TY - JOUR
T1 - Development and validation of an interpretable deep learning framework for Alzheimer's disease classification
AU - Qiu, Shangran
AU - Joshi, Prajakta S.
AU - Miller, Matthew I.
AU - Xue, Chonghua
AU - Zhou, Xiao
AU - Karjadi, Cody
AU - Chang, Gary H.
AU - Joshi, Anant S.
AU - Dwyer, Brigid
AU - Zhu, Shuhan
AU - Kaku, Michelle
AU - Zhou, Yan
AU - Alderazi, Yazan J.
AU - Swaminathan, Arun
AU - Kedar, Sachin
AU - Saint-Hilaire, Marie Helene
AU - Auerbach, Sanford H.
AU - Yuan, Jing
AU - Sartor, E. Alton
AU - Au, Rhoda
AU - Kolachalama, Vijaya B.
N1 - Publisher Copyright:
© 2020 The Author(s) (2020). Published by Oxford University Press on behalf of the Guarantors of Brain.
PY - 2020/6/1
Y1 - 2020/6/1
N2 - Alzheimer's disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer's disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer's disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer's disease and cognitively normal subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n = 417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n = 382), the Framingham Heart Study (n = 102), and the National Alzheimer's Coordinating Center (NACC) (n = 582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n = 11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer's disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.
AB - Alzheimer's disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer's disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer's disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer's disease and cognitively normal subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n = 417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n = 382), the Framingham Heart Study (n = 102), and the National Alzheimer's Coordinating Center (NACC) (n = 582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n = 11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer's disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.
KW - Alzheimer's disease
KW - biomarkers
KW - dementia
KW - neurodegeneration
KW - structural MRI
UR - http://www.scopus.com/inward/record.url?scp=85086624180&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086624180&partnerID=8YFLogxK
U2 - 10.1093/brain/awaa137
DO - 10.1093/brain/awaa137
M3 - Article
C2 - 32357201
AN - SCOPUS:85086624180
SN - 0006-8950
VL - 143
SP - 1920
EP - 1933
JO - Brain
JF - Brain
IS - 6
ER -