发表机构
Department of Mechanical Engineering, Boston University; The Photonics Center, Boston University; Rafik B. Hariri Institute for Computing and Computational Science & Engineering, Boston University; Department of Radiology, Boston University Chobanian & Avedisian School of Medicine; Department of Radiology, Boston Medical Center; Department of Electrical and Computer Engineering, Boston University; Department of Biomedical Engineering, Boston University; Division of Materials Science and Engineering, Boston University（波士顿大学机械工程系; 波士顿大学光子中心; 波士顿大学拉菲克·B·哈里里计算与计算科学与工程研究所; 波士顿大学切博尼亚与阿维迪亚安医学学院放射科; 波士顿医学中心放射科; 波士顿大学电气与计算机工程系; 波士顿大学生物医学工程系; 波士顿大学材料科学与工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出NeuroBridge框架，通过大规模自监督MRI预训练与多任务学习（海马分割、萎缩分类、重建）及门控融合微调，在AD和MCI诊断中达到88.17%准确率，优于单任务方法。
AI 中文摘要
引言：基于MRI准确识别阿尔茨海默病（AD）、轻度认知障碍（MCI）及相关痴呆仍具挑战，因为疾病相关的结构变化通常微妙且异质。我们开发了NeuroBridge，一个临床引导的多任务MRI框架用于神经退行性疾病诊断。方法：NeuroBridge将大规模自监督MRI预训练与海马分割、海马萎缩分类和重建目标相结合，随后进行门控融合微调。在ADNI和OASIS队列中评估性能，包括跨队列迁移、基于概率的分析和机会性筛查。结果：NeuroBridge在评估的分类任务中达到最高性能，在ADNI中AD与认知正常对照的准确率为88.17%，在OASIS中为82.78%。最大的提升出现在MCI相关和混合诊断设置中。该框架展示了强大的跨队列泛化能力、预测类别概率与准确性之间的系统关联，以及基于概率的机会性筛查的可行性。讨论：临床引导的多任务表示学习超越了传统的单任务方法，改善了神经退行性MRI诊断。NeuroBridge为痴呆评估和基于MRI的机会性筛查提供了一个稳健且可扩展的框架。
英文摘要
Accurate MRI-based identification of Alzheimer's disease (AD), mild cognitive impairment (MCI), and related dementias remains challenging because disease-related structural changes are often subtle and heterogeneous. We developed NeuroBridge, a clinically guided multi-task MRI framework for neurodegenerative disease diagnosis. NeuroBridge integrates large-scale self-supervised MRI pretraining with hippocampal segmentation, hippocampal atrophy classification, and reconstruction objectives, followed by gated fusion fine-tuning. Performance was evaluated across ADNI and OASIS cohorts, including cross-cohort transfer, probability-based analysis, and opportunistic screening. NeuroBridge achieved the highest performance across evaluated classification tasks, reaching 88.17% accuracy for AD versus cognitively normal controls in ADNI and 82.78% in OASIS. The largest gains occurred in MCI-related and mixed-diagnosis settings. The framework demonstrated strong cross-cohort generalization, systematic associations between predicted-class probability and accuracy, and the feasibility of probability-based opportunistic screening. Clinically guided multi-task representation learning improves neurodegenerative MRI diagnosis beyond conventional single-task approaches. NeuroBridge provides a robust and scalable framework for dementia assessment and MRI-based opportunistic screening.
Comments5 figures. 3 tables
