AI summaryⓘ
The authors studied how different ways of dividing the brain into regions (parcellation) and analyzing these regions affect the detection of Alzheimer's disease (AD). They compared fast deep learning methods for brain parcellation with a standard clinical tool using data from OASIS-1. They tested different combinations of parcellation methods, volume measurement techniques, and types of classifiers that determine AD diagnosis. Their evaluation used statistical confidence intervals to measure performance. This helps understand which combinations work best for AD detection.
brain parcellationAlzheimer's diseasedeep learningFreeSurferOASIS-1 datasetvolumetryclassificationbootstrap confidence intervalsfeedforward networksensemble methods
Authors
Jiadao Zou, Hongyu Guo, Wei Xi
Abstract
Brain parcellation and classification are typically evaluated in isolation, yet downstream AD detection performance depends on their interaction. We decouple these components and systematically benchmark fast deep learning parcellation methods (SynthSeg+, OpenMAP-T1) against the FreeSurfer (FS-HV) clinical baseline through down- stream AD classification on OASIS-1. Our factorial design evaluates three parcellation methods, two volumetry strategies (hard vs. soft), and four classifier paradigms (clinical thresholds, supervised feedforward networks, ensemble methods, and foundation models with zero/few-shot prompting), with all results quantified using BCa Bootstrap 95% confidence intervals.