Unified Deep Learning For Simultaneous Cardiac Cine MRI Reconstruction, Motion Estimation And Segmentation

doi:10.1109/ISBI56570.2024.10635390

	Unified Deep Learning For Simultaneous Cardiac Cine MRI Reconstruction, Motion Estimation And Segmentation
	Qian Pengfang; Zhou Zijian; Hu Peng; Qi Haikun
	2024
会议录名称	21ST IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING
ISSN	1945-7928
发表状态	已发表
DOI	10.1109/ISBI56570.2024.10635390
摘要	Deep learning methods have achieved great success in cardiac cine MRI reconstruction, motion estimation, and segmentation. However, most studies considered the three tasks separately. While benefits have been shown for dual-task learning, such as motion-compensated cine MRI reconstruction and motion-guided cine segmentation, a framework considering all three tasks to more effectively exploit inter-task dependency remains uninvestigated. To fill this gap, we propose a unified approach that adopts groupwise image registration to estimate motion between cine frames, which is leveraged to assist reconstruction and segmentation. In particular, motion-augmented images enhance the reconstruction task, and motion-generated annotations offer additional supervision for the segmentation task. The improved reconstruction and segmentation will in turn help to yield more accurate motion estimation. We embed the three tasks in an unrolled framework, enabling iterative coarse-to-fine refinement of predictions across all tasks. Experimental results on a cine MRI dataset show the superior performance of the proposed method compared with the single-task and dual-task baseline methods.
会议录编者/会议主办者	AI2D Center ; et al. ; Therapanacea ; Thermo Fisher Scientific ; United Imaging Intelligence ; Verasonics
关键词	Contrastive Learning Deep learning Deep reinforcement learning Image annotation Image enhancement Image reconstruction Image registration Image segmentation Motion capture Motion compensation Motion estimation Cardiac cine MRI Cine-MRI Deep learning Dual-tasks Learning methods Motion segmentation Motion-compensated reconstruction MRI reconstruction Segmentation Task learning
会议名称	21st IEEE International Symposium on Biomedical Imaging, ISBI 2024
会议地点	Athens, Greece
会议日期	27-30 May 2024
URL	查看原文
收录类别	EI
语种	英语
出版者	IEEE Computer Society
EI入藏号	20243717024349
EI主题词	Magnetic resonance imaging
EISSN	1945-8452
EI分类号	1101.2 ; 1101.2.1 ; 1106.3.1 ; 709 Electrical Engineering, General ; 746 Imaging Techniques
原始文献类型	Conference article (CA)
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/357336
专题	生物医学工程学院_PI研究组_胡鹏组信息科学与技术学院_硕士生生物医学工程学院生物医学工程学院_PI研究组_齐海坤组
通讯作者	Qian Pengfang
作者单位	School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
第一作者单位	生物医学工程学院
通讯作者单位	生物医学工程学院
第一作者的第一单位	生物医学工程学院
推荐引用方式 GB/T 7714	Qian Pengfang,Zhou Zijian,Hu Peng,et al. Unified Deep Learning For Simultaneous Cardiac Cine MRI Reconstruction, Motion Estimation And Segmentation[C]//AI2D Center, et al., Therapanacea, Thermo Fisher Scientific, United Imaging Intelligence, Verasonics:IEEE Computer Society,2024.