DMHFR:Decoder with Multi-Head Feature Receptors for Tract Image Segmentation  

作　　者：Jianuo Huang Bohan Lai Weiye Qiu Caixu Xu Jie He 

机构地区：[1]Department of Endoscopy Center,Zhongshan Hospital(Xiamen),Fudan University,Xiamen,361015,China [2]School of Computing and Data Science,Xiamen University Malaysia,Sepang,43900,Malaysia [3]School of Computer Science and Techonology,Tongji University,Shanghai,200092,China [4]Guangxi Key Laboratory of Machine Vision and Intelligent Control,Wuzhou University,Wuzhou,543002,China [5]Xiamen Clinical Research Center for Cancer Therapy,Xiamen,361015,China

出　　处：《Computers, Materials & Continua》2025年第3期4841-4862,共22页计算机、材料和连续体(英文)

基　　金：supported by Xiamen Medical and Health Guidance Project in 2021(No.3502Z20214ZD1070);supported by a grant from Guangxi Key Laboratory of Machine Vision and Intelligent Control,China(No.2023B02).

摘　　要：The self-attention mechanism of Transformers,which captures long-range contextual information,has demonstrated significant potential in image segmentation.However,their ability to learn local,contextual relationships between pixels requires further improvement.Previous methods face challenges in efficiently managing multi-scale fea-tures of different granularities from the encoder backbone,leaving room for improvement in their global representation and feature extraction capabilities.To address these challenges,we propose a novel Decoder with Multi-Head Feature Receptors(DMHFR),which receives multi-scale features from the encoder backbone and organizes them into three feature groups with different granularities:coarse,fine-grained,and full set.These groups are subsequently processed by Multi-Head Feature Receptors(MHFRs)after feature capture and modeling operations.MHFRs include two Three-Head Feature Receptors(THFRs)and one Four-Head Feature Receptor(FHFR).Each group of features is passed through these MHFRs and then fed into axial transformers,which help the model capture long-range dependencies within the features.The three MHFRs produce three distinct feature outputs.The output from the FHFR serves as auxiliary auxiliary features in the prediction head,and the prediction output and their losses will eventually be aggregated.Experimental results show that the Transformer using DMHFR outperforms 15 state of the arts(SOTA)methods on five public datasets.Specifically,it achieved significant improvements in mean DICE scores over the classic Parallel Reverse Attention Network(PraNet)method,with gains of 4.1%,2.2%,1.4%,8.9%,and 16.3%on the CVC-ClinicDB,Kvasir-SEG,CVC-T,CVC-ColonDB,and ETIS-LaribPolypDB datasets,respectively.

关 键 词：Medical image segmentation feature exploration feature aggregation deep learning multi-head feature receptor 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]