Separating dementia with Lewy bodies from Alzheimer's disease dementia using a volumetric MRI classifier.

Objectives: Distinguishing dementia with Lewy bodies (DLB) from Alzheimer's disease (AD) dementia, particularly in patients with DLB and concomitant AD pathology (DLB/AD+), can be challenging and there is no specific MRI signature for DLB. The aim of this study is to examine the additional value of MRI-based brain volumetry in separating patients with DLB (AD+/-) from patients with AD and controls.

Methods: We included 1518 participants from four cohorts (ADC, ADNI, PDBP and PredictND); 147 were patients with DLB (n = 76, DLB/AD+; n = 71, DLB/AD-), 668 patients with AD dementia, and 703 controls. We used an automatic segmentation tool to compute volumes of 70 brain regions, for which age, sex, and head size-dependent z-scores were calculated. We compared individual regions between the diagnostic groups and evaluated whether combining multiple regions improves differentiation. To assess the diagnostic performance, we used the area under the receiver operating characteristic curve (AUC) and sensitivity.

Results: The classifier using the combination of 70 volumetric brain regions correctly classified 60% of patients with DLB and 70% of patients with AD dementia. For DLB vs. AD, the classifier produced an AUC of 0.80 (0.77-0.83), which outperformed the best individual region, hippocampus (AUC: 0.73 [0.69-0.76], p < 0.01). For the comparison of DLB/AD+ vs. AD, the classifier increased the AUC to 0.74 (0.68-0.80), which was 0.70 (0.64-0.76) for the hippocampus, p = 0.25.

Conclusion: Using a combination of volumetric brain regions improved the classification accuracy, and thus the discrimination, of patients with DLB with and without concomitant AD pathology and AD.

Key points: Question No specific MRI signature for dementia with Lewy bodies (DLB) exists, making the differential diagnosis challenging, especially with dementia due to Alzheimer's disease (AD). Findings Volumes of individual brain regions defined by automatic MRI segmentation differed between DLB and AD patients and controls. Clinical relevance Automatic MRI segmentation can contribute to improving the discrimination of patients with DLB and AD, especially in non-specialized memory clinics.