AUTHOR=Shi Liantao , Wang Yufeng , Li Zhengguo , Qiumiao Wen 

TITLE=FRCNet: Feature Refining and Context-Guided Network for Efficient Polyp Segmentation

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2022.799541

DOI=10.3389/fbioe.2022.799541

ISSN=2296-4185

ABSTRACT=Colorectal cancer, also known as rectal cancer, is one of the most common forms of cancer, and it can be completely cured with early diagnosis.Usually, the most effective and objective method of screening and diagnosis is a colonoscopy.Polyp segmentation plays a crucial role in the diagnosis and treatment of diseases related to the digestive system, providing doctors with detailed auxiliary boundary information during clinical analysis.To this end, we propose a novel light-weight feature refining and context-guided network (FRCNet) for real-time polyp segmentation. To alleviate the interference of background noise and effectively distinguish the target polyps from the background, we first employ the enhanced context calibrated module to extract the most discriminative features by developing long-range spatial dependence through a context-calibrated operation. Furthermore, we also design the progressive context-aware fusion module to dynamically capture multi-scale polyps by collecting multi-range context information.Finally, the multi-scale pyramid aggregation module is used to learn more representative features and fuse them to refine the segmented results. Extensive experiments on the Kvasir-SEG and CVC-ClinicDB datasets demonstrate the effectiveness of the proposed model. Specifically, FRCNet achieves an IoU of 76.98% and Dice score of 84.58%  on the Kvasir-SEG dataset with a model size of only 0.78M parameters, outperforming state-of-the-art methods.