Attention based multi-scale parallel network for polyp segmentation

Pengfei Song

doi:10.1016/j.compbiomed.2022.105476

Attention based multi-scale parallel network for polyp segmentation

2022-07-01

39

PRE

AI

DOI：10.1016/j.compbiomed.2022.105476

Original

Original request for help

Save

Abstract

En 中文

Colonoscopy is an effective method for detecting colorectal polyps and preventing colorectal cancer. Therefore, in clinical practice, it is very important to accurately segment the location and shape of polyps from colorectal images, which can effectively assist clinicians in their diagnosis. However, the varying sizes and shapes of colorectal polyps and the fact that the polyps to be segmented are very small and closely resemble their surroundings make this a challenging task. To address these challenges, we propose a parallel network for multiscale attention decoding-AMNet. We first perform multi-scale fusion of the high-level feature information extracted from the backbone network using upsampling and downsampling, while aggregating the high-level feature information to generate an initial predictive segmentation map for subsequent contextual guidance. Using a parallel attention module as well as a reverse fusion module, relationships between regions and boundaries are established to further refine the edge information and improve the accuracy of the segmentation. Through extensive experiments on four publicly available polyp segmentation datasets, it has been demonstrated that our AMNet is effective in improving the accuracy of polyp segmentation.

Keywords:

Polyp segmentation

Colonoscopy

Attention mechanism

Multi-scale fusion

Attention based multi-scale parallel network for polyp segmentation

Abstract

Journal

Organization