An immune scoring prediction method for advanced lung cancer

Abstract

The present invention discloses a method for predicting the immune score of advanced lung cancer. The method comprises: obtaining slice image data of biological tissue of a patient to be predicted for lung cancer; improving the quality of the slice image data based on a neural network algorithm to obtain optimized image data; inputting the optimized image data into a feature extraction model to obtain a corresponding image feature vector; inputting the image feature vector into a trained immune therapy score prediction neural network to obtain the corresponding immune therapy effect of the patient to be predicted for lung cancer; the immune therapy score prediction neural network is trained using a training data set including multiple training tissue slice images and corresponding immune therapy score annotations. It can be seen that the present invention can achieve accurate immune therapy prediction directly based on images, reduce prediction costs, and improve prediction efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for predicting the effect of immunotherapy for lung cancer. Background Art

[0002] Lung cancer is one of the malignant tumors with the highest morbidity and mortality rates worldwide, accounting for approximately one-eighth of global cancer cases. As people pay more attention to their health, how to effectively treat lung cancer has become an important focus, especially how to effectively predict the prognosis of lung cancer treatment. In recent years, lung cancer treatment technology has continued to advance. With the emergence of immunotherapy technology, the survival rate of lung cancer patients has also been significantly improved. Existing technologies have also begun to use the immune microenvironment of tumors to predict the immunotherapy effect of lung cancer patients. However, when predicting the immunotherapy effect of lung cancer patients, existing technologies do not consider combining pathological image analysis and neural network models to improve the accuracy of predictions. In addition, some existing technologies that use gene signature methods are also expensive and inconvenient. It can be seen that the existing technologies have defects that need to be addressed urgently. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for predicting the effect of lung cancer immunotherapy, which can achieve accurate immunotherapy prediction directly based on images, reduce prediction costs, and improve prediction efficiency and accuracy.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for predicting the effect of lung cancer immunotherapy, the method comprising:

[0005] Acquire slice image data of biological tissue of a patient to be diagnosed with lung cancer;

[0006] Improving the quality of the slice image data based on a neural network algorithm to obtain optimized image data;

[0007] Inputting the optimized image data into a feature extraction model to obtain a corresponding image feature vector;

[0008] The image feature vector is input into a trained immunotherapy score prediction neural network to obtain the corresponding immunotherapy effect of the lung cancer patient to be predicted; the immunotherapy score prediction neural network is trained by a training data set including multiple training tissue section images and corresponding immunotherapy score annotations.

[0009] As an optional embodiment, in the first aspect of the present invention, the quality improvement of the slice image data based on the neural network algorithm to obtain optimized image data includes:

[0010] The slice image data belonging to the FS image is input into a trained image conversion model to obtain output FFPE-style optimized image data; the image conversion model is trained by a training data set including multiple training FS images and corresponding FFPE-style image annotations.

[0011] As an optional implementation, in the first aspect of the present invention, the feature extraction model is a Phikon model.

[0012] As an optional embodiment, in the first aspect of the present invention, inputting the image feature vector into a trained immunotherapy score prediction neural network to obtain the immunotherapy effect corresponding to the lung cancer patient to be predicted includes:

[0013] Inputting the image feature vector into a plurality of trained immunotherapy score prediction neural networks to obtain a therapeutic effect prediction result of each immunotherapy score prediction neural network for the image feature vector;

[0014] Calculating the average of all the efficacy prediction results to obtain an average efficacy parameter;

[0015] The immunotherapy effect corresponding to the lung cancer patient to be predicted is determined based on the average efficacy parameter and a preset judgment threshold.

[0016] As an optional embodiment, in the first aspect of the present invention, the immunotherapy score prediction neural network includes an input layer, a Transformer encoder, a fully connected layer and a classification probability output layer connected in sequence.

[0017] As an optional embodiment, in the first aspect of the present invention, the immunotherapy score prediction neural network is trained based on the LA-MIL method and optimized by the AdamW optimizer. The initial learning rate is set to 2e-05 and gradually adjusted within 20 training cycles. The batch size is set to 1, and the weighted binary cross entropy loss function is used. After each training cycle, the F1 score on the validation dataset is calculated and the model weight with the highest F1 score is selected for saving. Multiple trained immunotherapy score prediction neural networks are obtained through multi-fold training and cross-validation.

[0018] As an optional embodiment, in the first aspect of the present invention, inputting the optimized image data into a feature extraction model to obtain a corresponding image feature vector includes:

[0019] Acquiring patient information of the lung cancer patient to be predicted;

[0020] Inputting the patient information into the trained LLM model to obtain corresponding cancer type information;

[0021] Determining an image segmentation model corresponding to the cancer type information from a preset image segmentation model library; the image segmentation model is trained based on a training data set including a plurality of training case images corresponding to the cancer type information and core image region annotations;

[0022] Inputting the optimized image data into the image segmentation model to obtain a key area image corresponding to the optimized image data;

[0023] Determining a feature extraction model corresponding to the cancer type information in a preset feature extraction model library; the feature extraction model is trained based on a training pathology image corresponding to the cancer type information;

[0024] The key area image is input into the feature extraction model to obtain a corresponding image feature vector.

[0025] As an optional embodiment, in the first aspect of the present invention, the immunotherapy score annotation is determined by the following steps:

[0026] Acquiring tissue sample data corresponding to the training tissue slice image;

[0027] Determining the immune infiltration score corresponding to the tissue sample data based on the immune infiltration score model;

[0028] Calculating a weighted sum average of the immune infiltration scores corresponding to all the training tissue section images to obtain a score reference value; wherein the weighted calculation weight corresponding to each immune infiltration score includes a first weight and a second weight; the first weight is proportional to an image clarity parameter corresponding to the training tissue section image; the second weight is proportional to a score reliability parameter corresponding to the training tissue section image; the score reliability parameter is the similarity between patient data corresponding to the tissue sample data corresponding to the training tissue section image and patient data corresponding to the model comparison sample data of the immune infiltration score model;

[0029] The immunotherapy score label corresponding to the training tissue section image is determined according to a comparison result between the immune infiltration score and the score reference value.

[0030] A second aspect of an embodiment of the present invention discloses a system for predicting the effect of lung cancer immunotherapy, the system comprising:

[0031] An image acquisition module is used to acquire slice image data of biological tissue of a patient to be diagnosed with lung cancer;

[0032] a quality optimization module, configured to improve the quality of the slice image data based on a neural network algorithm to obtain optimized image data;

[0033] a feature extraction module, configured to input the optimized image data into a feature extraction model to obtain a corresponding image feature vector;

[0034] The efficacy prediction module is used to input the image feature vector into a trained immunotherapy score prediction neural network to obtain the corresponding immunotherapy effect of the lung cancer patient to be predicted; the immunotherapy score prediction neural network is trained by a training data set including multiple training tissue slice images and corresponding immunotherapy score annotations.

[0035] As an optional embodiment, in the second aspect of the present invention, the quality optimization module improves the quality of the slice image data based on a neural network algorithm to obtain a specific method for optimizing the image data, including:

[0036] The slice image data belonging to the FS image is input into a trained image conversion model to obtain output FFPE-style optimized image data; the image conversion model is trained by a training data set including multiple training FS images and corresponding FFPE-style image annotations.

[0037] As an optional implementation, in the second aspect of the present invention, the feature extraction model is a Phikon model.

[0038] As an optional embodiment, in the second aspect of the present invention, the efficacy prediction module inputs the image feature vector into a trained immunotherapy score prediction neural network to obtain the specific method of the immunotherapy effect corresponding to the lung cancer patient to be predicted, including:

[0039] Inputting the image feature vector into a plurality of trained immunotherapy score prediction neural networks to obtain a therapeutic effect prediction result of each immunotherapy score prediction neural network for the image feature vector;

[0040] Calculating the average of all the efficacy prediction results to obtain an average efficacy parameter;

[0041] The immunotherapy effect corresponding to the lung cancer patient to be predicted is determined based on the average efficacy parameter and a preset judgment threshold.

[0042] As an optional embodiment, in the second aspect of the present invention, the immunotherapy score prediction neural network includes an input layer, a Transformer encoder, a fully connected layer and a classification probability output layer connected in sequence.

[0043] As an optional embodiment, in the second aspect of the present invention, the immunotherapy score prediction neural network is trained based on the LA-MIL method and optimized by the AdamW optimizer. The initial learning rate is set to 2e-05 and gradually adjusted within 20 training cycles. The batch size is set to 1, and the weighted binary cross entropy loss function is used. After each training cycle, the F1 score on the validation dataset is calculated and the model weight with the highest F1 score is selected for saving. Multiple trained immunotherapy score prediction neural networks are obtained through multi-fold training and cross-validation.

[0044] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the feature extraction module inputs the optimized image data into the feature extraction model to obtain the corresponding image feature vector includes:

[0045] Acquiring patient information of the lung cancer patient to be predicted;

[0046] Inputting the patient information into the trained LLM model to obtain corresponding cancer type information;

[0047] Determining an image segmentation model corresponding to the cancer type information from a preset image segmentation model library; the image segmentation model is trained based on a training data set including a plurality of training case images corresponding to the cancer type information and core image region annotations;

[0048] Inputting the optimized image data into the image segmentation model to obtain a key area image corresponding to the optimized image data;

[0049] Determining a feature extraction model corresponding to the cancer type information in a preset feature extraction model library; the feature extraction model is trained based on a training pathology image corresponding to the cancer type information;

[0050] The key area image is input into the feature extraction model to obtain a corresponding image feature vector.

[0051] As an optional embodiment, in the second aspect of the present invention, the immunotherapy score annotation is determined by the following steps:

[0052] Acquiring tissue sample data corresponding to the training tissue slice image;

[0053] Determining the immune infiltration score corresponding to the tissue sample data based on the immune infiltration score model;

[0054] Calculating a weighted sum average of the immune infiltration scores corresponding to all the training tissue section images to obtain a score reference value; wherein the weighted calculation weight corresponding to each immune infiltration score includes a first weight and a second weight; the first weight is proportional to an image clarity parameter corresponding to the training tissue section image; the second weight is proportional to a score reliability parameter corresponding to the training tissue section image; the score reliability parameter is the similarity between patient data corresponding to the tissue sample data corresponding to the training tissue section image and patient data corresponding to the model comparison sample data of the immune infiltration score model;

[0055] The immunotherapy score label corresponding to the training tissue section image is determined according to a comparison result between the immune infiltration score and the score reference value.

[0056] The third aspect of the present invention discloses another lung cancer immunotherapy effect prediction system, the system comprising:

[0057] a memory storing executable program code;

[0058] a processor coupled to the memory;

[0059] The processor calls the executable program code stored in the memory to execute part or all of the steps in the method for predicting the effect of lung cancer immunotherapy disclosed in the first aspect of the present invention.

[0060] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the method for predicting the effect of lung cancer immunotherapy disclosed in the first aspect of the present invention.

[0061] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0062] The present invention can improve the quality of slice image data according to the neural network algorithm to obtain optimized image data, and then obtain the corresponding image feature vector based on the feature extraction model. Finally, the trained immunotherapy score prediction neural network is used to accurately predict the corresponding immunotherapy effect score of lung cancer patients, thereby realizing accurate immunotherapy prediction directly based on images, reducing prediction costs, and improving prediction efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0064] Figure 1 This is a flow chart of a method for predicting the effect of lung cancer immunotherapy disclosed in an embodiment of the present invention.

[0065] Figure 2 This is a schematic structural diagram of a lung cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention.

[0066] Figure 3 This is a schematic diagram of the structure of another lung cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention.

[0067] Figure 4 This is a schematic diagram of an algorithm flow of a lung cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0069] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0070] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0071] Before describing the specific embodiments of the present invention, the technical background of the present invention will be further described:

[0072] Lung cancer is one of the most morbid and fatal malignancies worldwide, accounting for approximately one-eighth of cancer cases worldwide. Non-small cell lung cancer (NSCLC) accounts for approximately 85% of all lung cancer types, and most NSCLC patients are diagnosed at an advanced stage. Despite recent advances in lung cancer treatment, the prognosis for patients with advanced NSCLC remains dismal. This is primarily due to the limited efficacy of traditional treatments (such as chemotherapy and radiotherapy) for advanced lung cancer, and the fact that most patients fail to achieve long-term survival benefits despite treatment. The emergence of immune checkpoint inhibitors (ICIs) has transformed the treatment paradigm for NSCLC and offered new therapeutic hope for patients with advanced non-squamous NSCLC. Studies have shown that ICIs significantly improve patient survival compared to traditional chemotherapy. Previous studies have further demonstrated that combining chemotherapy with immunotherapy in the first-line setting can significantly improve survival in patients with non-squamous NSCLC, with a tolerable toxicity profile. However, despite the encouraging response rates of chemotherapy combined with immunotherapy, the proportion of patients who achieve long-term survival benefits remains low, creating an urgent need for more accurate biomarkers to predict patient treatment responses and clinical outcomes. Currently, biomarkers such as PD-L1 expression and tumor mutation burden (TMB) have been widely used to predict the efficacy of immunotherapy, but their predictive accuracy is affected by the overlap between responders and non-responders, and therefore their clinical application is still limited.

[0073] Although existing technologies have made some progress in predicting immunotherapy responses in lung cancer, especially in advanced non-small cell lung cancer (NSCLC), they still have several significant shortcomings:

[0074] 1. Limitations of Biomarkers: While the main biomarkers currently used to predict immunotherapy responses, such as PD-L1 expression and tumor mutation burden (TMB), can guide clinical decision-making to a certain extent, their predictive power is affected by the overlap between responders and non-responders, making it impossible to accurately distinguish which patients will benefit from immunotherapy. This imprecision limits their widespread clinical application.

[0075] 2. Challenges in the Clinical Application of Gene Signatures: While gene signatures can provide important information about the tumor immune microenvironment, their evaluation process is complex and costly, making them difficult to widely apply in clinical practice. Furthermore, the evaluation of gene signatures requires specialized equipment and technical support, which limits their clinical promotion and use.

[0076] 3. Limitations of Computational Pathology Applications: Although computational pathology has shown promise in analyzing pathology slide images and predicting clinical outcomes, current research remains in its early stages. In particular, research and application in identifying NSCLC patient subgroups that may benefit from combined chemotherapy and immunotherapy are limited. Consequently, the application of computational pathology in clinical treatment decision-making has yet to be fully validated and widely accepted.

[0077] The present invention discloses a method and system for predicting the immunotherapy effect of lung cancer. This method improves the quality of slice image data using a neural network algorithm to obtain optimized image data, then uses a feature extraction model to obtain corresponding image feature vectors. Finally, a trained immunotherapy score prediction neural network is used to accurately predict the immunotherapy effect score for lung cancer patients. This method enables accurate immunotherapy prediction directly based on images, reduces prediction costs, and improves prediction efficiency and accuracy. These are described in detail below.

[0078] Example 1

[0079] See also Figure 1 , Figure 1 This is a flow chart of a method for predicting the effect of lung cancer immunotherapy disclosed in an embodiment of the present invention. Figure 1 The described lung cancer immunotherapy effect prediction method can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the method for predicting the effect of lung cancer immunotherapy may include the following operations:

[0080] 101. Obtain slice image data of biological tissue of a patient whose lung cancer is to be predicted.

[0081] 102. Based on the neural network algorithm, the quality of the slice image data is improved to obtain optimized image data.

[0082] 103. Input the optimized image data into a feature extraction model to obtain a corresponding image feature vector.

[0083] 104. Input the image feature vector into the trained immunotherapy score prediction neural network to obtain the corresponding immunotherapy effect of the lung cancer patient to be predicted.

[0084] Optionally, the immunotherapy score prediction neural network can be a support vector machine (SVM), a random forest (RandomForest), a fully convolutional neural network (FCN) or an XGBoost network.

[0085] Optionally, the immunotherapy score prediction neural network is trained using a training dataset comprising a plurality of training tissue slice images and corresponding immunotherapy score annotations.

[0086] It can be seen that the above-mentioned embodiment of the invention can improve the quality of slice image data according to the neural network algorithm to obtain optimized image data, and then obtain the corresponding image feature vector based on the feature extraction model, and finally accurately predict the corresponding immunotherapy effect score of lung cancer patients through the trained immunotherapy score prediction neural network, thereby realizing accurate immunotherapy prediction directly based on images, reducing prediction costs, and improving prediction efficiency and prediction accuracy.

[0087] As an optional embodiment, in the above steps, improving the quality of the slice image data based on a neural network algorithm to obtain optimized image data includes:

[0088] The slice image data belonging to the FS image is input into the trained image conversion model to obtain the output FFPE-style optimized image data; the image conversion model is trained by a training dataset including multiple training FS images and corresponding FFPE-style image annotations.

[0089] Optionally, the image conversion model can be the AI-FFPE model, a generative adversarial network (GAN)-based image style transfer method that converts frozen section (FS) images to the style of formalin-fixed paraffin-embedded (FFPE) images. This conversion improves the image quality of frozen sections, making them more stable and accurate in subsequent analysis.

[0090] It can be seen that through the above optional embodiments, the slice image data belonging to the FS image can be converted into better quality FFPE-style optimized image data based on the trained image conversion model to improve the image quality, thereby assisting in achieving accurate immunotherapy prediction directly based on the image, reducing prediction costs, and improving prediction efficiency and accuracy.

[0091] As an optional embodiment, in the above steps, the feature extraction model is a Phikon model.

[0092] It can be seen that through the above optional embodiments, the sufficient extraction of image features through the Phikon model is limited to improve the accuracy of subsequent predictions, assist in achieving accurate immunotherapy predictions directly based on images, reduce prediction costs, and improve prediction efficiency and accuracy.

[0093] As an optional embodiment, in the above step, inputting the image feature vector into a trained immunotherapy score prediction neural network to obtain the corresponding immunotherapy effect of the lung cancer patient to be predicted includes:

[0094] Inputting the image feature vector into multiple trained immunotherapy score prediction neural networks to obtain the efficacy prediction results of each immunotherapy score prediction neural network for the image feature vector;

[0095] Calculate the average of all efficacy prediction results to obtain the average efficacy parameter;

[0096] Based on the average efficacy parameters and the preset judgment threshold, the corresponding immunotherapy effect of the lung cancer patient to be predicted is determined.

[0097] It can be seen that through the above optional embodiments, multiple trained immunotherapy score prediction neural networks can be used to predict multiple efficacy prediction results and perform average calculation and threshold judgment, thereby improving the accuracy of efficacy prediction, realizing accurate immunotherapy prediction directly based on images, reducing prediction costs, and improving prediction efficiency and prediction accuracy.

[0098] As an optional embodiment, in the above steps, the immunotherapy score prediction neural network includes an input layer, a Transformer encoder, a fully connected layer, and a classification probability output layer connected in sequence.

[0099] It can be seen that through the above optional embodiments, the network structure of the immunotherapy score prediction neural network is defined, which can be used to accurately predict the therapeutic effect, assist in realizing accurate immunotherapy prediction directly based on images, reduce prediction costs, and improve prediction efficiency and prediction accuracy.

[0100] As an optional embodiment, in the above steps, the immunotherapy score prediction neural network is trained based on the LA-MIL method and optimized by the AdamW optimizer. The initial learning rate is set to 2e-05 and gradually adjusted within 20 training cycles. The batch size is set to 1, and the weighted binary cross entropy loss function is used. After each training cycle, the F1 score on the validation dataset is calculated and the model weight with the highest F1 score is selected for saving. Multiple trained immunotherapy score prediction neural networks are obtained through multi-fold training and cross-validation.

[0101] It can be seen that through the above optional embodiments, the training details of the immunotherapy score prediction neural network are limited to train a neural network model with more accurate prediction effects, assist in realizing accurate immunotherapy prediction directly based on images, reduce prediction costs, and improve prediction efficiency and accuracy.

[0102] As an optional embodiment, in the above step, inputting the optimized image data into the feature extraction model to obtain the corresponding image feature vector includes:

[0103] Obtaining patient information of a patient whose lung cancer is to be predicted;

[0104] Input the patient information into the trained LLM model to obtain the corresponding cancer type information;

[0105] Determining an image segmentation model corresponding to the cancer type information from a preset image segmentation model library; optionally, the image segmentation model is trained based on a training dataset including training case images corresponding to a plurality of cancer type information and core image region annotations;

[0106] Inputting the optimized image data into the image segmentation model to obtain the key area image corresponding to the optimized image data;

[0107] Determining a feature extraction model corresponding to the cancer type information from a preset feature extraction model library; optionally, the feature extraction model is trained based on training pathology images corresponding to the cancer type information;

[0108] The key area image is input into the feature extraction model to obtain the corresponding image feature vector.

[0109] It can be seen that through the above optional embodiments, the cancer type can be determined based on the LLM model in combination with the patient's information, and then the corresponding image segmentation model and feature extraction model can be determined based on the screening of the corresponding type, so as to achieve more accurate image key area determination and feature extraction, and assist in realizing accurate immunotherapy prediction directly based on the image, reducing prediction costs, and improving prediction efficiency and accuracy.

[0110] As an optional embodiment, in the above steps, the immunotherapy score annotation is determined by the following steps:

[0111] Obtaining tissue sample data corresponding to the training tissue slice image;

[0112] Based on the immune infiltration scoring model, determine the immune infiltration score corresponding to the tissue sample data;

[0113] Calculating a weighted sum average of the immune infiltration scores corresponding to all training tissue section images to obtain a score reference value; optionally, the weighted calculation weight corresponding to each immune infiltration score includes a first weight and a second weight; the first weight is proportional to an image clarity parameter corresponding to the training tissue section image; the second weight is proportional to a score reliability parameter corresponding to the training tissue section image; the score reliability parameter is the similarity between patient data corresponding to tissue sample data corresponding to the training tissue section image and patient data corresponding to model comparison sample data of the immune infiltration score model;

[0114] Based on the comparison results between the immune infiltration score and the score reference value, the immunotherapy score annotation corresponding to the training tissue section image is determined.

[0115] It can be seen that through the above optional embodiments, the immune infiltration score of the tissue sample can be determined based on the immune infiltration score model, and then the appropriate score reference value can be determined based on the weighted sum average calculation, so as to finally obtain the accurate immunotherapy score annotation of the training sample, so that the trained immunotherapy score prediction neural network has higher prediction accuracy, assists in realizing accurate immunotherapy prediction directly based on images, reduces prediction costs, and improves prediction efficiency and prediction accuracy.

[0116] In a more specific embodiment, a computational pathology-based pathological immune score (PIS) system was developed to provide a more accurate and reliable biomarker for predicting clinical outcomes in patients with advanced non-squamous NSCLC after chemotherapy combined with immunotherapy. Its main objectives include:

[0117] 1. Improved prediction accuracy: By integrating pathological image analysis of tumor tissue with quantification of tumor immune microenvironment (TIME) characteristics, the pathological immunoscore (PIS) system of this invention can more accurately identify which patients with advanced non-squamous NSCLC may benefit from chemotherapy combined with immunotherapy, thereby improving the accuracy of treatment effect prediction.

[0118] 2. Reduced evaluation cost and complexity: Compared with the gene signature method, the PIS system of the present invention relies on computational pathology analysis, which not only simplifies the biomarker evaluation process but also reduces costs, making it easier to promote and apply in clinical practice.

[0119] 3. Enhanced convenience of clinical application: By leveraging the advantages of computational pathology, the PIS system of the present invention can provide additional immune scoring information on the basis of conventional pathological image analysis, thereby helping clinicians to formulate personalized treatment plans more conveniently.

[0120] The training and workflow of a scoring algorithm model for this case immune scoring system can be found in Figure 4 First, whole slide images (WSIs) from the Cancer Genome Atlas Lung Adenocarcinoma (TCGA-LUAD) dataset were used as training data. These WSIs included both formalin-fixed paraffin-embedded (FFPE) and frozen section (FS) samples. Because frozen section images are typically of low quality, potentially affecting subsequent analysis, a neural network algorithm, such as the AI-FFPE method, was used to convert FS sections into FFPE-style images.

[0121] To enhance the representativeness of the dataset, a total of 1,333 WSIs were obtained from the TCGA-LUAD dataset and randomly divided into three parts for model training and cross-validation. The included dataset contained adult patients with primary lung adenocarcinoma from the United States. The inclusion criteria for patients were: (1) the availability of digital hematoxylin and eosin (H&E) stained tissue sections of formalin-fixed paraffin-embedded (FFPE) samples; and (2) the availability of gene expression profile data based on RNA sequencing. After preliminary screening, a total of 515 patients' WSIs were included.

[0122] Specifically, the implementation scheme of the algorithm model in this embodiment includes:

[0123] Step 1: Obtain whole-slice images from the TCGA-LUAD dataset and perform data augmentation and preprocessing.

[0124] Step 2: Convert frozen sections (FS) to formalin-fixed paraffin-embedded (FFPE) style using the AI-FFPE method and generate image tiles.

[0125] Step 3: Use the Phikon model for feature extraction and use the LA-MIL method for model training.

[0126] Step 4: Model validation and survival analysis were performed on the CPTAC-LUAD and ORIENT-11 external cohorts.

[0127] Specifically, because WSIs are typically large and unsuitable for direct input into standard image classification models, a weakly supervised multiple instance learning (MIL) approach was employed to address this issue. First, a simple thresholding method was used to identify tissue regions within the WSIs. From these regions, a set of image patches was generated using a sliding window approach. Each patch was 224 x 224 pixels in size and extracted at two magnifications (20X: 0.5 µm / pixel, 10X: 1 µm / pixel) to encompass information from different scales.

[0128] Furthermore, after generating the image blocks, the Phikon model is used to extract features from each block. The Phikon model is a foundational model for pathology images. Pre-trained on over 40 million pan-cancer digital pathology image blocks, it can encode each image block into a 768-dimensional feature vector. To capture more detailed information within the image blocks, the 768-dimensional features extracted at two magnification levels are combined to form a 1536-dimensional feature vector for each image block. While this method uses the Phikon model as a feature extractor, other foundational models for pathology images can also be used for feature extraction of image blocks.

[0129] Next, the extracted features are trained using a transformer-based MIL method (Local Attention-MIL, LA-MIL) based on local self-attention maps for weak supervision. Unlike classic MIL methods, LA-MIL, through its inherent self-attention mechanism, can effectively model the interdependencies between image patches, particularly the local spatial relationships between adjacent patches. This method is particularly well-suited for histopathology image analysis because it focuses on local attention between image patches rather than global self-attention, making it more accurate when processing biopsy samples.

[0130] Specifically, the basic structure of LA-MIL is Transformer. It includes an input layer, which takes as input the feature vector of the aforementioned extracted tile sequence; a Transformer encoder, which is composed of multiple local self-attention layers and feedforward neural network layers. Compared with the usual self-attention layer, the local self-attention layer allows the model to focus only on its neighboring image blocks when processing each input image block; a classification head, which inputs the output of the Transformer encoder into a fully connected layer for further processing. The output of the last fully connected layer is converted into a binary classification probability through a softmax function. Among them, the neighboring tiles of each tile are determined using the k-nearest neighbor graph network method, and the specific number of k can be 16, 64 or 128.

[0131] The trained labels are binary labels after stratification based on the sample's ESTIMATE immune infiltration score. The ESTIMATE score is a scoring method that infers tumor cell composition, stromal and immune infiltration based on transcriptome data. This labeling can be calculated using the Immuno-Oncology Bioresearch (IOBR) R package software to calculate the ESTIMATE immune infiltration score for each sample. The samples are then classified into high and low categories using the median ESTIMATE immune infiltration score of the entire training set as the threshold. Alternatively, the weighted sum average threshold used in the above embodiment can be used to classify the samples.

[0132] During training, the AdamW optimizer was used, with an initial learning rate set to 2e-05 and gradually adjusted over 20 training epochs. The batch size was set to 1, and a weighted binary cross-entropy loss function was used to handle imbalanced data. To enhance model stability, the F1 score on the validation set was calculated after each training epoch, and the model weights with the highest F1 score were selected and saved. Ultimately, three-fold training and cross-validation produced three different models, each generating a classification probability output. The classification probabilities of the three models were averaged to obtain the final predicted probability. If the final predicted probability of a sample was greater than or equal to 50%, the sample was classified as PIS-high; if the final predicted probability was less than 50%, the sample was classified as PIS-low.

[0133] To further validate the clinical effectiveness of the PIS system, a survival analysis was conducted on the ORIENT-11 cohort. The accuracy of the PIS system in treatment prediction was verified by comparing the progression-free survival (PFS) and overall survival (OS) of patients with high and low ESTIMATE scores predicted by the model. The results showed that patients predicted to have high scores had significantly better survival than those predicted to have low scores, indicating that the PIS system can effectively predict the response to chemotherapy combined with immunotherapy in patients with advanced non-squamous NSCLC.

[0134] Example 2

[0135] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of a lung cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention. Figure 2 The lung cancer immunotherapy effect prediction system described can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the lung cancer immunotherapy effect prediction system may include:

[0136] The image acquisition module 201 is used to acquire slice image data of biological tissue of a patient whose lung cancer is to be predicted.

[0137] The quality optimization module 202 is used to improve the quality of the slice image data based on a neural network algorithm to obtain optimized image data.

[0138] The feature extraction module 203 is used to input the optimized image data into a feature extraction model to obtain a corresponding image feature vector.

[0139] The efficacy prediction module 204 is used to input the image feature vector into the trained immunotherapy score prediction neural network to obtain the corresponding immunotherapy effect of the lung cancer patient to be predicted.

[0140] Optionally, the immunotherapy score prediction neural network is trained using a training dataset comprising a plurality of training tissue slice images and corresponding immunotherapy score annotations.

[0141] It can be seen that the above-mentioned embodiment of the invention can improve the quality of slice image data according to the neural network algorithm to obtain optimized image data, and then obtain the corresponding image feature vector based on the feature extraction model, and finally accurately predict the corresponding immunotherapy effect score of lung cancer patients through the trained immunotherapy score prediction neural network, thereby realizing accurate immunotherapy prediction directly based on images, reducing prediction costs, and improving prediction efficiency and prediction accuracy.

[0142] As an optional embodiment, the quality optimization module improves the quality of the slice image data based on a neural network algorithm, and obtains a specific method of optimizing the image data, including:

[0143] The slice image data belonging to the FS image is input into the trained image conversion model to obtain the output FFPE-style optimized image data; the image conversion model is trained by a training dataset including multiple training FS images and corresponding FFPE-style image annotations.

[0144] It can be seen that through the above optional embodiments, the slice image data belonging to the FS image can be converted into better quality FFPE-style optimized image data based on the trained image conversion model to improve the image quality, thereby assisting in achieving accurate immunotherapy prediction directly based on the image, reducing prediction costs, and improving prediction efficiency and accuracy.

[0145] As an optional embodiment, the feature extraction model is a Phikon model.

[0146] It can be seen that through the above optional embodiments, the sufficient extraction of image features through the Phikon model is limited to improve the accuracy of subsequent predictions, assist in achieving accurate immunotherapy predictions directly based on images, reduce prediction costs, and improve prediction efficiency and accuracy.

[0147] As an optional embodiment, the efficacy prediction module inputs the image feature vector into a trained immunotherapy score prediction neural network to obtain a specific method for predicting the immunotherapy effect of the lung cancer patient, including:

[0148] Inputting the image feature vector into multiple trained immunotherapy score prediction neural networks to obtain the efficacy prediction results of each immunotherapy score prediction neural network for the image feature vector;

[0149] Calculate the average of all efficacy prediction results to obtain the average efficacy parameter;

[0150] Based on the average efficacy parameters and the preset judgment threshold, the corresponding immunotherapy effect of the lung cancer patient to be predicted is determined.

[0151] It can be seen that through the above optional embodiments, multiple trained immunotherapy score prediction neural networks can be used to predict multiple efficacy prediction results and perform average calculation and threshold judgment, thereby improving the accuracy of efficacy prediction, realizing accurate immunotherapy prediction directly based on images, reducing prediction costs, and improving prediction efficiency and prediction accuracy.

[0152] As an optional embodiment, the immunotherapy score prediction neural network includes an input layer, a Transformer encoder, a fully connected layer, and a classification probability output layer connected in sequence.

[0153] It can be seen that through the above optional embodiments, the network structure of the immunotherapy score prediction neural network is defined, which can be used to accurately predict the therapeutic effect, assist in realizing accurate immunotherapy prediction directly based on images, reduce prediction costs, and improve prediction efficiency and prediction accuracy.

[0154] As an optional embodiment, the immunotherapy score prediction neural network is trained based on the LA-MIL method and optimized by the AdamW optimizer. The initial learning rate is set to 2e-05 and gradually adjusted within 20 training cycles. The batch size is set to 1. The weighted binary cross entropy loss function is used. After each training cycle, the F1 score on the validation dataset is calculated and the model weight with the highest F1 score is selected for saving. Multiple trained immunotherapy score prediction neural networks are obtained through multi-fold training and cross-validation.

[0155] It can be seen that through the above optional embodiments, the training details of the immunotherapy score prediction neural network are limited to train a neural network model with more accurate prediction effects, assist in realizing accurate immunotherapy prediction directly based on images, reduce prediction costs, and improve prediction efficiency and accuracy.

[0156] As an optional embodiment, the feature extraction module inputs the optimized image data into the feature extraction model to obtain the corresponding image feature vector in a specific manner including:

[0157] Obtaining patient information of a patient whose lung cancer is to be predicted;

[0158] Input the patient information into the trained LLM model to obtain the corresponding cancer type information;

[0159] Determining an image segmentation model corresponding to the cancer type information from a preset image segmentation model library; optionally, the image segmentation model is trained based on a training dataset including training case images corresponding to a plurality of cancer type information and core image region annotations;

[0160] Inputting the optimized image data into the image segmentation model to obtain the key area image corresponding to the optimized image data;

[0161] Determining a feature extraction model corresponding to the cancer type information from a preset feature extraction model library; optionally, the feature extraction model is trained based on training pathology images corresponding to the cancer type information;

[0162] The key area image is input into the feature extraction model to obtain the corresponding image feature vector.

[0163] It can be seen that through the above optional embodiments, the cancer type can be determined based on the LLM model in combination with the patient's information, and then the corresponding image segmentation model and feature extraction model can be determined based on the screening of the corresponding type, so as to achieve more accurate image key area determination and feature extraction, and assist in realizing accurate immunotherapy prediction directly based on the image, reducing prediction costs, and improving prediction efficiency and accuracy.

[0164] As an optional embodiment, the immunotherapy score annotation is determined by the following steps:

[0165] Obtaining tissue sample data corresponding to the training tissue slice image;

[0166] Based on the immune infiltration scoring model, determine the immune infiltration score corresponding to the tissue sample data;

[0167] Calculating a weighted sum average of the immune infiltration scores corresponding to all training tissue section images to obtain a score reference value; optionally, the weighted calculation weight corresponding to each immune infiltration score includes a first weight and a second weight; the first weight is proportional to an image clarity parameter corresponding to the training tissue section image; the second weight is proportional to a score reliability parameter corresponding to the training tissue section image; the score reliability parameter is the similarity between patient data corresponding to tissue sample data corresponding to the training tissue section image and patient data corresponding to model comparison sample data of the immune infiltration score model;

[0168] Based on the comparison results between the immune infiltration score and the score reference value, the immunotherapy score annotation corresponding to the training tissue section image is determined.

[0169] It can be seen that through the above optional embodiments, the immune infiltration score of the tissue sample can be determined based on the immune infiltration score model, and then the appropriate score reference value can be determined based on the weighted sum average calculation, so as to finally obtain the accurate immunotherapy score annotation of the training sample, so that the trained immunotherapy score prediction neural network has higher prediction accuracy, assists in realizing accurate immunotherapy prediction directly based on images, reduces prediction costs, and improves prediction efficiency and prediction accuracy.

[0170] Example 3

[0171] See also Figure 3 , Figure 3 This is another lung cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention. Figure 3 The lung cancer immunotherapy effect prediction system described is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the lung cancer immunotherapy effect prediction system may include:

[0172] A memory 301 storing executable program code;

[0173] a processor 302 coupled to the memory 301;

[0174] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the method for predicting the effect of immunotherapy for lung cancer described in the first embodiment.

[0175] Example 4

[0176] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for predicting the effect of immunotherapy for lung cancer described in the first embodiment.

[0177] Example 5

[0178] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the method for predicting the effect of lung cancer immunotherapy described in Example 1.

[0179] The foregoing description of specific embodiments of the present disclosure is intended to illustrate a method for performing a multi-tasking process. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0180] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0181] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0182] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0183] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0184] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0185] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0186] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0187] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0188] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0189] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0190] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0191] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0192] Finally, it should be noted that the method and system for predicting the effect of immunotherapy for lung cancer disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for predicting the effect of lung cancer immunotherapy, characterized in that: The method comprises: Acquire slice image data of biological tissue of a patient to be diagnosed with lung cancer; Based on a neural network algorithm, the quality of the slice image data is improved to obtain optimized image data; Inputting the optimized image data into a feature extraction model to obtain a corresponding image feature vector; The image feature vector is input into a trained immunotherapy score prediction neural network to obtain the immunotherapy effect corresponding to the lung cancer patient to be predicted; the immunotherapy score prediction neural network is trained using a training data set including a plurality of training tissue section images and corresponding immunotherapy score annotations, and the immunotherapy score annotations are determined by the following steps: Acquiring tissue sample data corresponding to the training tissue slice image; Determining the immune infiltration score corresponding to the tissue sample data based on the immune infiltration score model; Calculating a weighted sum average of the immune infiltration scores corresponding to all the training tissue section images to obtain a score reference value; wherein the weighted calculation weight corresponding to each immune infiltration score includes a first weight and a second weight; the first weight is proportional to an image clarity parameter corresponding to the training tissue section image; the second weight is proportional to a score reliability parameter corresponding to the training tissue section image; the score reliability parameter is the similarity between patient data corresponding to the tissue sample data corresponding to the training tissue section image and patient data corresponding to the model comparison sample data of the immune infiltration score model; The immunotherapy score label corresponding to the training tissue section image is determined according to a comparison result between the immune infiltration score and the score reference value.

2. The method for predicting the effect of lung cancer immunotherapy according to claim 1, characterized in that: The step of improving the quality of the slice image data based on a neural network algorithm to obtain optimized image data includes: The slice image data belonging to the FS image is input into a trained image conversion model to obtain output FFPE-style optimized image data; the image conversion model is trained by a training data set including multiple training FS images and corresponding FFPE-style image annotations.

3. The method for predicting the effect of lung cancer immunotherapy according to claim 1, wherein: The feature extraction model is the Phikon model.

4. The method for predicting the effect of lung cancer immunotherapy according to claim 1, wherein: Inputting the image feature vector into a trained immunotherapy score prediction neural network to obtain the immunotherapy effect corresponding to the lung cancer patient to be predicted includes: Inputting the image feature vector into a plurality of trained immunotherapy score prediction neural networks to obtain a therapeutic effect prediction result of each immunotherapy score prediction neural network for the image feature vector; Calculating the average of all the efficacy prediction results to obtain an average efficacy parameter; The immunotherapy effect corresponding to the lung cancer patient to be predicted is determined based on the average efficacy parameter and a preset judgment threshold.

5. The method for predicting the effect of lung cancer immunotherapy according to claim 1, wherein: The immunotherapy score prediction neural network includes an input layer, a Transformer encoder, a fully connected layer, and a classification probability output layer connected in sequence.

6. The method for predicting the effect of lung cancer immunotherapy according to claim 4, characterized in that: The immunotherapy score prediction neural network was trained based on the LA-MIL method and optimized using the AdamW optimizer. The initial learning rate was set to 2e-05 and gradually adjusted within 20 training cycles. The batch size was set to 1. A weighted binary cross-entropy loss function was used. After each training cycle, the F1 score on the validation dataset was calculated and the model weight with the highest F1 score was selected and saved. Multiple trained immunotherapy score prediction neural networks were obtained through multi-fold training and cross-validation.

7. The method for predicting the effect of lung cancer immunotherapy according to claim 2, wherein: Inputting the optimized image data into a feature extraction model to obtain a corresponding image feature vector includes: Acquiring patient information of the lung cancer patient to be predicted; Inputting the patient information into the trained LLM model to obtain corresponding cancer type information; Determining an image segmentation model corresponding to the cancer type information from a preset image segmentation model library; the image segmentation model is trained based on a training data set including a plurality of training case images corresponding to the cancer type information and core image region annotations; Inputting the optimized image data into the image segmentation model to obtain a key area image corresponding to the optimized image data; Determining a feature extraction model corresponding to the cancer type information in a preset feature extraction model library; the feature extraction model is trained based on a training pathology image corresponding to the cancer type information; The key area image is input into the feature extraction model to obtain a corresponding image feature vector.

8. A lung cancer immunotherapy effect prediction system, characterized in that: The system comprises: An image acquisition module is used to acquire slice image data of biological tissue of a patient to be diagnosed with lung cancer; a quality optimization module, configured to improve the quality of the slice image data based on a neural network algorithm to obtain optimized image data; a feature extraction module, configured to input the optimized image data into a feature extraction model to obtain a corresponding image feature vector; The efficacy prediction module is configured to input the image feature vector into a trained immunotherapy score prediction neural network to obtain the immunotherapy effect corresponding to the lung cancer patient to be predicted; the immunotherapy score prediction neural network is trained using a training data set comprising a plurality of training tissue slice images and corresponding immunotherapy score annotations, wherein the immunotherapy score annotations are determined by the following steps: Acquiring tissue sample data corresponding to the training tissue slice image; Determining the immune infiltration score corresponding to the tissue sample data based on the immune infiltration score model; Calculating a weighted sum average of the immune infiltration scores corresponding to all the training tissue section images to obtain a score reference value; wherein the weighted calculation weight corresponding to each immune infiltration score includes a first weight and a second weight; the first weight is proportional to an image clarity parameter corresponding to the training tissue section image; the second weight is proportional to a score reliability parameter corresponding to the training tissue section image; the score reliability parameter is the similarity between patient data corresponding to the tissue sample data corresponding to the training tissue section image and patient data corresponding to the model comparison sample data of the immune infiltration score model; The immunotherapy score label corresponding to the training tissue section image is determined according to a comparison result between the immune infiltration score and the score reference value.

9. A lung cancer immunotherapy effect prediction system, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for predicting the effect of lung cancer immunotherapy according to any one of claims 1 to 7.

Images