PCG-net: feature adaptive deep learning for automated head and neck organs-at-risk segmentation

Frontiers in Oncology

Oncology

Xudong Xue¹  Wei Wei¹  Yi Ding¹  Chi Ma²  Xiao Wang²  Xiao Yu³  Changchao Wei⁴  Benpeng Zhu⁵  Shunyao Luan⁵ 

[1] Department of Radiation Oncology, Hubei Cancer Hospital, TongJi Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China;Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Rutgers-Robert Wood Johnson Medical School, New Brunswick, NJ, United States;Department of Radiation Oncology, The First Affiliated Hospital of University of Science and Technology of China, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China;Key Laboratory of Artificial Micro and Nano-structures of Ministry of Education, Center for Theoretical Physics, School of Physics and Technology, Wuhan University, Wuhan, China;School of Integrated Circuit, Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China;

关键词: head and neck cancer;    radiation therapy;    medical image;    deep learning;    automated segmentation;   

DOI  :  10.3389/fonc.2023.1177788

 received in 2023-03-08, accepted in 2023-10-03,  发布年份 2023

来源: Frontiers

【 摘 要 】

IntroductionRadiation therapy is a common treatment option for Head and Neck Cancer (HNC), where the accurate segmentation of Head and Neck (HN) Organs-AtRisks (OARs) is critical for effective treatment planning. Manual labeling of HN OARs is time-consuming and subjective. Therefore, deep learning segmentation methods have been widely used. However, it is still a challenging task for HN OARs segmentation due to some small-sized OARs such as optic chiasm and optic nerve.MethodsTo address this challenge, we propose a parallel network architecture called PCG-Net, which incorporates both convolutional neural networks (CNN) and a Gate-Axial-Transformer (GAT) to effectively capture local information and global context. Additionally, we employ a cascade graph module (CGM) to enhance feature fusion through message-passing functions and information aggregation strategies. We conducted extensive experiments to evaluate the effectiveness of PCG-Net and its robustness in three different downstream tasks. ResultsThe results show that PCG-Net outperforms other methods, improves the accuracy of HN OARs segmentation, which can potentially improve treatment planning for HNC patients.DiscussionIn summary, the PCG-Net model effectively establishes the dependency between local information and global context and employs CGM to enhance feature fusion for accurate segment HN OARs. The results demonstrate the superiority of PCGNet over other methods, making it a promising approach for HNC treatment planning.

【 授权许可】

Unknown   
Copyright © 2023 Luan, Wei, Ding, Xue, Wei, Yu, Wang, Ma and Zhu