NeuroBridge: Bridging Multi-Task MRI Knowledge for Neurodegenerative Disease Diagnosis

2026-07-01

AI Summary

This study addresses the diagnostic challenges posed by the subtle and highly heterogeneous structural changes in Alzheimer’s disease (AD) and related cognitive impairments on MRI. To this end, the authors propose NeuroBridge, a novel framework that integrates large-scale self-supervised MRI pretraining with clinically guided multitask learning—encompassing hippocampal segmentation, atrophy classification, and image reconstruction—and employs a gating mechanism for adaptive feature fusion and probability-driven opportunistic screening. The approach substantially enhances model generalization and diagnostic performance in both mixed-diagnosis and cross-cohort settings, achieving AD classification accuracies of 88.17% and 82.78% on the ADNI and OASIS datasets, respectively. Notably, it demonstrates exceptional performance in mild cognitive impairment (MCI) detection and mixed-diagnosis scenarios, underscoring its strong potential for clinical translation.

Abstract

INTRODUCTION: 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. METHODS: 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. RESULTS: 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. DISCUSSION: 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.

Problem

• Alzheimer's disease
• mild cognitive impairment
• MRI diagnosis
• neurodegenerative disease
• structural heterogeneity

Innovation

• multi-task learning
• self-supervised pretraining
• gated fusion
• hippocampal segmentation
• cross-cohort generalization