Year: 2025
Type: article
Abstract: Captured polyp images often suffer from degradation, such as dim lighting, blur, and overexposure. Direct segmentation is prone to artifact diffusion, which significantly degrades the performance of downstream segmentation algorithms and leads to inaccurate boundary delineation. Addressing these varied degradations requires a dynamic, intelligent process that diagnoses and applies targeted corrections. We present AgentPolyp, a novel framework driven by an intelligent agent that integrates CLIP-based semantic guidance and dynamic image enhancement with a lightweight segmentation network. The agent adaptively selects reinforcement learning strategies to perform context-aware denoising, contrast adjustment, and artifact reduction. This selection process is continuously optimized through a feedback loop that includes quality assessment, ensuring the optimization and enhancement of downstream segmentation. This approach addresses degradation complexity and feature compatibility issues, offering a deployable solution for endoscopic polyp analysis.
Source: IEEE Signal Processing Letters
Authors: Pu Wang, Zhihua Zhang, Guangwei Gao, Youshan Zhang, Zhuoran Zheng
Language: English
Subfield: Oncology
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W4412610139