Aggelos K. Katsaggelos

This paper uses geometric deep learning to predict sex and age from brain shape data, achieving high accuracy and correlation.

This paper introduces geometric deep learning frameworks for analyzing brain morphology in Alzheimer's disease, showing improved classification and morphological insights compared to prior methods.

This paper develops a 3D-CNN model using transfer learning to predict conversion from MCI to DAT, achieving 82.4% accuracy and identifying key brain regions associated with disease progression.

This paper proposes an attention-based multiple instance learning approach for CT hemorrhage detection using scan-level labels, achieving better performance than methods relying on slice-level annotations.

This study uses geometric deep learning to predict fluid intelligence from brain morphology across two cohorts, finding that amygdala, hippocampus, and specific cortical regions are key predictors.