计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240700030-9.doi: 10.11896/jsjkx.240700030

• 智能医学工程 • 上一篇    下一篇

基于ESC-TransUNet网络的脑出血CT图像分割

谭佳慧1, 文琛言1, 黄巍2, 胡凯1   

  1. 1 湘潭大学计算机学院网络空间安全学院 湖南 湘潭 411105
    2 长沙市第一医院放射科计算机医学图像处理研究中心 长沙 410005
  • 出版日期:2025-06-16 发布日期:2025-06-12
  • 通讯作者: 胡凯(kaihu@xtu.edu.cn)
  • 作者简介:(3035993981@qq.com)
  • 基金资助:
    国家自然科学基金(62272404);湖南省普通高等学校教学改革研究项目(202401000574);湖南省科技厅项目(2021SK53105);湖南省教育厅项目(23A0146);湖南省大学生创新创业训练计划项目(S202310530024)

CT Image Segmentation of Intracranial Hemorrhage Based on ESC-TransUNet Network

TAN Jiahui1, WEN Chenyan1, HUANG Wei2, HU Kai1   

  1. 1 School of Computer Science & School of Cyberspace Science,Xiangtan University,Xiangtan,Hunan 411105,China
    2 Computer Medical Image Processing Research Center,Department of Radiology,Changsha First Hospital,Changsha 410005,China
  • Online:2025-06-16 Published:2025-06-12
  • About author:TAN Jiahui,born in 2003,undergra-duate.Her main research interests include deep learning and medical image processing.
    HU Kai,born in 1984,Ph.D,professor,is a senior member of CCF(No.46150S).His main research interests include machine learning,pattern recognition,bioinformatics,and medical ima-ge processing.
  • Supported by:
    National Natural Science Foundation of China(62272404),Research Project on Teaching Reform of Colleges in Hunan Province(202401000574),Science and Technology Department of Hunan Province(2021SK53105),Project of Education Department of Hunan Province(23A0146) and Innovation and Entrepreneurship Training Program for Hunan University Students(S202310530024).

PDF (PC)

43

摘要： 针对脑出血CT图像处理中遇到的出血区域空间位置、形状、尺寸多变性以及与周围组织强度值相近导致边界难以确定等挑战,提出了一种改进TransUNet的图像分割模型(ESC-TransUNet)。该模型首先在上采样前增添了显式视觉中心(Explicit Visual Center,EVC),能够捕获图像中远距离像素的关联程度,并保留输入图像中局部边角区域的详细信息,有助于有效提取出血区域特征。其次,在编码器阶段引入了注意力混洗机制(Shuffle Attention,SA),有效地学习了出血区域与背景间的微小差异,从而提高了分割任务的精确度。最后,在解码器阶段采用CBM2结构促进信息更有效传递,增强模型泛化能力和准确性。在脑出血公开数据集Physionet(PHY) 上进行了大量实验,结果表明,所提方法超过了其他9种主要的分割方法,在脑出血CT图像分割任务中获得了更优异的性能。

关键词: 深度学习, CT图像, 脑出血分割, 注意力混洗机制, 显式视觉中心

Abstract: In view of the challenges encountered in CT image processing of intracranial hemorrhage,such as the variability of the spatial position,shape and size of the hemorrhage region and the difficulty in determining the boundary due to the similar intensity value of the surrounding tissue,an improved TransUNet image segmentation model(ESC-TransUNet) is proposed.Firstly,an explicit visual center(EVC) is added to the model before upsampling,which can capture the correlation degree of far-distance pixels in the image and retain the detailed information of local corner regions in the input image,which is helpful to effectively extract the features of the bleeding region.Secondly,a shuffle attention(SA) mechanism is introduced in the encoder stage,which effectively learns the small differences between the bleeding area and the background,thus improving the accuracy of the segmentation task.Finally,CBM2 structure is used in the decoder stage to promote more effective information transmission and enhance the generalization ability and accuracy of the model.Numerous experiments have been conducted on Physionet(PHY),a publicly available dataset on intracranial hemorrhage.The results show that the proposed method outperforms the other nine main segmentation methods and achieves better performance in the task of intracranial hemorrhage CT image segmentation.

Key words: Deep learning, CT images, Intracranial hemorrhage segmentation, Shuffle attention mechanism, Explicit visual center

中图分类号: 

  • TP391
[1]QURESHI A I,MENDELOW A D,HANLEY D F.Intracerebral haemorrhage[J].The Lancet,2009,373(9675):1632-1644.
[2]RAMPHUL K,RAMPHUL Y,SOMBANS S L,et al.Inci-dence and mortality rates of acute ischemic stroke in hospitalized patients in the United States[J].Archives of Medical Science-Atherosclerotic Diseases,2021,6(1):132-134.
[3]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolutional networks for biomedical image segmentation [C]//Medical Image Computing and Computer-assisted Intervention-MICCAI 2015:18th International Conference,Munich,Germany,October 5-9,2015,proceedings,part III.Springer International Publishing,2015:234-241.
[4]MILLETARI F,NAVAB N,AHMADI S A.V-net:Fully convolutional neural networks for volumetric medical image segmentation[C]//In 2016 Fourth International Conference on 3D Vision(3DV).IEEE,2016:565-571.
[5]ZHANG Z,LIU Q,WANG Y.Road extraction by deep residual u-net[J].IEEE Geoscience and Remote Sensing Letters,2018,15(5):749-753.
[6]ZHOU Z,RAHMAN SIDDIQUEE M M,TAJBAKHSH N,et al.Unet++:A nested u-net architecture for medical image segmentation [C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support:4th International Workshop,DLMIA 2018,and 8th International Workshop,ML-CDS 2018,Held in Conjunction with MICCAI 2018,Granada,Spain,September 20,2018,Proceedings.Springer International Publishing,2018:3-11.
[7]OKTAY O,SCHLEMPER J,FOLGOC L L,et al.Attention u-net:Learning where to look for the pancreas [J].arXiv:1804.03999,2018.
[8]IBTEHAZ N,RAHMAN M S.MultiResUNet:Rethinkingthe U-Net architecture for multimodal biomedical image segmentation [J].Neural Networks,2020,121:74-87.
[9]ALOM M Z,YAKOPCIC C,TAHA T M,et al.Nuclei segmentation with recurrent residual convolutional neural networks based U-Net(R2U-Net)[C]//Proceedings of NAECON 2018-IEEE National Aerospace and Electronics Conference.IEEE,2018:228-233.
[10]ASHISH V.Attention is all you need [C]//Advances in Neural Information Processing Systems.2017.
[11]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An image is worth 16x16 words [J].arXiv:2010.11929,2020.
[12]CHEN J,LU Y,YU Q,et al.Transunet:Transformers makestrong encoders for medical image segmentation [J].arXiv:2102.04306,2021.
[13]ZHANG Y,LIU H,HU Q.Transfuse:Fusing transformers and CNNs for medical image segmentation [C]//Medical Image Computing and Computer Assisted Intervention－MICCAI 2021:24th International Conference,Strasbourg,France,September 27-October 1,2021,Proceedings,Part I.Springer International Publishing,2021:14-24.
[14]CAO H,WANG Y,CHEN J,et al.Swin-UNet:UNet-like pure transformer for medical image segmentation [C]//European Conference on Computer Vision.Cham:Springer Nature Swit-zerland,2022:205-218.
[15]QUAN Y,ZHANG D,ZHANG L,et al.Centralized feature pyramid for object detection [J].IEEE Transactions on Image Processing,2023,32(6):1234-1245.
[16]ZHANG Q L,YANG Y B.Sa-net:Shuffle attention for deep convolutional neural networks [C]//ICASSP 2021－2021 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2021:2235-2239.
[17]MISRA D.Mish:A self regularized non-monotonic activationfunction [J].arXiv:1908.08681,2019.
[18]MA N,ZHANG X,ZHENG H T,et al.Shufflenet v2:Practical guidelines for efficient CNN architecture design [C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:116-131.
[19]HSSAYENI M,CROOCK M,SALMAN A,et al.Computedtomography images for intracranial hemorrhage detection and segmentation.Intracranial hemorrhage segmentation using a deep convolutional model [J].Data,2020,5(1):14.
[20]YIN B,ZHANG X,HOU Q,et al.Camoformer:Masked separable attention for camouflaged object detection [J].arXiv:2212.06570,2022.
[21]ROY S,KOEHLER G,ULRICH C,et al.MedNext:Transformer-driven scaling of ConvNets for medical image segmentation [C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham:Springer Nature Switzerland,2023:405-415.
[22]SUN G,PAN Y,KONG W,et al.DA-TransUNet:IntegratingSpatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentation [J].arXiv:2310.12570,2023.
[23]CHEN Y,ZOU B,GUO Z,et al.ScUnet++:Swin-UNet and CNN bottleneck hybrid architecture with multi-fusion dense skip connection for pulmonary embolism CT image segmentation [C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.IEEE/CVF,2024:7759-7767.
[24]LAN L,CAI P,JIANG L,et al.BRAU-Net++:U-ShapedHybrid CNN-Transformer Network for Medical Image Segmentation [J].arXiv:2401.00722,2024.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发