My article on chest and liver cine-MR frame forecasting with transformers and online-trained RNNs (ArXiv preprint)
Graph-structured data classification based on spectral methods and the generalized likelihood ratio test
An application to Alzheimer's disease diagnosis from PET image data
1. Introduction
Brain imaging data often exhibit structured relationships between regions. Instead of treating features independently, this project models PET data for each subject as a signal on a graph, where nodes represent anatomical brain regions and edge weights encode similarity between regions across subjects. The classification task is formulated as a hypothesis test between two graph models (healthy versus diseased), using spectral properties of graph signals.
References
- Chenhui Hu, Jorge Sepulcre, Keith A. Johnson, Georges E. Fakhri, Yue M. Lu, and Quanzheng Li, "Matched signal detection on graphs: Theory and application to brain imaging data classification", NeuroImage (2016)