发表机构
Shenyang Medical College; University of Ibadan; University of Ghana; Obafemi Awolowo University; Kwame Nkrumah University of Science and Technology（沈阳医学院; 伊巴丹大学; 加纳大学; 奥巴费米·阿沃洛沃大学; 夸梅·恩克鲁玛科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究评估四个神经影像基础模型在非洲脑MRI诊断任务上的泛化能力，发现冻结模型表现不足，而端到端训练的ViT3D取得最佳效果，提示需参数高效适应与多站点验证。
AI 中文摘要
在大型、主要来自西方人群的数据集上预训练的神经影像基础模型，越来越多地被提议作为脑MRI分析的通用骨干网络。然而，它们对代表性不足的临床人群的泛化能力在很大程度上仍未得到检验。我们使用来自尼日利亚临床脑MRI数据集的88名受试者队列，在四种模态配置（T1w、T2w、T1w+T2w、FLAIR）下，评估了四个近期基础模型（BrainIAC、Neuro-JEPA、NeuroVFM和Primus）在三分类诊断任务（对照、痴呆、帕金森病）上的表现，并与端到端训练的ViT3D基线进行比较。冻结的骨干网络退化为多数类预测，而Neuro-JEPA在FLAIR上表现出适度但仍有限的判别能力。相比之下，端到端训练的ViT3D在每个任务上都取得了更高的准确率和MCC（最高准确率53.4%，MCC=0.27），并且是唯一具有非平凡召回率的模型。我们的研究结果表明，这些冻结的神经影像基础模型不足以在小型、非西方的临床队列中进行细粒度诊断分类，这促使需要参数高效的适应和更广泛的多站点外部验证，以在全球健康环境中实现公平部署。
英文摘要
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, Neuro-JEPA, 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. The frozen backbones collapse to majority-class predictions, while Neuro-JEPA 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.
CommentsMICCAI AFRICAI Workshop, Strasbourg, France, 2026, 10 Pages, 1 Figure, 2 Tables
