Left Atrial Segmentation Combining Multi-atlas Whole Heart Labeling and Shape-Based Atlas Selection

Autor: Gerard Sanroma, Lei Li, Lingchao Xu, Xiahai Zhuang, Marta Nuñez-Garcia, Constantine Butakoff, Oscar Camara
Přispěvatelé: Pop, Mihaela, Sermesant, Maxime, Zhao, Jichao, Li, Shuo, McLeod, Kristin, Young, Alistair, Rhode, Kawal, Mansi, Tommaso
Jazyk: angličtina
Rok vydání: 2019
Předmět:
Zdroj: Cham : Springer International Publishing, Lecture Notes in Computer Science 11395, 302-310 (2019). doi:10.1007/978-3-030-12029-0_33
Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges / Pop, Mihaela (Editor) ; Cham : Springer International Publishing, 2019, Chapter 33 ; ISSN: 0302-9743=1611-3349 ; ISBN: 978-3-030-12028-3=978-3-030-12029-0 ; doi:10.1007/978-3-030-12029-0
Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges / Pop, Mihaela (Editor) ; Cham : Springer International Publishing, 2019, Chapter 33 ; ISSN: 0302-9743=1611-3349 ; ISBN: 978-3-030-12028-3=978-3-030-12029-0 ; doi:10.1007/978-3-030-12029-0International Workshop on Statistical Atlases and Computational Models of the Heart
Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges ISBN: 9783030120283
STACOM@MICCAI
Popis: Segmentation of the left atria (LA) from late gadolinium enhanced magnetic resonance imaging (LGE-MRI) is challenging since atrial borders are not easily distinguishable in the images. We propose a method based on multi-atlas whole heart segmentation and shape modeling of the LA. In the training phase we first construct whole heart LGE-MRI atlases and build a principal component analysis (PCA) model able to capture the high variability of the LA shapes. All atlases are clustered according to their LA shape using an unsupervised clustering method which additionally outputs the most representative case in each cluster. All cluster representatives are registered to the target image and ranked using conditional entropy. A small subset of the most similar representatives is used to find LA shapes with similar morphology in the training set that are used to obtain the final LA segmentation. We tested our approach using 80 LGE-MRI data for training and 20 LGE-MRI data for testing obtaining a Dice score of \(0.842 \pm 0.049\).
Databáze: OpenAIRE
Externí odkaz: