Simultaneous Matrix Diagonalization for Structural Brain Networks Classification
This addresses the challenge of small sample size and high dimensionality in brain disease classification for medical diagnosis, though it appears incremental.
The paper tackles brain disease classification from connectome data by using simultaneous approximate diagonalization of adjacency matrices to compute stable eigenstructures as features, achieving competitive performance with state-of-the-art methods for Alzheimer's disease detection.
This paper considers the problem of brain disease classification based on connectome data. A connectome is a network representation of a human brain. The typical connectome classification problem is very challenging because of the small sample size and high dimensionality of the data. We propose to use simultaneous approximate diagonalization of adjacency matrices in order to compute their eigenstructures in more stable way. The obtained approximate eigenvalues are further used as features for classification. The proposed approach is demonstrated to be efficient for detection of Alzheimer's disease, outperforming simple baselines and competing with state-of-the-art approaches to brain disease classification.