A k-Space Super-Resolution and Registration-Guided Thalamic Subregions Segmentation Model for Analyzing Thalamic Iron Changes in AD

Motivation: Alzheimer's disease (AD) lacks effective treatment, and investigating iron homeostasis in specific thalamic subregions may reveal new pathological insights. Goal(s): This study aims to identify precise imaging biomarkers and therapeutic targets through quantitative iron analysis of 50 thalamic subregions. Approach: We applied T1-weighted super-resolution reconstruction and a registration-guided deep-learning model for segmenting 50 thalamic subregions, examining iron levels and their correlation with AD severity in 45 AD patients and 53 healthy controls. Results: Significant iron alterations were found in 46 thalamic subregions in AD patients, with positive correlations to cognitive decline (MoCA scores). Impact: There is currently a lack of research on quantitative iron analysis in fine-grained thalamic subregions of AD patients. This study could provide new prognostic assessments and therapeutic target references for AD research.