CEST-Enhanced Dual TransUNet for Precise Segmentation of Nasopharyngeal Carcinoma

Motivation: Accurate segmentation of nasopharyngeal carcinoma (NPC) is essential in radiotherapy planning to optimize treatment efficacy and minimize harm to surrounding healthy tissues. Goal(s): This research aimed to enhance NPC segmentation accuracy by integrating chemical exchange saturation transfer (CEST) imaging with anatomical imaging. Approach: The study leveraged the intrinsic differences in the CEST effect between carcinoma and adjacent tissues to improve segmentation on anatomical images. Results: The incorporation of CEST imaging significantly enhanced segmentation performance, demonstrating its potential as a valuable tool in radiotherapy planning for NPC. Impact: The deep-learning model effectively utilized CEST contrast for precise NPC segmentation, enhancing radiotherapy planning by accurately targeting carcinoma and preserving healthy tissue, while advancing CEST imaging's role in clinical oncology.