{"data":{"id":3,"backendId":"98dd9de4-e116-46c8-b146-bf808aceff47","title":"Learning Under Extreme Data Scarcity: Subject-Level Evaluation of Lightweight CNNs for fMRI-Based Prodromal Parkinsons Detection","summary":"arXiv:2603.00060v1 Announce Type: new Abstract: Deep learning is often applied in settings where data are limited, correlated, and difficult to obtain, yet evaluation practices do not always reflect these constraints. Neuroimaging for prodromal Parkinsons disease is one such case, where subject numbers are small and individual scans produce many highly related samples. This work examines prodromal Parkinsons detection from resting-state fMRI as a machine learning problem centered on learning und","analysis":"This paper provides high methodological value for medical AI by addressing a common error (data leakage) in a high-stakes diagnostic use case.","category":"technology","strategicTrack":"biotech","capitalRelevance":{"social":2,"cultural":4,"economic":5,"physical":7,"symbolic":3,"temporal":6,"informational":8,"psychological":1,"technological":9},"tags":["fMRI","Parkinsons Disease","Deep Learning","Data Scarcity","Medical AI","CNN"],"qualityScore":10,"valueScore":8,"interestScore":7,"potentialScore":8,"uniquenessScore":8,"sourceCount":1,"confidence":5,"detectedAt":"2026-03-04T10:13:18.217Z","createdAt":"2026-03-04 13:49:27"}}