Dual-branch multi-information aggregation network with transformer and convolution for polyp segmentation

• Published in: Computers in biology and medicine Vol. 168; p. 107760
• Main Authors: Zhang, Wenyu, Lu, Fuxiang, Su, Hongjing, Hu, Yawen
• Format: Journal Article
• Language: English
• Published: United States Elsevier Limited 01.01.2024
• Subjects: Algorithms; Artificial neural networks; Blurring; Colon; Colonic Polyps - diagnostic imaging; Colonoscopy; Convolution; Datasets; Deep learning; Diagnosis, Computer-Assisted; Humans; Image Processing, Computer-Assisted; Light reflection; Machine learning; Modules; Motion effects; Neural networks; Neural Networks, Computer; Polyps; Segmentation; State of the art; Transformers; Information aggregation; CNN; Transformer; Polyp segmentation
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107760

Computer-Aided Diagnosis (CAD) for polyp detection offers one of the most notable showcases. By using deep learning technologies, the accuracy of polyp segmentation is surpassing human experts. In such CAD process, a critical step is concerned with segmenting colorectal polyps from colonoscopy images. Despite remarkable successes attained by recent deep learning related works, much improvement is still anticipated to tackle challenging cases. For instance, the effects of motion blur and light reflection can introduce significant noise into the image. The same type of polyps has a diversity of size, color and texture. To address such challenges, this paper proposes a novel dual-branch multi-information aggregation network (DBMIA-Net) for polyp segmentation, which is able to accurately and reliably segment a variety of colorectal polyps with efficiency. Specifically, a dual-branch encoder with transformer and convolutional neural networks (CNN) is employed to extract polyp features, and two multi-information aggregation modules are applied in the decoder to fuse multi-scale features adaptively. Two multi-information aggregation modules include global information aggregation (GIA) module and edge information aggregation (EIA) module. In addition, to enhance the representation learning capability of the potential channel feature association, this paper also proposes a novel adaptive channel graph convolution (ACGC). To validate the effectiveness and advantages of the proposed network, we compare it with several state-of-the-art (SOTA) methods on five public datasets. Experimental results consistently demonstrate that the proposed DBMIA-Net obtains significantly superior segmentation performance across six popularly used evaluation matrices. Especially, we achieve 94.12% mean Dice on CVC-ClinicDB dataset which is 4.22% improvement compared to the previous state-of-the-art method PraNet. Compared with SOTA algorithms, DBMIA-Net has a better fitting ability and stronger generalization ability.