DCATNet: polyp segmentation with deformable convolution and contextual-aware attention network

Abstract Polyp segmentation is crucial in computer-aided diagnosis but remains challenging due to the complexity of medical images and anatomical variations. Current state-of-the-art methods struggle with accurate polyp segmentation due to the variability in size, shape, and texture. These factors m...

Full description

Bibliographic Details

Published in:	BMC Medical Imaging
Main Authors:	Zenan Wang, Tianshu Li, Ming Liu, Jue Jiang, Xinjuan Liu
Format:	Article
Language:	English
Published:	BMC 2025-04-01
Subjects:	Transformer Deformable attention Colorectal Polyp polyp segmentation Deep learning
Online Access:	https://doi.org/10.1186/s12880-025-01661-w