the HE image;

A HE image of the three-level lymphatic structure is generated according to the three-level lymphatic structure mask and the HE image.

In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

one or more processors;

a memory for storing one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the three-level lymphatic structure recognition model construction method based on image registration, or the three-level lymphatic structure recognition method based on image registration described in any embodiment.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for constructing a three-level lymphatic structure recognition model based on image registration, or the three-level lymphatic structure recognition method based on image registration described in any embodiment.

The embodiment of the present invention provides a three-level lymphatic structure recognition model construction and recognition method based on image registration, which is mainly used for sub-pixel level registration of pathological HE images and immunofluorescence images and automatic detection of three-level lymphatic structures, providing an algorithm and software basis for doctors' clinical diagnosis. Specifically, a HE image and immunofluorescence image pairing database is first constructed, and then the HE and immunofluorescence images are automatically registered at the sub-pixel level from coarse to fine, and the three-level lymphatic structure mask in the HE image is obtained according to the registration matrix. The target detection model obtained based on the mask and HE image training can automatically identify the three-level lymphatic structure in the HE image. The whole process does not require manual intervention, ensuring the efficiency and accuracy of pathological structure recognition. The morphology, quantity and other characteristics of the three-level lymphatic structure detected by the pathological HE image can provide a reliable reference for the prediction of clinical treatment efficacy, formulation of treatment strategies, and prediction of prognosis effects of patients.

More specifically, in response to the time-consuming and laborious problem of manual registration of traditional fluorescence images and HE images or naked-eye observation by doctors, this embodiment proposes a coarse-to-fine automatic registration method, which can achieve relatively fine registration, sufficient to cope with the recognition of sub-pixel pathological structures such as tertiary lymphatic structures. At the same time, a YOLO v5 target detection model is established based on the automatic registration results to identify the tertiary lymphatic structure area from the HE image, avoiding subjective differences and labor consuming caused by manual delineation of the region of interest, registration, and manual extraction of parameter features.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

FIG1 is a flow chart of a method for constructing a three-level lymphatic structure recognition model based on image registration provided by an embodiment of the present invention;

FIG2 is a schematic diagram of a HE and immunofluorescence paired database sample of the present invention;

3 is a flow chart of another method for constructing a three-level lymphatic structure recognition model based on image registration provided by an embodiment of the present invention;

FIG4 is a schematic diagram of the structure of a YOLO v5 model provided by an embodiment of the present invention;

FIG5 is a flow chart of a method for identifying three-level lymphatic structures based on image registration according to an embodiment of the present invention;

FIG6 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

As described in the background technology, there is an urgent need for an image processing method that can automatically identify the tertiary lymphatic structure in HE images. There are the following difficulties in automatically identifying the tertiary lymphatic structure from the HE image: 1) The specific location of the tertiary lymphatic structure in the HE image requires manual comparison of the immunofluorescence image and the HE image. Even if the manual comparison is performed, it is impossible to obtain a more detailed outline of the tertiary lymphatic structure on the HE image based on the immunofluorescence image. 2) The HE image and the immunofluorescence image of the corresponding slice are not naturally registered. Due to the washing of the dye and manual operation, the image will be offset and misaligned. Due to the large pixel resolution of the pathological image, manual registration is very difficult, and there are subjective differences, making it difficult to achieve the desired effect. Therefore, there is a need for a fully automatic image registration method that can achieve registration of HE and immunofluorescence images of different modalities without relying on manual guidance, thereby realizing accurate detection of the tertiary lymphatic structure on the HE image.

In view of the above difficulties, FIG1 is a flow chart of a method for constructing a three-level lymphatic structure recognition model based on image registration provided by an embodiment of the present invention. The method is executed by an electronic device and specifically includes the following steps:

S110 , acquiring a plurality of HE images including the third-level lymphatic structures and corresponding fluorescence images.

This step constructs a paired database of HE images and immunofluorescence images as a training set for the three-level lymphatic structure recognition model. In a specific embodiment, pathological sections of lung cancer patients can be collected first, and then HE staining and immunofluorescence treatment are performed in sequence, and the dye is washed off in the middle. During the processing, the integrity of the slices and the position offset are minimized to facilitate the registration and image processing in subsequent operations. By processing several patients through the above operations, a paired database including HE images and immunofluorescence images can be obtained, and each HE image and its corresponding fluorescence image are shown in Figure 2.

S120 , using an edge detection algorithm to detect the edges of each HE image and the fluorescence image, and performing a rough registration of each HE image and the corresponding fluorescence image according to the detected edge information.

This step is based on the established database, uses an edge detection algorithm to detect the slice edges of the HE image and the immunofluorescence image, and performs the first registration between each image pair based on the edge information, which is called image-level coarse registration. In a specific embodiment, the coarse registration may include the following steps:

Step 1: Process any HE image and the corresponding fluorescence image into two thumbnail grayscale images. Since the pixels of the HE image and the fluorescence image are very large, in order to reduce the data processing burden, the two images are first reduced to grayscale images of a certain size.

Step 2: Use the edge detection algorithm to process each thumbnail grayscale image to obtain the edge map of each thumbnail grayscale image. Optionally, the edge detection algorithm is a Sobel operator edge detection algorithm. For a given two-dimensional grayscale image I, the Sobel operator calculates the gradients in the horizontal and vertical directions through convolution operations, which are represented by G _x and G _y respectively. The combination of these two gradients can obtain the edge strength and direction, thereby completing the edge detection of the image. Specifically, the convolution kernel of the Sobel operator is as follows:

At each pixel in the image, I _x and I _y are used to represent the horizontal and vertical gradients at that point, respectively, and are obtained by the following calculation:

I _x =I*G _x

I _y =I*G _y

Where * represents the convolution operation. Then, the edge strength E can be calculated:

The gradient direction θ can be calculated by the following formula:

In this embodiment, the edge images of the HE pathology thumbnail and the immunofluorescence pathology thumbnail are denoted as o and g, respectively.

Step three, use a rigid registration algorithm to align the two edge images to obtain a coarse registration matrix. Optionally, first, use a rigid registration algorithm to align the two edge images to obtain a coarse registration matrix of the two edge images; then, enlarge the coarse registration matrix of the two edge images to the size of the HE image to obtain a coarse registration matrix of the HE image. In a specific embodiment, the rigid registration algorithm provided by the AntsPy library can be used to align o and g to obtain a coarse registration matrix denoted as M; the registered HE thumbnail O′=o@M, where @ represents the registration operation. The HE pathology original image is denoted as O, and according to the scaling factor α of O and O′, the registered HE original image is O″=O@(M#α), where # represents the scaling process of the registration matrix, and M#α is the coarse registration matrix of the HE image.

S130, dividing each of the roughly registered HE images and fluorescence images into a plurality of image blocks, performing fine registration on each HE image block and the corresponding fluorescence image block, and solving the fine registration matrix of the HE image according to the fine registration matrix of each HE image block in the same HE image.

This step performs fine registration at the image block level (or sub-pixel level fine registration) to extract finer image information. Optionally, after obtaining the fine registration matrix of each image block, firstly average the fine registration matrices of each HE image block in the same HE image; then, enlarge the averaged matrix to the size of the HE image as the fine registration matrix of the HE image.

In a specific embodiment, the registered HE pathology original image O″ and the immunofluorescence original image G can be firstly divided into n small image blocks p _O and p _G , with one-to-one position correspondence. Then, each pair of small image blocks is registered to obtain a fine registration matrix M′ of the n image blocks; and then the n matrices are averaged to obtain Finally, the scaling factor β is obtained according to the small image block and the HE pathology original image, and the HE image after two registrations is O″′＝O″@(M″#β), where M″#β is the fine registration matrix of the HE image.

S140 , concatenating the coarse registration matrix and the fine registration matrix of each HE image into a total registration matrix, and registering the three-level lymphatic structure mask of each fluorescence image according to each total registration matrix to obtain the three-level lymphatic structure mask of each HE image.

It can be known from S120 and S130 that O″′＝O″@(M″#β)＝O@(M#α)@(M″#β), wherein M#α is the coarse registration matrix of the HE image, and M″#β is the fine registration matrix of the HE image, then the registration operation of @(M#α)@(M″#β) corresponds to the total registration matrix. This registration matrix can automatically align the HE image and the immunofluorescence image from coarse to fine sub-pixel level without manual intervention, thereby ensuring the accuracy of the registration. More specifically, coarse refers to the rigid registration at the whole slice thumbnail level after image processing, and fine refers to the image after rigid registration continues to be rigidly registered at the small image block level, and the registration transformation matrix of each small image block is averaged to obtain the final registered image.

At the same time, the contour of the tertiary lymphatic structure can be manually drawn by the doctor on the fluorescent image, and the tertiary lymphatic structure mask of the fluorescent image can be obtained according to the contour. Then, the tertiary lymphatic structure mask is registered according to the total registration matrix to obtain the mask of the tertiary lymphatic structure in the HE image, which represents the position and contour of the tertiary lymphatic structure in the HE image.

S150, taking each HE image as input and the three-level lymphatic structure mask of each HE image as output, training a neural network-based target detection model, and using the trained target detection model as a three-level lymphatic structure recognition model.

In this step, the position and contour of the tertiary lymphatic structure in the HE image obtained in S140 are used as labels to train the target detection model based on the neural network, so that after any HE image to be identified is input into the trained target detection model, the model can output the position and contour (i.e., mask) of the tertiary lymphatic structure in the HE image, and the whole process is shown in Figure 3. Optionally, the target detection model is a YOLO v5 model, and the trained YOLO v5 model can automatically detect the tertiary lymphatic structure in the HE structure, ensuring efficient and accurate recognition of the pathological structure.

In a specific implementation, the specific structure of the YOLO v5 model is shown in FIG4. During training, the full slice data can be cut into smaller image data blocks, and then the HE image data block is used as input, and the three-level lymphatic structure mask in the data block is used as output to train the target detection model. The block data is convenient for being sent to the target detection network to identify the three-level lymphatic structure, and the full slice detection result can be obtained after the block detection results are summarized.

Based on the above three-level lymphatic structure recognition model, FIG5 is a flow chart of a three-level lymphatic structure recognition method based on image registration provided by an embodiment of the present invention. As shown in FIG5, the method includes:

S210: Acquire a HE image to be identified.

The image includes tertiary lymphatic structures and other tissues. This embodiment will accurately identify the tertiary lymphatic structures in the image.

S220 , using the three-level lymphatic structure recognition model constructed by the above method to process the HE image to be recognized, to obtain the three-level lymphatic structure mask in the HE image.

If the training phase involves cutting the whole slice data into smaller image data blocks for training, then in this step the HE image is also cut into smaller data blocks, which are respectively sent to the three-level lymphatic structure recognition model for recognition. The whole slice recognition result can be obtained by summarizing the block recognition results.

S230 , obtaining a HE image of the third-level lymphatic structure according to the third-level lymphatic structure mask and the HE image.

The final HE image has removed other tissues in the original image, and can more clearly display the morphology of the tertiary lymphatic structure.

In summary, the embodiment of the present invention discloses a three-level lymphatic structure recognition model construction and recognition method based on image registration, which is mainly used for sub-pixel level registration of pathological HE images and immunofluorescence images and automatic detection of three-level lymphatic structures, providing an algorithm and software basis for doctors' clinical diagnosis, etc. Specifically, a HE image and immunofluorescence image pairing database is first constructed, and then the HE and immunofluorescence images are automatically registered at the sub-pixel level from coarse to fine, and the three-level lymphatic structure mask in the HE image is obtained according to the registration matrix. The target detection model obtained based on the mask and HE image training can automatically identify the three-level lymphatic structure in the HE image. The whole process does not require manual intervention, which ensures the efficiency and accuracy of pathological structure recognition. The morphology, quantity and other characteristics of the three-level lymphatic structure detected by the pathological HE image can provide a reliable reference for the prediction of clinical treatment efficacy, formulation of treatment strategies, and prediction of prognosis effects of patients.

More specifically, in response to the time-consuming and laborious problem of manual registration of traditional fluorescence images and HE images or observation by the naked eye of doctors, this embodiment proposes a coarse-to-fine automatic registration method, which can achieve relatively fine registration, sufficient to cope with the recognition of sub-pixel pathological structures such as tertiary lymphatic structures. At the same time, a YOLO v5 target detection model is established based on the automatic registration results to identify the tertiary lymphatic structure area from the HE image, avoiding subjective differences and labor consuming caused by manual delineation of the region of interest, registration, and manual extraction of parameter features.

Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. As shown in Figure 6, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device can be one or more, and Figure 6 takes one processor 60 as an example; the processor 60, memory 61, input device 62 and output device 63 in the device can be connected via a bus or other means, and Figure 6 takes connection via a bus as an example.

The memory 61, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as the three-level lymphatic structure recognition model construction method based on image registration in the embodiment of the present invention, or the program instructions/modules corresponding to the three-level lymphatic structure recognition method based on image registration. The processor 60 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 61, that is, realizing the above-mentioned three-level lymphatic structure recognition model construction method based on image registration, or the three-level lymphatic structure recognition method based on image registration.

The memory 61 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 61 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 61 may further include a memory remotely arranged relative to the processor 60, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The input device 62 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 63 may include a display device such as a display screen.

An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any embodiment of the method for constructing a three-level lymphatic structure recognition model based on image registration, or the method for recognizing a three-level lymphatic structure based on image registration.

The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims (10)

1. The three-level lymphatic structure recognition model construction method based on image registration is characterized by comprising the following steps of:

Acquiring a plurality of HE images comprising a tertiary lymphoid structure and corresponding fluorescence images;

detecting the edges of each HE image and the fluorescent image by adopting an edge detection algorithm, and performing coarse registration on each HE image and the corresponding fluorescent image according to the detected edge information;

Dividing each rough registered HE image and fluorescent image into a plurality of image blocks, carrying out fine registration on each HE image block and corresponding fluorescent image block, and solving a fine registration matrix of each HE image block in the same HE image according to the fine registration matrix of each HE image block;

cascading the coarse registration matrix and the fine registration matrix of each HE image into total registration matrix, and registering the tertiary lymphoid structure mask of each fluorescent image according to each total registration matrix to obtain the tertiary lymphoid structure mask of each HE image;

and taking each HE image as input, taking the tertiary lymphoid structure mask of each HE image as output, training a target detection model based on a neural network, and taking the trained target detection model as a tertiary lymphoid structure recognition model.

2. The method of claim 1, wherein detecting edges of each HE image and the fluorescent image using an edge detection algorithm and coarsely registering each HE image and the corresponding fluorescent image based on the detected edge information comprises:

processing any HE image and the corresponding fluorescence image into two thumbnail gray-scale images respectively;

processing each thumbnail gray level image by using an edge detection algorithm to obtain each edge image;

And registering the two edge maps by using a rigid registration algorithm to obtain a coarse registration matrix.

3. The method of claim 2, wherein registering the two edge maps using a rigid registration algorithm results in a coarse registration matrix, comprising:

Registering the two edge maps by using a rigid registration algorithm to obtain a coarse registration matrix of the two edge maps;

and amplifying the coarse registration matrix of the two edge maps to the size of the HE image to obtain the coarse registration matrix of the HE image.

4. The method of claim 1, wherein the solving the fine registration matrix of the HE image from the fine registration matrix of each HE image block in the same HE image comprises:

Averaging the fine registration matrix of each HE image block in the same HE image;

And amplifying the average matrix to the size of the HE image to serve as a fine registration matrix of the HE image.

5. The method of claim 1, further comprising, prior to said registering the tertiary lymphoid structure mask for each fluoroscopic image according to each total registration matrix:

And obtaining the tertiary lymphatic structure mask of the fluorescence image according to the tertiary lymphatic structure outline manually drawn in any fluorescence image.

6. The method of claim 1, wherein the object detection model is a YOLO v5 model.

7. The method of claim 1, wherein the edge detection algorithm is a Sobel operator edge detection algorithm.

8. A three-level lymphatic structure identification method based on image registration, which is characterized by comprising the following steps:

Acquiring an HE image to be identified;

Processing the HE image to be identified by using the three-level lymphatic structure identification model constructed by the method of any one of claims 1-7 to obtain a three-level lymphatic structure mask of the HE image;

and generating HE images of the tertiary lymphoid structure according to the tertiary lymphoid structure mask and the HE images.

9. An electronic device, comprising:

one or more processors;

A memory for storing one or more programs,

The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the image registration-based tertiary lymphoid structure identification model construction method of any one of claims 1-7, or the image registration-based tertiary lymphoid structure identification method of claim 8.

10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the image registration-based tertiary lymphoid structure identification model construction method according to any one of claims 1-7, or the image registration-based tertiary lymphoid structure identification method according to claim 8.