Work

An adaptive fusion of composite attention convolutional neural network for polyp image segmentation

Year: 2026

Type: article

Abstract: Background: Accurate localization and segmentation of polyp lesions in colonoscopic images are crucial for the early diagnosis of colorectal cancer and treatment planning. However, endoscopic imaging is often affected by noise interference. This includes issues like uneven illumination, mucosal reflections, and motion artifacts. To mitigate the impact of such interference on segmentation performance, it is essential to integrate multi-scale feature analysis effectively. Features at different scales capture distinct aspects of image information. Yet, existing methods typically rely on simple feature summation or concatenation. These methods lack the capability for adaptive fusion across scales. Methods: To address these limitations, this paper proposes AFCNet-an Adaptive Fusion Composite Attention Convolutional Neural Network. AFCNet is designed to improve robustness against noise interference and enhance multi-scale feature fusion for polyp segmentation. The key innovations of AFCNet include: (1) integrating depthwise separable convolution with attention mechanisms in a multi-branch architecture. This allows for the simultaneous extraction of fine details and salient features. (2) Constructing a dynamic multi-scale feature pyramid with learnable weight allocation for adaptive cross-scale fusion. Results: in IoU, validating its effectiveness and generalization capability in polyp segmentation tasks. Conclusion: AFCNet is a novel polyp segmentation network that leverages convolutional attention and adaptive multi-scale feature fusion, delivering exceptional generalization and adaptability.

Source: Frontiers in Physiology

DOI: 10.3389/fphys.2025.1678403

Authors: Bojiao Jin, Yi Zhang, Qianqing Nie, Lin Qi, Wei Qian

Institution: Northeastern University

Language: English

Topic: Colorectal Cancer Screening and Detection

Subfield: Oncology

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $3,801