AI RESEARCH
NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding
arXiv CS.LG
•
ArXi:2605.20525v1 Announce Type: cross We present NeuroQA, a large-scale benchmark for visual question answering in 3D brain magnetic resonance imaging (MRI), with 56,953 QA pairs from 12,977 subjects across 12 datasets. It spans ages 5-104 and five clinical domains: Alzheimer's, Parkinson's, tumors, white matter disease, and neurodevelopment. Unlike prior medical Visual Question Answering (VQA) efforts that operate on 2D slices or rely on narrow diagnostic labels, NeuroQA pairs every item with a full 3D volume.