TY - GEN
T1 - Late Fusion U-Net with GAN-Based Augmentation for Generalizable Cardiac MRI Segmentation
AU - Al Khalil, Yasmina
AU - Amirrajab, Sina
AU - Pluim, Josien
AU - Breeuwer, Marcel
N1 - Publisher Copyright:
© 2022, Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - Accurate segmentation of the right ventricle (RV) in cardiac magnetic resonance (CMR) images is crucial for ventricular structure and function assessment. However, due to its variable anatomy and ill-defined borders, RV segmentation remains an open problem. While recent advances in deep learning show great promise in tackling these challenges, such methods are typically developed on homogeneous data-sets, not reflecting realistic clinical variation in image acquisition and pathology. In this work, we develop a model, aimed at segmenting all three cardiac structures in a multi-center, multi-disease and multi-view setting, using data provided by the M&Ms-2 challenge. We propose a pipeline addressing various aspects of segmenting heterogeneous data, consisting of heart region detection, augmentation through image synthesis and multi-fusion segmentation. Our extensive experiments demonstrate the importance of different elements of the pipeline, achieving competitive results for RV segmentation in both short-axis and long-axis MR images.
AB - Accurate segmentation of the right ventricle (RV) in cardiac magnetic resonance (CMR) images is crucial for ventricular structure and function assessment. However, due to its variable anatomy and ill-defined borders, RV segmentation remains an open problem. While recent advances in deep learning show great promise in tackling these challenges, such methods are typically developed on homogeneous data-sets, not reflecting realistic clinical variation in image acquisition and pathology. In this work, we develop a model, aimed at segmenting all three cardiac structures in a multi-center, multi-disease and multi-view setting, using data provided by the M&Ms-2 challenge. We propose a pipeline addressing various aspects of segmenting heterogeneous data, consisting of heart region detection, augmentation through image synthesis and multi-fusion segmentation. Our extensive experiments demonstrate the importance of different elements of the pipeline, achieving competitive results for RV segmentation in both short-axis and long-axis MR images.
KW - Cardiac MR segmentation
KW - Domain generalization
KW - Late-fusion network
KW - Medical image synthesis
UR - https://www.scopus.com/pages/publications/85124029184
U2 - 10.1007/978-3-030-93722-5_39
DO - 10.1007/978-3-030-93722-5_39
M3 - Conference contribution
AN - SCOPUS:85124029184
SN - 978-3-030-93721-8
T3 - Lecture Notes in Computer Science (LNCS)
SP - 360
EP - 373
BT - Statistical Atlases and Computational Models of the Heart. Multi-Disease, Multi-View, and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge
A2 - Puyol Antón, Esther
A2 - Pop, Mihaela
A2 - Martín-Isla, Carlos
A2 - Sermesant, Maxime
A2 - Suinesiaputra, Avan
A2 - Camara, Oscar
A2 - Lekadir, Karim
A2 - Young, Alistair
PB - Springer
CY - Cham
T2 - 12th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2021 held in conjunction with MICCAI 2021
Y2 - 27 September 2021 through 27 September 2021
ER -
