UDT:U-shaped deformable transformer for subarachnoid haemorrhage image segmentation  

作　　者：Wei Xie Lianghao Jin Shiqi Hua Hao Sun Bo Sun Zhigang Tu Jun Liu 

机构地区：[1]Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning,Central China Normal University,Wuhan,China [2]School of Computer Science,Central China Normal University,Wuhan,China [3]National Language Resources Monitoring and Research Center for Network Media,Central China Normal University,Wuhan,China [4]The First Affiliated Hospital of Dalian Medical University,Dalian,China [5]State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan,China [6]Information Systems Technology and Design Pillar,Singapore University of Technology and Design,Singapore,Singapore

出　　处：《CAAI Transactions on Intelligence Technology》2024年第3期756-768,共13页智能技术学报（英文）

基　　金：National Natural Science Foundation of China,Grant/Award Numbers:62377026,62201222;Knowledge Innovation Program of Wuhan-Shuguang Project,Grant/Award Number:2023010201020382;National Key Research and Development Programme of China,Grant/Award Number:2022YFD1700204;Fundamental Research Funds for the Central Universities,Grant/Award Numbers:CCNU22QN014,CCNU22JC007,CCNU22XJ034.

摘　　要：Subarachnoid haemorrhage(SAH),mostly caused by the rupture of intracranial aneu-rysm,is a common disease with a high fatality rate.SAH lesions are generally diffusely distributed,showing a variety of scales with irregular edges.The complex characteristics of lesions make SAH segmentation a challenging task.To cope with these difficulties,a u-shaped deformable transformer(UDT)is proposed for SAH segmentation.Specifically,first,a multi-scale deformable attention(MSDA)module is exploited to model the diffuseness and scale-variant characteristics of SAH lesions,where the MSDA module can fuse features in different scales and adjust the attention field of each element dynamically to generate discriminative multi-scale features.Second,the cross deformable attention-based skip connection(CDASC)module is designed to model the irregular edge char-acteristic of SAH lesions,where the CDASC module can utilise the spatial details from encoder features to refine the spatial information of decoder features.Third,the MSDA and CDASC modules are embedded into the backbone Res-UNet to construct the proposed UDT.Extensive experiments are conducted on the self-built SAH-CT dataset and two public medical datasets(GlaS and MoNuSeg).Experimental results show that the presented UDT achieves the state-of-the-art performance.

关 键 词：image segmentation medical image processing 

分 类 号：R743.35[医药卫生—神经病学与精神病学] TP39[医药卫生—临床医学]