TY - JOUR
T1 - Diagnostic and Prognostic Classification of Brain Disorders Using Residual Learning on Structural MRI Data
AU - Abrol, Anees
AU - Rokham, Hooman
AU - Calhoun, Vince D.
PY - 2019/7/1
Y1 - 2019/7/1
N2 - In this work, we study the potential of the deep residual neural network (ResNet) architecture to learn abstract neuroanatomical alterations in the structural MRI data by evaluating its diagnostic and prognostic classification performance on two large, independent multi-group (ADNI and BSNIP) neuroimaging datasets. We conduct several binary classification tasks to assess the diagnostic/prognostic performance of the ResNet architecture through a rigorous, repeated and stratified k-fold cross-validation procedure for each of the classification tasks independently. We obtained better than state of the art performance for the clinically most important task in the ADNI dataset analysis, and significantly higher classification accuracies over a standard machine learning method (linear SVM) in each of the ADNI and BSNIP classification tasks. Overall, our results indicate the high potential of this architecture to learn effectual feature representations from structural brain imaging data.
AB - In this work, we study the potential of the deep residual neural network (ResNet) architecture to learn abstract neuroanatomical alterations in the structural MRI data by evaluating its diagnostic and prognostic classification performance on two large, independent multi-group (ADNI and BSNIP) neuroimaging datasets. We conduct several binary classification tasks to assess the diagnostic/prognostic performance of the ResNet architecture through a rigorous, repeated and stratified k-fold cross-validation procedure for each of the classification tasks independently. We obtained better than state of the art performance for the clinically most important task in the ADNI dataset analysis, and significantly higher classification accuracies over a standard machine learning method (linear SVM) in each of the ADNI and BSNIP classification tasks. Overall, our results indicate the high potential of this architecture to learn effectual feature representations from structural brain imaging data.
UR - http://www.scopus.com/inward/record.url?scp=85077980962&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077980962&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2019.8857902
DO - 10.1109/EMBC.2019.8857902
M3 - Article
C2 - 31946769
AN - SCOPUS:85077980962
SN - 2694-0604
VL - 2019
SP - 4084
EP - 4088
JO - Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
JF - Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
ER -