Domain-Adaptive Diagnosis of Lewy Body Disease with Transferability Aware Transformer

2025-07-07

AI Summary

Diagnosing Lewy body disease (LBD) faces dual challenges of scarce labeled data and significant domain shift between Alzheimer’s disease (AD) and LBD, hindering effective cross-disease knowledge transfer. Method: We propose the first transferability-aware Transformer framework for cross-disease domain adaptation in neurodegenerative disorder diagnosis. Our approach constructs structural brain connectomes from T1-weighted MRI, models global topological patterns via self-attention, and introduces a novel transferability assessment module to dynamically disentangle pathology-relevant shared features from domain-specific confounds. An adaptive weighting strategy further enhances transferable feature representation while suppressing domain noise. Results: Evaluated on small-scale LBD datasets, our method substantially mitigates AD–LBD domain shift, achieving significant accuracy improvements over state-of-the-art baselines. This work establishes a new paradigm for cross-disease knowledge transfer in rare neurodegenerative disorders.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Lewy Body Disease (LBD) is a common yet understudied form of dementia that imposes a significant burden on public health. It shares clinical similarities with Alzheimer's disease (AD), as both progress through stages of normal cognition, mild cognitive impairment, and dementia. A major obstacle in LBD diagnosis is data scarcity, which limits the effectiveness of deep learning. In contrast, AD datasets are more abundant, offering potential for knowledge transfer. However, LBD and AD data are typically collected from different sites using different machines and protocols, resulting in a distinct domain shift. To effectively leverage AD data while mitigating domain shift, we propose a Transferability Aware Transformer (TAT) that adapts knowledge from AD to enhance LBD diagnosis. Our method utilizes structural connectivity (SC) derived from structural MRI as training data. Built on the attention mechanism, TAT adaptively assigns greater weights to disease-transferable features while suppressing domain-specific ones, thereby reducing domain shift and improving diagnostic accuracy with limited LBD data. The experimental results demonstrate the effectiveness of TAT. To the best of our knowledge, this is the first study to explore domain adaptation from AD to LBD under conditions of data scarcity and domain shift, providing a promising framework for domain-adaptive diagnosis of rare diseases.

Problem

• Diagnosing Lewy Body Disease with limited data availability
• Addressing domain shift between Alzheimer's and Lewy Body Disease datasets
• Transferring knowledge from Alzheimer's to enhance LBD diagnosis

Innovation

• Transferability Aware Transformer for domain adaptation
• Adaptive weighting of disease-transferable features
• Structural MRI-derived connectivity as training data