Title
AtrialJSQnet: A New framework for joint segmentation and quantification of left atrium and scars incorporating spatial and shape information
Abstract
•Formulate a new framework, where left atrial (LA) segmentation, scar projection onto the LA surface and scar quantification are performed simultaneously.•Solve a challenging task, i.e., fully automated atrial scar quantification from LGE MRI, with promising results compared to the results or algorithms reported in the literature.•Propose a new spatial encoding loss to incorporates spatial information of LA and scars, and explicitly utilize the spatial relationship between LA and scars by shape attention.•Provide thorough validation and parameter studies for the proposed techniques on a public dataset.
Year
DOI
Venue
2022
10.1016/j.media.2021.102303
Medical Image Analysis
Keywords
DocType
Volume
Atrial segmentation,Scar quantification,Spatial encoding,Shape attention
Journal
76
ISSN
Citations 
PageRank 
1361-8415
1
0.36
References 
Authors
0
4
Name
Order
Citations
PageRank
Lei Li1335.37
Veronika A. M. Zimmer2177.66
Julia A Schnabel31978151.49
Xiahai Zhuang441138.76