TY - JOUR
T1 - Multi-Site Infant Brain Segmentation Algorithms
T2 - The iSeg-2019 Challenge
AU - Sun, Yue
AU - Gao, Kun
AU - Wu, Zhengwang
AU - Li, Guannan
AU - Zong, Xiaopeng
AU - Lei, Zhihao
AU - Wei, Ying
AU - Ma, Jun
AU - Yang, Xiaoping
AU - Feng, Xue
AU - Zhao, Li
AU - Le Phan, Trung
AU - Shin, Jitae
AU - Zhong, Tao
AU - Zhang, Yu
AU - Yu, Lequan
AU - Li, Caizi
AU - Basnet, Ramesh
AU - Ahmad, M. Omair
AU - Swamy, M. N.S.
AU - Ma, Wenao
AU - Dou, Qi
AU - Bui, Toan Duc
AU - Noguera, Camilo Bermudez
AU - Landman, Bennett
AU - Gotlib, Ian H.
AU - Humphreys, Kathryn L.
AU - Shultz, Sarah
AU - Li, Longchuan
AU - Niu, Sijie
AU - Lin, Weili
AU - Jewells, Valerie
AU - Shen, Dinggang
AU - Li, Gang
AU - Wang, Li
N1 - Publisher Copyright:
© 1982-2012 IEEE.
PY - 2021/5
Y1 - 2021/5
N2 - To better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; h owever, one of the major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, the iSeg-2019 challenge (http://iseg2019.web.unc.edu) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. T raining/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participated in the iSeg-2019. In this article, 8 top-ranked methods were reviewed by detailing their pipelines/implementations, presenting experimental results, and evaluating performance across different sites in terms of whole brain, regions of interest, and gyral landmark curves. We further pointed out their limitations and possible directions for addressing the multi-site issue. We find that multi-site consistency is still an open issue. We hope that the multi-site dataset in the iSeg-2019 and this review article will attract more researchers to address the challenging and critical multi-site issue in practice.
AB - To better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; h owever, one of the major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, the iSeg-2019 challenge (http://iseg2019.web.unc.edu) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. T raining/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participated in the iSeg-2019. In this article, 8 top-ranked methods were reviewed by detailing their pipelines/implementations, presenting experimental results, and evaluating performance across different sites in terms of whole brain, regions of interest, and gyral landmark curves. We further pointed out their limitations and possible directions for addressing the multi-site issue. We find that multi-site consistency is still an open issue. We hope that the multi-site dataset in the iSeg-2019 and this review article will attract more researchers to address the challenging and critical multi-site issue in practice.
KW - Infant brain segmentation
KW - deep learning
KW - domain adaptation
KW - isointense phase
KW - low tissue contrast
KW - multi-site issue
UR - http://www.scopus.com/inward/record.url?scp=85100450936&partnerID=8YFLogxK
U2 - 10.1109/TMI.2021.3055428
DO - 10.1109/TMI.2021.3055428
M3 - Article
C2 - 33507867
AN - SCOPUS:85100450936
SN - 0278-0062
VL - 40
SP - 1363
EP - 1376
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
IS - 5
M1 - 9339962
ER -