GL-Segnet: Global-Local representation learning net for medical image segmentation

Frontiers in Neuroscience

Neuroscience

Hui Chen¹  Qi Wang²  Di Gai²  Weidong Min²  Zheng Huang²  Pengxiang Su³  Yusong Xiao³  Jiqian Zhang³ 

[1] Office of Administration, Jiangxi Provincial Institute of Cultural Relics and Archaeology, Nanchang, China;School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China;Jiangxi Key Laboratory of Smart City, Nanchang, China;Institute of Metaverse, Nanchang University, Nanchang, China;School of Software, Nanchang University, Nanchang, China;

关键词: neuroscience;    medical image segmentation;    vision transformer;    Global-Local representation learning;    multi-scale feature fusion;   

DOI  :  10.3389/fnins.2023.1153356

 received in 2023-01-29, accepted in 2023-03-20,  发布年份 2023

来源: Frontiers

【 摘 要 】

Medical image segmentation has long been a compelling and fundamental problem in the realm of neuroscience. This is an extremely challenging task due to the intensely interfering irrelevant background information to segment the target. State-of-the-art methods fail to consider simultaneously addressing both long-range and short-range dependencies, and commonly emphasize the semantic information characterization capability while ignoring the geometric detail information implied in the shallow feature maps resulting in the dropping of crucial features. To tackle the above problem, we propose a Global-Local representation learning net for medical image segmentation, namely GL-Segnet. In the Feature encoder, we utilize the Multi-Scale Convolution (MSC) and Multi-Scale Pooling (MSP) modules to encode the global semantic representation information at the shallow level of the network, and multi-scale feature fusion operations are applied to enrich local geometric detail information in a cross-level manner. Beyond that, we adopt a global semantic feature extraction module to perform filtering of irrelevant background information. In Attention-enhancing Decoder, we use the Attention-based feature decoding module to refine the multi-scale fused feature information, which provides effective cues for attention decoding. We exploit the structural similarity between images and the edge gradient information to propose a hybrid loss to improve the segmentation accuracy of the model. Extensive experiments on medical image segmentation from Glas, ISIC, Brain Tumors and SIIM-ACR demonstrated that our GL-Segnet is superior to existing state-of-art methods in subjective visual performance and objective evaluation.

【 授权许可】

Unknown   
Copyright © 2023 Gai, Zhang, Xiao, Min, Chen, Wang, Su and Huang.