联合图像配准的脑卒中病灶自动分割方法研究  

Research on automatic segmentation method of stroke lesions jointwith image registration

作　　者：李欣蔚 许炜鑫 陈勇 秦对 张冰玉 李章勇[1] 王伟[1] LI Xinwei;XU Weixin;CHEN Yong;QIN Dui;ZHANG Bingyu;LI Zhangyong;WANG Wei(Research Center of Biomedical Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,P.R.China;First Affiliated Hospital of Army Medical University,Department of Medical Engineering,Chongqing 400038,P.R.China)

机构地区：[1]重庆邮电大学生物医学工程研究中心,重庆400065 [2]陆军军医大学第一附属医院医学工程科,重庆400038

出　　处：《重庆邮电大学学报（自然科学版）》2024年第4期729-737,共9页Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)

基　　金：国家自然科学基金项目(62106032,62171073,62311530103);教育部“春晖计划”合作科研项目(HZKY20220209)。

摘　　要：针对目前慢性脑卒中的病灶分割准确性相对较低的问题,提出了一种联合深度图像配准的慢性脑卒中自动分割方法。采用深度拉普拉斯金字塔图像配准网络,在微分同胚映射的空间内以从粗到细的方式获得大脑分区,以得到病灶位置的解剖先验信息;将原始磁共振图像和配准阶段的分区结果联合,输入到加入了通道和空间注意力模块的U-Net进行病灶分割。在公开的数据集ATLAS上进行测试表明,提出的方法有效提高了慢性脑卒中病灶分割的准确性,比经典的2D U-Net提升了4.4百分点,证明了基于深度图像配准的大脑分区先验可有效增强模型对病灶的分割性能,更好的组织分割能提高病灶分割准确性。To address the challenge of relatively low segmentation accuracy in chronic stroke lesions,we propose a novel approach for automatic segmentation in chronic stroke using joint deep image registration.The method employs a deep Laplacian pyramid image registration network to obtain brain tissue partitions in a coarse-to-fine manner within the space of diffeomorphic mappings,acquiring anatomical prior information for lesion locations.The original MRI images and the results from the registration phase are then combined and fed into a U-Net augmented with channel and spatial attention modules for lesion segmentation.Testing on the publicly available ATLAS dataset demonstrates the effectiveness of the proposed method in improving the accuracy of chronic stroke lesion segmentation.It achieves a 4.4%improvement over the classical 2D U-Net,highlighting that the deep image registration-based brain partition prior effectively enhances the model’s segmentation performance.Moreover,superior tissue segmentation contributes to better lesion segmentation accuracy.

关 键 词：慢性脑卒中 图像配准 病灶分割 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]