A multi-scale feature capturing and spatial position attention model for colorectal polyp image segmentation.
10.7507/1001-5515.202412012
- Author:
Wen GUO
1
;
Xiangyang CHEN
1
;
Jian WU
1
;
Jiaqi LI
2
;
Pengxue ZHU
3
Author Information
1. School of Computer Science & Engineering Artificial Intelligence, Wuhan Institute of Technology, Wuhan 430205, P. R. China.
2. CCCC Fifth Engineering Co., Ltd, Beijing 102308, P. R. China.
3. School of Mathematics & Information, China West Normal University, Nanchong, Sichuan 637001, P. R. China.
- Publication Type:Journal Article
- Keywords:
Attention mechanism;
Colorectal polyp;
Deep learning;
Medical image segmentation;
Multi-scale feature fusion
- MeSH:
Humans;
Colonic Polyps/diagnostic imaging*;
Colorectal Neoplasms/diagnostic imaging*;
Neural Networks, Computer;
Image Processing, Computer-Assisted/methods*;
Algorithms;
Early Detection of Cancer
- From:
Journal of Biomedical Engineering
2025;42(5):910-918
- CountryChina
- Language:Chinese
-
Abstract:
Colorectal polyps are important early markers of colorectal cancer, and their early detection is crucial for cancer prevention. Although existing polyp segmentation models have achieved certain results, they still face challenges such as diverse polyp morphology, blurred boundaries, and insufficient feature extraction. To address these issues, this study proposes a parallel coordinate fusion network (PCFNet), aiming to improve the accuracy and robustness of polyp segmentation. PCFNet integrates parallel convolutional modules and a coordinate attention mechanism, enabling the preservation of global feature information while precisely capturing detailed features, thereby effectively segmenting polyps with complex boundaries. Experimental results on Kvasir-SEG and CVC-ClinicDB demonstrate the outstanding performance of PCFNet across multiple metrics. Specifically, on the Kvasir-SEG dataset, PCFNet achieved an F1-score of 0.897 4 and a mean intersection over union (mIoU) of 0.835 8; on the CVC-ClinicDB dataset, it attained an F1-score of 0.939 8 and an mIoU of 0.892 3. Compared with other methods, PCFNet shows significant improvements across all performance metrics, particularly in multi-scale feature fusion and spatial information capture, demonstrating its innovativeness. The proposed method provides a more reliable AI-assisted diagnostic tool for early colorectal cancer screening.
