Toggle light / dark theme

ProMUSE: Progressive Multimodal Uncertainty-Guided Staged Evidential Alzheimer Disease Classification

Alzheimer’s disease (AD) is a fatal disorder that destroys memory and cognitive skills in the elderly population. Treatments for AD are most effective in the early stage, leading to an increasing demand for early AD diagnosis increasingly relies on multimodal data, such as clinical assessments, structural magnetic resonance imaging (MRI), and positron emission tomography (PET) imaging. However, MRI and PET acquisition remain costly and not universally accessible, making all-modality inference impractical in real-world clinical workflows. We propose a progressive multimodal uncertainty-guided staged evidential network (ProMUSE) that adaptively determines when additional modalities are necessary. This helps reduce the overall cost of data acquisition while maintaining accuracy.

Leave a Comment

Lifeboat Foundation respects your privacy! Your email address will not be published.