AUTHOR=Qureshi Muhammad Naveed Iqbal , Ryu Seungjun , Song Joonyoung , Lee Kun Ho , Lee Boreom 

TITLE=Evaluation of Functional Decline in Alzheimer’s Dementia Using 3D Deep Learning and Group ICA for rs-fMRI Measurements

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=11

YEAR=2019

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2019.00008

DOI=10.3389/fnagi.2019.00008

ISSN=1663-4365

ABSTRACT=<p><bold>Purpose</bold>: To perform automatic assessment of dementia severity using a deep learning framework applied to resting-state functional magnetic resonance imaging (rs-fMRI) data.</p><p><bold>Method</bold>: We divided 133 Alzheimer’s disease (AD) patients with clinical dementia rating (CDR) scores from 0.5 to 3 into two groups based on dementia severity; the groups with very mild/mild (CDR: 0.5–1) and moderate to severe (CDR: 2–3) dementia consisted of 77 and 56 subjects, respectively. We used rs-fMRI to extract functional connectivity features, calculated using independent component analysis (ICA), and performed automated severity classification with three-dimensional convolutional neural networks (3D-CNNs) based on deep learning.</p><p><bold>Results</bold>: The mean balanced classification accuracy was 0.923 ± 0.042 (<italic>p</italic> &lt; 0.001) with a specificity of 0.946 ± 0.019 and sensitivity of 0.896 ± 0.077. The rs-fMRI data indicated that the medial frontal, sensorimotor, executive control, dorsal attention, and visual related networks mainly correlated with dementia severity.</p><p><bold>Conclusions</bold>: Our CDR-based novel classification using rs-fMRI is an acceptable objective severity indicator. In the absence of trained neuropsychologists, dementia severity can be objectively and accurately classified using a 3D-deep learning framework with rs-fMRI independent components.</p>