Tumor radiotherapy reaction prediction model and method based on capsule graph structure neural network

Abstract

The invention relates to the technical field of medicine and deep learning, in particular to a tumor radiotherapy reaction prediction model and method based on a capsule graph structure neural network. The method comprises the following steps: acquiring a tumor data set, and extracting tumor data features from the tumor data set; the tumor data features are classified according to the risk levels, graph structure data sets are constructed respectively, and whether the tumor reacts or not is marked; constructing a deep learning model based on a capsule graph structure neural network; pre-training the deep learning model, and performing performance evaluation on the deep learning model to obtain a trained deep learning model; and inputting a to-be-predicted tumor data set into the trained deep learning model, and predicting whether the whole tumor has a radiotherapy reaction or not. According to the application, the image data before tumor radiotherapy and the radiotherapy dose can be utilized to predict whether the regional radiotherapy reactions of different severity degrees of the tumor are effective, so that a doctor is assisted to reasonably formulate the radiotherapy dose, precise radiotherapy is realized, and the radiotherapy side effect is reduced.

Description

Technical Field

[0001] The present application relates to the fields of medicine and deep learning technology, and in particular to a tumor radiotherapy response prediction model and method based on a capsule graph structure neural network. Background Art

[0002] Lung cancer, also known as primary bronchial lung cancer, is the most common lung malignancy originating from the trachea, bronchial mucosa or glands. Globally, the incidence and mortality of lung cancer are extremely high and on the rise. The incidence and mortality of lung cancer in men rank first among malignant tumors, and radiotherapy is a common tumor treatment method. At present, the setting of radiotherapy doses depends largely on the subjective decision of doctors. Excessive radiotherapy doses can cause side effects such as hair loss, skin damage, and physical weakness; while insufficient radiotherapy doses cannot produce the expected therapeutic effect. Therefore, it is crucial to set different doses for sub-regions with different risk levels and ensure that the dose set for each sub-region is reasonable and effective. Summary of the invention

[0003] The present application provides a tumor radiotherapy response prediction model and method based on a capsule graph structure neural network, which can predict whether regional radiotherapy of tumors of different severity is effective, thereby intelligently assisting doctors to reasonably formulate radiotherapy doses, achieve precise radiotherapy, reduce radiotherapy reaction side effects, and improve radiotherapy effects.

[0004] To solve the above technical problems, in the first aspect, an embodiment of the present application provides a method for predicting tumor radiotherapy response based on a capsule graph structure neural network, the method comprising the following steps: first, obtaining a tumor data set, and extracting tumor data features from the tumor data set; then, classifying the tumor data features according to the risk level; and based on the classified data features, respectively constructing graph structure data sets, and marking whether the tumor in the graph structure data set responds; next, based on the graph structure data set, constructing a deep learning model based on a capsule graph structure neural network; then, using a leave-one-out cross-validation method, pre-training the deep learning model to obtain optimized model parameters; and based on the optimized model parameters, performing a performance evaluation on the deep learning model to obtain a trained deep learning model; finally, inputting the tumor data set to be predicted into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

[0005] In some exemplary embodiments, extracting tumor data features includes: extracting X, Y, Z coordinates of each pixel point of the tumor, the standard uptake value of the early stage of radiotherapy response, the standard uptake value of the mid-stage of radiotherapy response, and the radiotherapy dose from the tumor data features.

[0006] In some exemplary embodiments, tumor data features are classified according to risk levels, including: using a K-means clustering method, with X-coordinates, Y-coordinates, Z-coordinates, and standard uptake values ​​of the early radiotherapy response of the pixel points as features, all pixels of the tumor of each patient are clustered into three categories, namely, high-risk areas, medium-risk areas, and low-risk areas.

[0007] In some exemplary embodiments, graph structured data sets are constructed based on the classified data features, including: taking the standard uptake value and radiotherapy dose of the early radiotherapy response of each point of the tumor as node feature values, connecting each point with its neighboring points to form edges, forming a graph structured data for each patient's tumor, and converting the classified data features into a graph structured data set.

[0008] In some exemplary embodiments, whether a tumor in a graph structure data set responds is labeled, including: determining whether the standard uptake value of the entire tumor before radiotherapy and the standard uptake value of the middle stage of radiotherapy satisfy a corresponding relationship; if so, determining that the entire tumor responds, labeling the radiotherapy response effective, and attaching a label "0"; if not, determining that the entire tumor does not respond, labeling the radiotherapy response invalid, and attaching a label "1"; the corresponding relationship is:

[0009]

[0010] in, It represents the average value of the standard uptake value of all pixels in the entire tumor before radiotherapy, and the standard uptake value reflects the degree of tumor lesions; It represents the average value of the standard uptake value of all pixels in the entire tumor during the middle of radiotherapy.

[0011] In some exemplary embodiments, a deep learning model based on a capsule graph structured neural network is constructed based on a graph structured dataset, including: first, based on the graph structured dataset, a main architecture of a capsule graph structured neural network is constructed; the main architecture of the capsule graph structured neural network includes a basic node capsule extraction block, a high-level graph capsule extraction block, and a graph classification block connected in sequence; then, a pre-network architecture of the capsule graph structured neural network is constructed; the pre-network architecture of the capsule graph structured neural network is used to convert tumor data into graph structured data, and input the graph structured data into the main architecture of the capsule graph structured neural network for training; based on the graph structured dataset, a main architecture of a capsule graph structured neural network is constructed, including: first, using a graph neural network to extract local vertex features with different receptive fields from the graph structured dataset, and then constructing a main node capsule in the basic node capsule extraction block; then, in the high-level graph capsule extraction block, an attention module and a dynamic routing are fused to generate multiple capsules for the graph; finally, in the graph classification block, dynamic routing is applied again to generate class capsules for graph classification.

[0012] In some exemplary embodiments, a leave-one-out cross-validation method is used to pre-train the deep learning model to obtain optimized model parameters; and based on the optimized model parameters, the performance of the deep learning model is evaluated to obtain a trained deep learning model, including: using a leave-one-out cross-validation method to divide the tumor data set into a test set and a training set, using the training set to train the deep learning model, and using the test set to test the trained deep learning model; adjusting the parameters of the tested deep learning model to obtain an optimized deep learning model and optimized model parameters; based on the optimized model parameters, the performance of the deep learning model is evaluated according to the evaluation indicators of accuracy and area under the receiver operating characteristic curve to obtain a trained deep learning model.

[0013] In some exemplary embodiments, a tumor data set to be predicted is input into a trained deep learning model to predict whether the entire tumor will respond to radiotherapy, including: preprocessing the tumor data set to be predicted to obtain a preprocessed tumor graph structure data set; inputting the preprocessed tumor graph structure data set into the trained deep learning model to predict whether the entire tumor will respond to radiotherapy.

[0014] In some exemplary embodiments, the predicted tumor data set is preprocessed to obtain a preprocessed tumor graph structure data set, including: performing preprocessing operations of feature extraction and pixel risk level clustering on the predicted tumor data set in sequence to obtain the preprocessed tumor graph structure data set.

[0015] In the second aspect, the embodiment of the present application also provides a tumor radiotherapy response prediction model based on a capsule graph structure neural network, comprising a data preprocessing module, a model main body module, a model training module, a model evaluation module and a prediction module connected in sequence; the data preprocessing module is used to obtain a tumor data set and extract tumor data features from the tumor data set; classify the tumor data features according to the risk level; and based on the classified data features, respectively construct a graph structure data set, and mark whether the tumor in the graph structure data set responds; the model main body module is used to construct a deep learning model based on the capsule graph structure neural network according to the graph structure data set; the model training module is used to pre-train the deep learning model using a leave-one-out cross-validation method to obtain optimized model parameters; the model evaluation module is used to perform performance evaluation on the deep learning model based on the optimized model parameters to obtain a trained deep learning model; the prediction module is used to input the tumor data set to be predicted into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

[0016] The technical solution provided by the embodiments of the present application has at least the following advantages:

[0017] The embodiment of the present application provides a tumor radiotherapy response prediction model and method based on a capsule graph structure neural network, the method comprising the following steps: first, obtaining a tumor data set and extracting tumor data features from the tumor data set; then, classifying the tumor data features according to the risk level; and based on the classified data features, respectively constructing graph structure data sets, and marking whether the tumor in the graph structure data set responds; next, based on the graph structure data set, constructing a deep learning model based on a capsule graph structure neural network; then, using a leave-one-out cross-validation method, pre-training the deep learning model to obtain optimized model parameters; and based on the optimized model parameters, performing a performance evaluation on the deep learning model to obtain a trained deep learning model; finally, inputting the tumor data set to be predicted into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

[0018] The tumor radiotherapy response prediction model and method based on capsule graph structure neural network provided in the embodiments of the present application have the following advantages:

[0019] (1) This application converts the original tumor image data into graph structure data, takes the pre-radiotherapy response standard uptake value (PreSUV) and radiotherapy dose (Dose) of each tumor point as node feature values, connects each point with its neighboring points to form edges, so that it can express the three-dimensional spatial relationship of tumor pixels and can be applied to graph structure neural networks.

[0020] (2) This application first uses K-means clustering to classify tumor pixels according to their severity, and then predicts whether tumor subregions with different risk levels will respond to radiotherapy, thereby improving the accuracy of the prediction and promoting the implementation of precision radiotherapy.

[0021] (3) This application uses evaluation indicators to compare with traditional network models to verify the effectiveness, accuracy and adjustability of the tumor radiotherapy response prediction model.

[0022] The model provided in this application can predict whether a tumor will respond to radiotherapy, thereby intelligently assisting doctors to rationally formulate radiotherapy doses, achieve precise radiotherapy, reduce radiotherapy reaction side effects, and improve radiotherapy effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplifications do not constitute limitations on the embodiments. Unless otherwise stated, the pictures in the drawings do not constitute proportional limitations.

[0024] Figure 1 A schematic diagram of a flow chart of a method for predicting tumor radiotherapy response based on a capsule graph structure neural network provided in one embodiment of the present application;

[0025] Figure 2A schematic diagram of a data preprocessing flow of a method for predicting tumor radiotherapy response based on a capsule graph structure neural network provided in one embodiment of the present application;

[0026] Figure 3 A network architecture diagram of a capsule graph structure neural network provided in an embodiment of the present application;

[0027] Figure 4 A schematic diagram of the structure of a tumor radiotherapy response prediction model based on a capsule graph structure neural network provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] The current setting of radiotherapy dose is mainly based on the physician's experience and judgment, which is affected by individual differences and accidental factors. This approach makes it difficult to ensure the scientificity, rationality and effectiveness of the treatment. Therefore, scientific and reasonable setting of radiotherapy dose for tumor target area is crucial for the realization of precise radiotherapy.

[0029] In view of the shortcomings of the prior art, the embodiment of the present application provides a tumor radiotherapy response prediction model and method based on a capsule graph structure neural network, which includes the following steps: first, obtain a tumor data set and extract tumor data features from the tumor data set; then, classify the tumor data features according to the risk level; and based on the classified data features, respectively construct a graph structure data set, and mark whether the tumor in the graph structure data set responds; next, based on the graph structure data set, construct a deep learning model based on a capsule graph structure neural network; then, use the leave-one-out cross-validation method to pre-train the deep learning model to obtain optimized model parameters; and based on the optimized model parameters, perform performance evaluation on the deep learning model to obtain a trained deep learning model; finally, input the tumor data set to be predicted into the trained deep learning model to predict whether the entire tumor has a radiotherapy response. The model provided by the present application can predict whether regional radiotherapy of different severity levels of tumors is effective, so as to intelligently assist doctors in rationally formulating radiotherapy doses, achieve precise radiotherapy, reduce the side effects of radiotherapy reactions, and improve the effect of radiotherapy.

[0030] The following will describe the various embodiments of the present application in detail with reference to the accompanying drawings. However, it will be appreciated by those skilled in the art that in the various embodiments of the present application, many technical details are provided in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solution claimed in the present application can be implemented.

[0031] See also Figure 1 The present application embodiment provides a method for predicting tumor radiotherapy response based on a capsule graph structure neural network, the method comprising the following steps:

[0032] Step S1: Obtain a tumor data set, and extract tumor data features from the tumor data set.

[0033] Step S2: classify the tumor data features according to the risk level; and based on the classified data features, construct graph structure data sets respectively, and mark whether the tumor in the graph structure data set responds.

[0034] Step S3: Based on the graph structure data set, a deep learning model based on a capsule graph structure neural network is constructed.

[0035] Step S4: Use the leave-one-out cross-validation method to pre-train the deep learning model to obtain optimized model parameters; and based on the optimized model parameters, perform performance evaluation on the deep learning model to obtain a trained deep learning model.

[0036] Step S5: input the tumor data set to be predicted into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

[0037] The capsule graph neural network uses the concept of capsules to solve the shortcomings of the existing graph embedding algorithm based on the graph neural network (Graph Neural Network, GNN). The included attention module can be used to process graphs of various sizes, allowing the model to focus on processing the key parts of the graph. The deep neural network uses the graph structure data for the pytorch deep learning framework to achieve classification tasks. It can input the graph structure data converted from the original tumor image data, take the pre-radiotherapy response standard uptake value (PreSUV) and radiotherapy dose (Dose) of each tumor point as the node feature value, connect each point with its neighboring points to form an edge, and the data can express the three-dimensional spatial relationship of tumor pixels, highlight the characteristics of tumor data, and avoid the feature loss caused by image segmentation. Based on this, the present application proposes a tumor radiotherapy response prediction model and method based on a capsule graph structure neural network, which can predict whether the tumor will respond after radiotherapy, so as to intelligently assist doctors to reasonably formulate radiotherapy doses, achieve precise radiotherapy, reduce the side effects of radiotherapy reactions, and improve the effect of radiotherapy.

[0038] In some embodiments, extracting tumor data features in step S1 includes: extracting the X, Y, and Z coordinates of each pixel point of the tumor, the early standard uptake value (PreSUV) of radiotherapy response, the mid-standard uptake value (MidSUV) of radiotherapy response, and the radiotherapy dose (Dose) from the tumor data features.

[0039] In some embodiments, in step S2, the tumor data features are classified according to the risk level. Specifically, the data is divided into three categories with different risk levels. The classification process is: using the K-means clustering method, with the X-coordinate, Y-coordinate, Z-coordinate, and pixel point radiotherapy response pre-standard uptake value (PreSUV) as features, all pixel points of each patient's tumor are clustered into three categories, namely, high-risk area, medium-risk area, and low-risk area.

[0040] In some embodiments, based on the classified data features, graph structured data sets are constructed separately, including: taking the PreSUV and Dose of each tumor point as node feature values, connecting each point with its adjacent points to form edges, forming a graph structured data for each patient's tumor, and converting the classified data features into graph structured data, that is, converting the original tumor data into a graph structured data set.

[0041] In some embodiments, whether the tumor in the graph structure data set responds is marked, including: determining whether the standard uptake value of the entire tumor before radiotherapy and the standard uptake value of the middle stage of radiotherapy satisfy the corresponding relationship; if so, it is determined that the entire tumor responds, marking the radiotherapy response as effective, and adding a label "0"; if not, it is determined that the entire tumor does not respond, marking the radiotherapy response as invalid, and adding a label "1"; the corresponding relationship is shown in formula (1):

[0042]

[0043] in, It represents the average value of the standard uptake value of all pixels in the entire tumor before radiotherapy, and the standard uptake value reflects the degree of tumor lesions; It represents the average value of the standard uptake value of all pixels in the entire tumor during the middle of radiotherapy.

[0044] It should be noted that the Standard Uptake Value (SUV) is a semi-quantitative index commonly used in positron emission computed tomography (PET) in tumor diagnosis. It refers to the ratio of the radioactivity of the imaging agent taken up by local tissues to the average injected activity of the whole body. Currently, SUV is widely used in the differentiation of benign and malignant tumors, efficacy evaluation, and prognosis prediction.

[0045] Specifically, in step S3, based on the graph structure data set, a deep learning model based on a capsule graph structure neural network is constructed, including:

[0046] Step S301, based on the graph structure data set, construct the main architecture of the capsule graph structure neural network; the main architecture of the capsule graph structure neural network includes a basic node capsule extraction block, a high-level graph capsule extraction block and a graph classification block connected in sequence.

[0047] Step S302, constructing a pre-network architecture of a capsule graph structure neural network; the pre-network architecture of the capsule graph structure neural network is used to convert tumor data into graph structure data, and input the graph structure data into the main architecture of the capsule graph structure neural network for training.

[0048] Specifically, in step S301, based on the graph structure data set, the main architecture of the capsule graph structure neural network is constructed, including:

[0049] Step S3011: Use GNN to extract local vertex features with different receptive fields.

[0050] Step S3012: construct a main node capsule in the basic node capsule extraction block.

[0051] Step S3013, the attention module and dynamic routing are then fused in the high-level graph capsule extraction block to generate multiple capsules for the graph.

[0052] Step S3014: Apply dynamic routing again in the graph classification block to generate class capsules for graph classification.

[0053] Specifically, in step S302, a pre-network architecture of a capsule graph structure neural network is constructed. Based on the pre-network architecture of the capsule graph structure neural network, the original tumor data is converted into graph structure data, and the graph structure data is input into the main architecture of the capsule graph structure neural network for training, and leave-one-out cross-validation is performed to adjust network parameters to obtain the optimal deep learning model.

[0054] In some embodiments, step S4 uses a leave-one-out cross-validation method to pre-train the deep learning model to obtain optimized model parameters; and based on the optimized model parameters, the deep learning model is performance evaluated to obtain a trained deep learning model, including:

[0055] Step S401: Use the leave-one-out cross-validation method to divide the tumor data set into a test set and a training set, use the training set to train the deep learning model, and use the test set to test the trained deep learning model.

[0056] Step S402: Adjust the parameters of the tested deep learning model to obtain an optimized deep learning model and optimized model parameters.

[0057] Step S403: Based on the optimized model parameters, the deep learning model is evaluated for performance according to the evaluation indicators of accuracy and area under the receiver operating characteristic curve to obtain a trained deep learning model.

[0058] Specifically, step S4 mainly adopts the leave-one-out cross-validation method to pre-train the capsule graph structure neural network model, adjust the network parameters, and evaluate the performance of the model. When the tumor data set is divided into a test set and a training set, the leave-one-out cross-validation method is used to take each tumor data in the tumor data set as a test set, and the rest as a training set, and train a small model respectively. The error of the overall model is the average of the errors of each model. During the training process of each small model, the marginal loss function is used to calculate the classification loss, where k is the number of classifications, and λ is used to stop the initial learning to reduce the length of all class capsules. Especially when k is very large, formula (2) is used for calculation:

[0059]

[0060] Where c is the capsule vector, and m and T are constants.

[0061] According to the loss after model training convergence, the model parameters are adjusted to minimize the loss after convergence in model verification. Finally, the model parameters that minimize the loss after convergence are selected and imported into the deep learning model, and the model is tested using the test set. Then, the parameters of the tested deep learning model are adjusted to obtain an optimized deep learning model and optimized model parameters; finally, based on the optimized model parameters, the performance of the deep learning model is evaluated according to evaluation indicators such as accuracy and area under the receiver operating characteristic curve (AUC) to obtain a trained deep learning model.

[0062] Specifically, in step S5, the tumor data set to be predicted is input into the trained deep learning model to predict whether the entire tumor has a radiotherapy response, including:

[0063] Step S501: preprocess the tumor data set to be predicted to obtain a preprocessed tumor graph structure data set.

[0064] Step S502: input the preprocessed tumor graph structure data set into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

[0065] In some embodiments, in step S501, preprocessing the tumor dataset to be predicted to obtain a preprocessed tumor graph structure dataset includes:

[0066] The tumor data set to be predicted is subjected to preprocessing operations of feature extraction and pixel risk level clustering in sequence to obtain a preprocessed tumor graph structure data set.

[0067] It should be noted that the format of the preprocessed tumor graph structure dataset can be correctly read by the deep learning model.

[0068] See also Figure 2 The present application embodiment provides a data preprocessing flow diagram of a method for predicting tumor radiotherapy response based on a capsule graph structure neural network, comprising the following steps:

[0069] First, data features are extracted. The X, Y, and Z coordinates of each pixel of the tumor, the early standard uptake value (PreSUV) of radiotherapy response, the mid-standard uptake value (MidSUV) of radiotherapy response, and the radiotherapy dose (Dose) are extracted from the tumor data features.

[0070] Then, the data was divided into three categories with different risk levels. The K-means clustering method was used to cluster all the pixels of each patient's tumor into three categories, namely high-risk area, medium-risk area, and low-risk area, based on the X-coordinate, Y-coordinate, Z-coordinate, and pre-radiotherapy response standard uptake value (PreSUV) of the pixel.

[0071] Next, a graph-structured dataset is constructed, with the PreSUV and Dose of each tumor point used as node feature values, and each point and its neighboring points forming edges. Each patient's tumor forms a graph-structured data set, and the original tumor data is converted into a graph-structured dataset.

[0072] Finally, the tumor response is marked to determine whether the standard uptake value of the entire tumor before radiotherapy and the standard uptake value of the middle stage of radiotherapy meet the corresponding relationship; if so, it is determined that the entire tumor responds, the radiotherapy response is effective, and a label "0" is added; if not, it is determined that the entire tumor does not respond, the radiotherapy response is invalid, and a label "1" is added; the corresponding relationship is:

[0073]

[0074] in, It represents the average value of the standard uptake value of all pixels in the entire tumor before radiotherapy, and the standard uptake value reflects the degree of tumor lesions; It represents the average value of the standard uptake value of all pixels in the entire tumor during the middle of radiotherapy.

[0075] See also Figure 3, the embodiment of the present application provides a network architecture diagram of a capsule graph structure neural network, including a network main architecture of a capsule graph structure neural network and a network pre-architecture of a capsule graph structure neural network. The network main architecture first uses GNN to extract local vertex features with different receptive fields, and then builds a main node capsule in the basic node capsule extraction block; then, in the high-level graph capsule extraction block, the attention module and dynamic routing are integrated to generate multiple capsules for the graph; finally, dynamic routing is applied again in the graph classification block to generate class capsules for graph classification. Construct the network pre-architecture of the capsule graph structure neural network, convert the original tumor data into graph structure data, and input the graph structure data into the main architecture of the capsule graph structure neural network for training, perform leave-one-out cross-validation, adjust the network parameters, and obtain the optimal deep learning model.

[0076] See also Figure 4 The embodiment of the present application also provides a tumor radiotherapy response prediction model based on a capsule graph structure neural network, including a data preprocessing module 101, a model main body module 102, a model training module 103, a model evaluation module 104 and a prediction module 105 connected in sequence; the data preprocessing module 101 is used to obtain a tumor data set and extract tumor data features from the tumor data set; classify the tumor data features according to the risk level; and based on the classified data features, respectively construct a graph structure data set, and mark whether the tumor in the graph structure data set responds; the model main body module 102 is used to construct a deep learning model based on a capsule graph structure neural network according to the graph structure data set; the model training module 103 is used to pre-train the deep learning model using a leave-one-out cross-validation method to obtain optimized model parameters; the model evaluation module 104 is used to perform performance evaluation on the deep learning model according to the optimized model parameters to obtain a trained deep learning model; the prediction module 105 is used to input the tumor data set to be predicted into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

[0077] The following is a detailed description of the tumor radiotherapy response prediction model based on capsule graph structure neural network provided by the present application with respect to a specific embodiment.

[0078] First, the tumor radiotherapy response prediction model based on capsule graph structure neural network proposed in the embodiment of the present application is based on Windows 11 system and implemented using Python 3.9.

[0079] In addition, it should be noted that the examples of the present application analyze and evaluate the radiotherapy response of non-small cell lung cancer.

[0080] First, extract data features. Extract the coordinates X, Y, and Z of each pixel of the tumor, the standard uptake value (PreSUV) of the early radiotherapy response, the standard uptake value (MidSUV) of the mid-radiotherapy response, and the radiotherapy dose (Dose) from the tumor data features. Divide the data into three categories with different risk levels. Use the K-means clustering method to cluster all the pixels of each patient's tumor into three categories, namely high-risk area, medium-risk area, and low-risk area, with the X-coordinate, Y-coordinate, Z-coordinate, and pixel point standard uptake value (PreSUV) of the early radiotherapy response as features. Construct a graph structure data set, take the PreSUV and Dose of each tumor point as node feature values, and form edges between each point and its neighboring points. Each patient's tumor forms a graph structure data set, and the original tumor data is converted into a graph structure data set. Label whether each patient's tumor responds. If the entire tumor responds, the radiotherapy response is effective, and the label "0" is attached; if the entire tumor does not respond, the radiotherapy response is invalid, and the label "1" is attached.

[0081] Then, a deep learning model based on capsule graph structure neural network is constructed. First, GNN is used to extract local vertex features with different receptive fields, and then the main node capsule is constructed in the basic node capsule extraction block; then the attention module and dynamic routing are fused in the advanced graph capsule extraction block to generate multiple capsules for the graph; finally, dynamic routing is applied again in the graph classification block to generate class capsules for graph classification. The graph structure data is input into the main architecture of the capsule graph structure neural network for training. The tumor data of each patient in the tumor data set is used as the test set, and the rest are used as the training set. A model is trained for each model, and the error of the overall model is the average of the errors of each model mentioned above; the parameters are adjusted to obtain the optimized deep learning model and optimized model parameters.

[0082] Next, the performance of the deep learning model is evaluated through the evaluation module. The evaluation indicators include accuracy, area under the receiver operating characteristic curve (AUC), etc. For the entire tumor area of ​​the patient, the model can reach an AUC of 0.6929 on the test set; for the high-risk tumor area, the model can reach an AUC of 0.5952 on the test set; for the medium-risk tumor area, the model can reach an AUC of 0.5317 on the test set. It can be seen that the model has the best prediction effect on the entire tumor area, and the prediction effect on the high-risk tumor area is second.

[0083] Finally, the preprocessed tumor data set that needs to be predicted is input into the trained deep learning model. The trained deep learning model gives the prediction result through the prediction module, which can predict whether the tumor responds after radiotherapy.

[0084] Based on the above technical scheme, the embodiment of the present application provides a tumor radiotherapy response prediction model and method based on a capsule graph structure neural network, and the method includes the following steps: first, a tumor data set is obtained, and tumor data features are extracted from the tumor data set; then, the tumor data features are classified according to the risk level; and based on the classified data features, graph structure data sets are respectively constructed, and whether the tumor in the graph structure data set responds is marked; next, based on the graph structure data set, a deep learning model based on a capsule graph structure neural network is constructed; then, a leave-one-out cross-validation method is used to pre-train the deep learning model to obtain optimized model parameters; and based on the optimized model parameters, the deep learning model is performance evaluated to obtain a trained deep learning model; finally, the tumor data set to be predicted is input into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

[0085] The present application proposes a tumor radiotherapy response prediction model and method based on a capsule graph structure neural network. First, the present application converts the original tumor image data into graph structure data, takes the PreSUV and Dose of each tumor point as the node feature value, and connects each point with its neighboring points to form an edge, so that it can express the three-dimensional spatial relationship of tumor pixels and can be applied to graph structure neural networks. Secondly, the present application first uses K-means clustering to classify tumor pixels according to their severity, and predicts whether the tumor sub-regions of different risk levels respond to radiotherapy, improves the accuracy of the prediction, and promotes the implementation of precision radiotherapy. Finally, the present application uses evaluation indicators to compare with traditional network models to verify the effectiveness, accuracy and adjustability of the constructed tumor radiotherapy response prediction model. The model provided by the present application can predict whether the tumor will respond after radiotherapy, so as to intelligently assist doctors to reasonably formulate radiotherapy doses, achieve precise radiotherapy, reduce the side effects of radiotherapy reactions, and improve the effect of radiotherapy.

[0086] Those skilled in the art can understand that the above-mentioned embodiments are specific examples for implementing the present application, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of the present application. Any person skilled in the art can make their own changes and modifications without departing from the spirit and scope of the present application, so the scope of protection of the present application shall be based on the scope defined in the claims.

Claims

1. A method for predicting tumor radiotherapy response based on capsule graph structure neural network, characterized in that: The following steps are involved: Acquire a tumor data set, and extract tumor data features from the tumor data set; Classifying the tumor data features according to the risk level; and constructing graph structure data sets based on the classified data features, and marking whether the tumor in the graph structure data sets responds; Based on the graph structure data set, a deep learning model based on a capsule graph structure neural network is constructed; The deep learning model is pre-trained by using a leave-one-out cross-validation method to obtain optimized model parameters; and based on the optimized model parameters, the deep learning model is performance evaluated to obtain a trained deep learning model; The tumor data set to be predicted is input into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

2. The method for predicting tumor radiotherapy response based on capsule graph structure neural network according to claim 1, characterized in that: Extract tumor data features, including: The X, Y, and Z coordinates of each pixel of the tumor, the standard uptake value in the early stage of radiotherapy response, the standard uptake value in the middle stage of radiotherapy response, and the radiotherapy dose are extracted from the tumor data features.

3. The method for predicting tumor radiotherapy response based on capsule graph structure neural network according to claim 1, characterized in that: The tumor data features are classified according to risk levels, including: Using the K-means clustering method, all the pixels of each patient's tumor were clustered into three categories, namely high-risk area, medium-risk area, and low-risk area, based on the X-coordinate, Y-coordinate, Z-coordinate, and standard uptake value of the pixel point before radiotherapy response.

4. The method for predicting tumor radiotherapy response based on capsule graph structure neural network according to claim 1, characterized in that: Based on the classified data features, graph structure datasets are constructed separately, including: The standard uptake value and radiotherapy dose of each tumor point in the early stage of radiotherapy response are used as node feature values, and each point is connected to its neighboring points to form edges. Each patient's tumor forms a graph structure data, and the classified data features are converted into a graph structure data set.

5. The method for predicting tumor radiotherapy response based on capsule graph structure neural network according to claim 1, characterized in that: Annotating whether the tumor in the graph structure dataset responds includes: Determine whether the standard uptake value of the entire tumor before radiotherapy and the standard uptake value during radiotherapy satisfy the corresponding relationship; If yes, it is determined that the entire tumor has responded, and the radiotherapy response is marked as effective, with an additional label of "0"; If not, it is determined that there is no response to the entire tumor, and the radiotherapy response is marked as ineffective, with an additional label of "1"; The corresponding relationship is: in, It represents the average value of the standard uptake value of all pixels in the entire tumor before radiotherapy, and the standard uptake value reflects the degree of tumor lesions; It represents the average value of the standard uptake value of all pixels in the entire tumor during the middle of radiotherapy.

6. The method for predicting tumor radiotherapy response based on capsule graph structure neural network according to claim 1, characterized in that: Based on the graph structure data set, a deep learning model based on a capsule graph structure neural network is constructed, including: Based on the graph structure data set, a main architecture of a capsule graph structure neural network is constructed; the main architecture of the capsule graph structure neural network includes a basic node capsule extraction block, a high-level graph capsule extraction block and a graph classification block connected in sequence; Constructing a pre-network architecture of a capsule graph structure neural network; the pre-network architecture of the capsule graph structure neural network is used to convert tumor data into graph structure data, and input the graph structure data into the main architecture of the capsule graph structure neural network for training; Based on the graph structure dataset, the main architecture of the capsule graph structure neural network is constructed, including: Firstly, a graph neural network is used to extract local vertex features with different receptive fields from the graph structure dataset, and then the main node capsule is constructed in the basic node capsule extraction block. Then, the attention module and dynamic routing are fused in the advanced graph capsule extraction block to generate multiple capsules for the graph. Finally, dynamic routing is applied again in the graph classification block to generate class capsules for graph classification.

7. The method for predicting tumor radiotherapy response based on capsule graph structure neural network according to claim 1, characterized in that: The deep learning model is pre-trained by using a leave-one-out cross-validation method to obtain optimized model parameters; and based on the optimized model parameters, the deep learning model is performance evaluated to obtain a trained deep learning model, including: Using a leave-one-out cross-validation method, the tumor data set is divided into a test set and a training set, the training set is used to train the deep learning model, and the test set is used to test the trained deep learning model; Adjusting the parameters of the tested deep learning model to obtain an optimized deep learning model and optimized model parameters; Based on the optimized model parameters, the performance of the deep learning model is evaluated according to the evaluation indicators of accuracy and area under the receiver operating characteristic curve to obtain a trained deep learning model.

8. The method for predicting tumor radiotherapy response based on capsule graph structure neural network according to claim 1, characterized in that: The tumor data set to be predicted is input into the trained deep learning model to predict whether the entire tumor will respond to radiotherapy, including: Preprocessing the tumor data set to be predicted to obtain a preprocessed tumor graph structure data set; The preprocessed tumor graph structure dataset is input into the trained deep learning model to predict whether the entire tumor responds to radiotherapy.

9. The method for predicting tumor radiotherapy response based on capsule graph structure neural network according to claim 8, characterized in that: The tumor data set to be predicted is preprocessed to obtain a preprocessed tumor graph structure data set, including: The tumor data set to be predicted is subjected to preprocessing operations of feature extraction and pixel risk level clustering in sequence to obtain a preprocessed tumor graph structure data set.

10. A tumor radiotherapy response prediction model based on capsule graph structure neural network, characterized in that: It includes a data preprocessing module, a model main body module, a model training module, a model evaluation module and a prediction module which are connected in sequence; The data preprocessing module is used to obtain a tumor data set and extract tumor data features from the tumor data set; Classifying the tumor data features according to the risk level; and constructing graph structure data sets based on the classified data features, and marking whether the tumor in the graph structure data sets responds; The model main body module is used to construct a deep learning model based on a capsule graph structure neural network according to the graph structure data set; The model training module is used to pre-train the deep learning model using a leave-one-out cross-validation method to obtain optimized model parameters; The model evaluation module is used to perform performance evaluation on the deep learning model according to the optimized model parameters to obtain a trained deep learning model; The prediction module is used to input the tumor data set to be predicted into the trained deep learning model to predict whether the entire tumor will respond to radiotherapy.

Images