An Efficient 3D Convolutional Neural Network for Dose Prediction in Cancer Radiotherapy from CT Images
<b>Introduction</b>: Cancer is a highly lethal disease with a significantly high mortality rate. One of the most commonly used methods for treatment is radiation therapy. However, cancer treatment using radiotherapy is a time-consuming process that requires significant manual work from p...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/2/177 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588730546782208 |
|---|---|
| author | Lam Thanh Hien Pham Trung Hieu Do Nang Toan |
| author_facet | Lam Thanh Hien Pham Trung Hieu Do Nang Toan |
| author_sort | Lam Thanh Hien |
| collection | DOAJ |
| description | <b>Introduction</b>: Cancer is a highly lethal disease with a significantly high mortality rate. One of the most commonly used methods for treatment is radiation therapy. However, cancer treatment using radiotherapy is a time-consuming process that requires significant manual work from planners and doctors. In radiation therapy treatment planning, determining the dose distribution for each of the regions of the patient’s body is one of the most difficult and important tasks. Nowadays, artificial intelligence has shown promising results in improving the quality of disease treatment, particularly in cancer radiation therapy. <b>Objectives</b>: The main objective of this study is to build a high-performance deep learning model for predicting radiation therapy doses for cancer and to develop software to easily manipulate and use this model. <b>Materials and Methods</b>: In this paper, we propose a custom 3D convolutional neural network model with a U-Net-based architecture to automatically predict radiation doses during cancer radiation therapy from CT images. To ensure that the predicted doses do not have negative values, which are not valid for radiation doses, a rectified linear unit (ReLU) function is applied to the output to convert negative values to zero. Additionally, a proposed loss function based on a dose–volume histogram is used to train the model, ensuring that the predicted dose concentrations are highly meaningful in terms of radiation therapy. The model is developed using the OpenKBP challenge dataset, which consists of 200, 100, and 40 head and neck cancer patients for training, testing, and validation, respectively. Before the training phase, preprocessing and augmentation techniques, such as standardization, translation, and flipping, are applied to the training set. During the training phase, a cosine annealing scheduler is applied to update the learning rate. <b>Results and Conclusions</b>: Our model achieved strong performance, with a good DVH score (1.444 Gy) on the test dataset, compared to previous studies and state-of-the-art models. In addition, we developed software to display the dose maps predicted by the proposed model for each 2D slice in order to facilitate usage and observation. These results may help doctors in treating cancer with radiation therapy in terms of both time and effectiveness. |
| format | Article |
| id | doaj-art-d6800ee36682421398a6be24f9330760 |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-d6800ee36682421398a6be24f93307602025-01-24T13:29:00ZengMDPI AGDiagnostics2075-44182025-01-0115217710.3390/diagnostics15020177An Efficient 3D Convolutional Neural Network for Dose Prediction in Cancer Radiotherapy from CT ImagesLam Thanh Hien0Pham Trung Hieu1Do Nang Toan2Faculty of Information Technology, Lac Hong University, Huynh Van Nghe, Bien Hoa 76120, VietnamInstitute of Information Technology, Vietnam Academy of Science and Technology, Hoang Quoc Viet, Hanoi 10072, VietnamInstitute of Information Technology, Vietnam Academy of Science and Technology, Hoang Quoc Viet, Hanoi 10072, Vietnam<b>Introduction</b>: Cancer is a highly lethal disease with a significantly high mortality rate. One of the most commonly used methods for treatment is radiation therapy. However, cancer treatment using radiotherapy is a time-consuming process that requires significant manual work from planners and doctors. In radiation therapy treatment planning, determining the dose distribution for each of the regions of the patient’s body is one of the most difficult and important tasks. Nowadays, artificial intelligence has shown promising results in improving the quality of disease treatment, particularly in cancer radiation therapy. <b>Objectives</b>: The main objective of this study is to build a high-performance deep learning model for predicting radiation therapy doses for cancer and to develop software to easily manipulate and use this model. <b>Materials and Methods</b>: In this paper, we propose a custom 3D convolutional neural network model with a U-Net-based architecture to automatically predict radiation doses during cancer radiation therapy from CT images. To ensure that the predicted doses do not have negative values, which are not valid for radiation doses, a rectified linear unit (ReLU) function is applied to the output to convert negative values to zero. Additionally, a proposed loss function based on a dose–volume histogram is used to train the model, ensuring that the predicted dose concentrations are highly meaningful in terms of radiation therapy. The model is developed using the OpenKBP challenge dataset, which consists of 200, 100, and 40 head and neck cancer patients for training, testing, and validation, respectively. Before the training phase, preprocessing and augmentation techniques, such as standardization, translation, and flipping, are applied to the training set. During the training phase, a cosine annealing scheduler is applied to update the learning rate. <b>Results and Conclusions</b>: Our model achieved strong performance, with a good DVH score (1.444 Gy) on the test dataset, compared to previous studies and state-of-the-art models. In addition, we developed software to display the dose maps predicted by the proposed model for each 2D slice in order to facilitate usage and observation. These results may help doctors in treating cancer with radiation therapy in terms of both time and effectiveness.https://www.mdpi.com/2075-4418/15/2/1773D deep learning modelCT imagesdose predictionU-Net architectureresidual connectiondose–volume histogram |
| spellingShingle | Lam Thanh Hien Pham Trung Hieu Do Nang Toan An Efficient 3D Convolutional Neural Network for Dose Prediction in Cancer Radiotherapy from CT Images Diagnostics 3D deep learning model CT images dose prediction U-Net architecture residual connection dose–volume histogram |
| title | An Efficient 3D Convolutional Neural Network for Dose Prediction in Cancer Radiotherapy from CT Images |
| title_full | An Efficient 3D Convolutional Neural Network for Dose Prediction in Cancer Radiotherapy from CT Images |
| title_fullStr | An Efficient 3D Convolutional Neural Network for Dose Prediction in Cancer Radiotherapy from CT Images |
| title_full_unstemmed | An Efficient 3D Convolutional Neural Network for Dose Prediction in Cancer Radiotherapy from CT Images |
| title_short | An Efficient 3D Convolutional Neural Network for Dose Prediction in Cancer Radiotherapy from CT Images |
| title_sort | efficient 3d convolutional neural network for dose prediction in cancer radiotherapy from ct images |
| topic | 3D deep learning model CT images dose prediction U-Net architecture residual connection dose–volume histogram |
| url | https://www.mdpi.com/2075-4418/15/2/177 |
| work_keys_str_mv | AT lamthanhhien anefficient3dconvolutionalneuralnetworkfordosepredictionincancerradiotherapyfromctimages AT phamtrunghieu anefficient3dconvolutionalneuralnetworkfordosepredictionincancerradiotherapyfromctimages AT donangtoan anefficient3dconvolutionalneuralnetworkfordosepredictionincancerradiotherapyfromctimages AT lamthanhhien efficient3dconvolutionalneuralnetworkfordosepredictionincancerradiotherapyfromctimages AT phamtrunghieu efficient3dconvolutionalneuralnetworkfordosepredictionincancerradiotherapyfromctimages AT donangtoan efficient3dconvolutionalneuralnetworkfordosepredictionincancerradiotherapyfromctimages |