Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer s disease classification

Y. Liu, L. Teverovskiy, O. Carmichael, R. Kikinis, M. E. Shenton, C. C. Carter, A. Stenger, S. Davis, H. Aizenstien, J. T. Becker, O. L. Lopes, C. C. Meltzer
Proceedings of the 7th International Conference on Medical Image Computing and Computer Assisted Intervention MICCAI, 2004
Pages 393-401
2004

Download full paper

Abstract

We construct a computational framework for automatic central nervous system (CNS) disease discrimination using high resolution Magnetic Resonance Images (MRI) of human brains. More than 3000 MR image features are extracted, forming a high dimensional coarse-to-fine hierarchical image description that quantifies brain asymmetry, texture and statistical properties in corresponding local regions of the brain. Discriminative image feature subspaces are computed, evaluated and selected automatically. Our initial experimental results show 100 and first episode SZ versus their respective matched controls. Under the same computational framework, we also find higher than 95 separability among Alzheimerrsquos Disease, mild cognitive impairment patients, and their matched controls. An average of 88 success rate is achieved using leave-one-out cross validation on five different well-chosen patient-control image sets of sizes from 15 to 27 subjects per disease class.

Reference

Liu Y, Teverovskiy L, Carmichael O, Kikinis R, Shenton ME, Carter CC, Stenger A, Davis S, Aizenstien H, Becker JT, Lopes OL, Meltzer CC. Discriminative mr image feature analysis for automatic schizophrenia and alzheimer s disease classification. In C Barillot, DR Haynor, P Hellier, eds., Proceedings of the 7th International Conference on Medical Image Computing and Computer Assisted Intervention MICCAI, 2004. Springer-Verlag GmbH, 2004;393-401.

Grants

PO1 AG04953, PO1 DA015900-01
© 2013 Psychiatry Neuroimaging Laboratory | Last updated 04.15.2013