CQENet: A segmentation model for nasopharyngeal carcinoma based on confidence quantitative evaluation.
Authors
Affiliations (5)
Affiliations (5)
- Computer Science and Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China; National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China.
- Liaoning Cancer Hospital & Institute, Shenyang, China.
- Computer Science and Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China; National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China. Electronic address: [email protected].
- Peoples Hospital of Naiman Banner, Inner Mongolia, China.
- Department of Medical Oncology, The Fourth Affiliated Hospital of China Medical University, Shenyang, China.
Abstract
Accurate segmentation of the tumor regions of nasopharyngeal carcinoma (NPC) is of significant importance for radiotherapy of NPC. However, the precision of existing automatic segmentation methods for NPC remains inadequate, primarily manifested in the difficulty of tumor localization and the challenges in delineating blurred boundaries. Additionally, the black-box nature of deep learning models leads to insufficient quantification of the confidence in the results, preventing users from directly understanding the model's confidence in its predictions, which severely impacts the clinical application of deep learning models. This paper proposes an automatic segmentation model for NPC based on confidence quantitative evaluation (CQENet). To address the issue of insufficient confidence quantification in NPC segmentation results, we introduce a confidence assessment module (CAM) that enables the model to output not only the segmentation results but also the confidence in those results, aiding users in understanding the uncertainty risks associated with model outputs. To address the difficulty in localizing the position and extent of tumors, we propose a tumor feature adjustment module (FAM) for precise tumor localization and extent determination. To address the challenge of delineating blurred tumor boundaries, we introduce a variance attention mechanism (VAM) to assist in edge delineation during fine segmentation. We conducted experiments on a multicenter NPC dataset, validating that our proposed method is effective and superior to existing state-of-the-art models, possessing considerable clinical application value.