摘要
Segmentation of intracranial aneurysm(IA)from computed tomography angiography(CTA)images is of significant importance for quantitative assessment of IA and further surgical treatment.Manual segmentation of IA is a labor-intensive,time-consuming job and suffers from inter-and intra-observer variabilities.Training deep neural networks usually requires a large amount of labeled data,while annotating data is very time-consuming for the IA segmentation task.This paper presents a novel weight-perceptual self-ensembling model for semi-supervised IA segmentation,which employs unlabeled data by encouraging the predictions of given perturbed input samples to be consistent.Considering that the quality of consistency targets is not comparable to each other,we introduce a novel sample weight perception module to quantify the quality of different consistency targets.Our proposed module can be used to evaluate the contributions of unlabeled samples during training to force the network to focus on those well-predicted samples.We have conducted both horizontal and vertical comparisons on the clinical intracranial aneurysm CTA image dataset.Experimental results show that our proposed method can improve at least 3%Dice coefficient over the fully-supervised baseline,and at least 1.7%over other state-of-the-art semi-supervised methods.
作者
李才子
刘瑞强
钟焕新
范峻铭
司伟鑫
张猛
王平安
Cai-Zi Li;Rui-Qiang Liu;Huan-Xin Zhong;Jun-Ming Fan;Wei-Xin Si;Meng Zhang;Pheng-Ann Heng(Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen 518055,China;University of Chinese Academy of Sciences,Beijing 100049,China;Shantou University,Shantou 515063,China;Shenzhen Second People′s Hospital,Shenzhen 518035,China;Department of Computer Science and Engineering,The Chinese University of Hong Kong,Hong Kong 999077,China)
基金
supported by Shenzhen Fundamental Research Program of China under Grant Nos.JCYJ20200109110420626 and JCYJ20200109110208764
the National Natural Science Foundation of China under Grant Nos.U1813204 and 61802385
the Natural Science Foundation of Guangdong of China under Grant No.2021A1515012604
the Clinical Research Project of Shenzhen Municiple Health Commission under Grant No.SZLY2017011.
