Abstract
Neuroimaging foundation models pretrained on large, predominantly western cohorts are increasingly proposed as general-purpose backbones for brain MRI analysis. Yet, their ability to generalize to underrepresented clinical populations remains largely untested. We evaluate four recent foundation models (BrainIAC, NeuroJEPA, NeuroVFM, and Primus) on a three-way diagnostic classification task (Control, Dementia, Parkinson’s disease) using a cohort of 88 subjects from a Nigerian clinical brain MRI dataset, across four modality configurations (T1w, T2w, T1w+T2w, FLAIR), and compare against an end-to-end trained ViT3D baseline. All four frozen backbones collapse to majority-class predictions, while NeuroJEPA on FLAIR shows modest but still limited discrimination. In contrast, the end-to-end trained ViT3D achieves higher accuracy and MCC on every task (up to 53.4% accuracy, MCC=0.27) and is the only model with non-trivial recall. Our findings suggest that these frozen neuroimaging foundation models are insufficient for fine-grained diagnostic classification in small, non-western clinical cohorts, motivating parameter-efficient adaptation and broader multi-site external validation for equitable deployment in global health settings.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/AFRICAI_040.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=2k6KnDI0Mx
BibTex
@InProceedings{AkiOlu_Evaluating_MICCAISAT2026,
author = { Akinmuleya, Oluwatobi Iyanuoluwa AND Akano, Olatokun Shamsudeen AND Ankapong, Samuel Danquah AND Lawal, Olamide AND Musah, Toufiq},
title = { { Evaluating the Generalization of Neuroimaging Foundation Models on African Brain MRI } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17264},
month = {pending},
page = {pending}
}