Differentiating Dementia with Lewy Bodies and Alzheimer's Disease by Deep Learning to Structural MRI.

BACKGROUND AND PURPOSE: Dementia with Lewy bodies (DLB) is the second most prevalent cause of degenerative dementia next to Alzheimer's disease (AD). Though current DLB diagnostic criteria employ several indicative biomarkers, relative preservation of the medial temporal lobe as revealed by structural MRI suffers from low sensitivity and specificity, making them unreliable as sole supporting biomarkers. In this study, we investigated how a deep learning approach would be able to differentiate DLB from AD with structural MRI data. METHODS: Two-hundred and eight patients (101 DLB, 69 AD, and 38 controls) participated in this retrospective study. Gray matter images were extracted using voxel-based morphometry (VBM). In order to compare the conventional statistical analysis with deep-learning feature extraction, we built a classification model for DLB and AD with a residual neural network (ResNet) type of convolutional neural network architecture, which is one of the deep learning models. The anatomically standardized gray matter images extracted in the same way as for the VBM process were used as inputs, and the classification performance achieved by our model was evaluated. RESULTS: Conventional statistical analysis detected no significant atrophy other than fine differences on the middle temporal pole and hippocampal regions. The feature extracted by the deep learning method differentiated DLB from AD with 79.15％ accuracy compared to the 68.41% of the conventional method. CONCLUSIONS: Our results confirmed that the deep learning method with gray matter images can detect fine differences between DLB and AD that may be underestimated by the conventional method.

Association between cognitive quotient test score and hippocampal volume: a novel, rapid application-based screening tool.

We aimed to develop a brief, preclinical test to screen the reduced hippocampal volume that is a marker of early dementia [Cognitive Quotient (CQ) test]. We performed an observational study of adult subjects who underwent brain MRI in seven institutions from February 2018 to May 2019. The CQ test consists of five components: (1) digits forward, (2) digits backward, (3) Stroop test, (4) simple calculation, and (5) mental rotation. The primary outcome measure was hippocampal volume. We separated the data into derivation (n = 322) and validation cohorts (n = 96). In the derivation cohort, we built two scoring systems using the results of CQ test (model 1 and 2). In the validation cohort, we validated the correlation of the scoring systems with hippocampal volume. In the derivation cohort, there was a moderate correlation between the scoring systems and hippocampal volume [e.g., correlation coefficient = 0.62 in model 1 (95% CI 0.44-0.75)]. Likewise, in the validation cohort, there was a moderate correlation between the scoring systems and hippocampal volume [e.g., correlation coefficient = 0.54 in model 2 (95% CI 0.38-0.67)]. In this analysis of 418 participants, the score of newly developed CQ test was correlated with hippocampal volume.