AUTHOR=Chen Xinyuan , Zhu Ji , Yang Yiwei , Zhang Jie , Men Kuo , Yi Junlin , Chen Ming , Dai Jianrong 

TITLE=Investigating transfer learning to improve the deep-learning-based segmentation of organs at risk among different medical centers for nasopharyngeal carcinoma

JOURNAL=Frontiers in Physics

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2023.1147900

DOI=10.3389/fphy.2023.1147900

ISSN=2296-424X

ABSTRACT=Purpose: Convolutional neural networks (CNNs) offer a promising approach to automating organ segmentation in radiotherapy. However, variations of segmentation protocols made by different medical centers may induce a well-trained CNN model in one center cannot perform well to other centers. In this study, we proposed a transfer learning method to improve the of deep-learning based segmentation models among different medical centers using nasopharyngeal cancer (NPC) data.

Methods: The NPC data included 300 cases (S_Train) from one institution (the source center) and 60 cases from another (the target center), divided into a training set of 50 cases (T_Train) and a test set of 10 target cases (T_Test). A Resnet CNN architecture was developed with 103 layers. We first trained Model_S and Model_T from scratch with the datasets S_Train and T_train, respectively. Transfer learning was then used to train Model_ST by fine-tuning the last 10 layers of Model_S with images from T_Train. We also investigated the effect of the numbers of re-trained layers on the performance. The performance of each model was evaluated using the dice similarity coefficient (DSC) was used as the evaluation metrics . We compared the DSC value using the three different models (Model_S, Model_T, and Model_ST).

Results: When Model_S, Model_T, and Model_ST were applied to the T_Test dataset, the transfer learning (Model_ST) had the best performance. Compared with Model_S, the p values of all OARs were less than 0.05. Compared with Model_T, the p values of most OARs were less than 0.05, but there was no significant statistical difference in Model_ST for brain stem (p=0.071), mandible (p=0.177), left temporal lobes (p=0.084) and right temporal lobes (p=0.068). Although there was no statistical difference for these organs, the mean accuracy of Model_ST was higher than Model_T. The proposed transfer learning can reduce training time by up to 33%.

Conclusions: Transfer learning can improve organ segmentation for NPC by adapting a previously trained CNN model to a new image domain, reducing the training time and saving physicians from labeling a large number of contours.