TY - JOUR
T1 - Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks
T2 - A large-scale study
AU - Gabr, Refaat E.
AU - Coronado, Ivan
AU - Robinson, Melvin
AU - Sujit, Sheeba J.
AU - Datta, Sushmita
AU - Sun, Xiaojun
AU - Allen, William J.
AU - Lublin, Fred D.
AU - Wolinsky, Jerry S.
AU - Narayana, Ponnada A.
N1 - Publisher Copyright:
© The Author(s), 2019.
PY - 2020/9/1
Y1 - 2020/9/1
N2 - Objective: To investigate the performance of deep learning (DL) based on fully convolutional neural network (FCNN) in segmenting brain tissues in a large cohort of multiple sclerosis (MS) patients. Methods: We developed a FCNN model to segment brain tissues, including T2-hyperintense MS lesions. The training, validation, and testing of FCNN were based on ~1000 magnetic resonance imaging (MRI) datasets acquired on relapsing–remitting MS patients, as a part of a phase 3 randomized clinical trial. Multimodal MRI data (dual-echo, FLAIR, and T1-weighted images) served as input to the network. Expert validated segmentation was used as the target for training the FCNN. We cross-validated our results using the leave-one-center-out approach. Results: We observed a high average (95% confidence limits) Dice similarity coefficient for all the segmented tissues: 0.95 (0.92–0.98) for white matter, 0.96 (0.93–0.98) for gray matter, 0.99 (0.98–0.99) for cerebrospinal fluid, and 0.82 (0.63–1.0) for T2 lesions. High correlations between the DL segmented tissue volumes and ground truth were observed (R2 > 0.92 for all tissues). The cross validation showed consistent results across the centers for all tissues. Conclusion: The results from this large-scale study suggest that deep FCNN can automatically segment MS brain tissues, including lesions, with high accuracy.
AB - Objective: To investigate the performance of deep learning (DL) based on fully convolutional neural network (FCNN) in segmenting brain tissues in a large cohort of multiple sclerosis (MS) patients. Methods: We developed a FCNN model to segment brain tissues, including T2-hyperintense MS lesions. The training, validation, and testing of FCNN were based on ~1000 magnetic resonance imaging (MRI) datasets acquired on relapsing–remitting MS patients, as a part of a phase 3 randomized clinical trial. Multimodal MRI data (dual-echo, FLAIR, and T1-weighted images) served as input to the network. Expert validated segmentation was used as the target for training the FCNN. We cross-validated our results using the leave-one-center-out approach. Results: We observed a high average (95% confidence limits) Dice similarity coefficient for all the segmented tissues: 0.95 (0.92–0.98) for white matter, 0.96 (0.93–0.98) for gray matter, 0.99 (0.98–0.99) for cerebrospinal fluid, and 0.82 (0.63–1.0) for T2 lesions. High correlations between the DL segmented tissue volumes and ground truth were observed (R2 > 0.92 for all tissues). The cross validation showed consistent results across the centers for all tissues. Conclusion: The results from this large-scale study suggest that deep FCNN can automatically segment MS brain tissues, including lesions, with high accuracy.
KW - artificial intelligence
KW - Deep learning
KW - tissue classification
KW - white matter lesions
UR - http://www.scopus.com/inward/record.url?scp=85067845872&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85067845872&partnerID=8YFLogxK
U2 - 10.1177/1352458519856843
DO - 10.1177/1352458519856843
M3 - Article
C2 - 31190607
AN - SCOPUS:85067845872
SN - 1352-4585
VL - 26
SP - 1217
EP - 1226
JO - Multiple Sclerosis Journal
JF - Multiple Sclerosis Journal
IS - 10
ER -