AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

OpenBrain: An Auditable Generated-Label Release for Whole-Brain MRI Parcellation

Qizhen Lan, Yu-Chun Hsu, YUXIANG WEI, Lijing Zhu, Zenan Sun, Liang He, Lishan Yu, Xiaoqian Jiang

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces OpenBrain, a confidence-aware, provenance-verified release of 35,838 generated whole-brain MRI parcellations from 607 OpenNeuro T1w datasets, organized as auditable case records.

Problem

Generated whole-brain MRI parcellation releases at cohort scale provide little evidence about which cases are reliable enough for reuse.

Approach

Releases generated labels as an auditable case-record collection with per-case confidence and provenance verification, rather than a directory of standalone segmentation files.

Key results

Measured effects reported in the paper

What was changedWhereMeasuredEffect
retain only lowest-risk 25% of cases by QC-7 riskgenerated whole-brain labels · IXImacro Dice: +1.3 ppImproved
retain only lowest-risk 25% of cases by QC-7 riskgenerated whole-brain labels · BrainLatmacro Dice: +3.7 ppImproved
retain only lowest-risk 25% of cases by QC-7 riskgenerated whole-brain labels · Mindboggle-101 (manual labels)macro Dice: +1.5 ppImproved
select lower-risk instead of random training cases (1,000 budget)nnU-Net trained on OpenBrain · Mindboggle-101macro Dice: 0.710 -> 0.746Improved
select higher-risk instead of random training casesnnU-Net trained on OpenBrain · Mindboggle-101macro Dice: 0.710 -> 0.456Hurt
evaluate on small-structure subset onlylower-risk training selection · BrainLat small structuresDef-A Dice: +0.4 pp, CI [-0.5, +1.2]No clear effect
remove any single committee axis from QC-7 (ablation)QC-7 aggregate · cross-cohort mean, K=25%macro Dice gain: about 0.1 pp changeNo clear effect
merge committee axes into one term (ablation)QC-7 aggregate · cross-cohort mean, K=25%macro Dice gain: 2.17 -> 2.04Hurt
add committee axes to r1-r4 (ablation)QC-7 aggregate · cross-cohort mean, K=25%macro Dice gain: 1.51 -> 2.17Improved
use 110-label instead of 96-label evaluation space (ablation)QC-7 retention · IXImacro Dice gain: +1.3 -> +1.6No clear effect

Experimental setup

Datasets: OpenNeuro T1w datasets

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy