The Hidden Markov Brains

Tuan D. Pham

School of Engineering and Information Technology 
The University of New South Wales
Canberra, ACT 2600, Australia

On Sabbatical Leave with Multidisciplinary Parallel-Vector Computing Center
Department of Civil and Environmental Engineering, Norfolk, Virginia, USA

Abstract

This talk presents hidden Markov models (HMM) of the brain on MRI for the
inference of white matter hyperintensities and brain age prediction. Rating and
quantification of cerebral white matter hyperintensities on magnetic resonance
imaging are important tasks in various clinical and scientific settings. We
have recently proposed that prior knowledge about white matter hyperintensities
can be accumulated and utilised to enable a reliable inference of the rating of
a new white matter hyperintensity observation [1]. The use of HMM for rating
inference of white matter hyperintensities can be used as a computerized
rating-assisting tool and can be very economical for diagnostic evaluation of
brain tissue lesions. We have also applied HMM for MRI-based brain age
prediction [2]. Cortical thinning and intracortical gray matter volume losses
are widely observed in normal ageing, while the decreasing rate of the volume
loss in subjects with neurodegenerative diseases such as Alzheimer's disease is
reported to be faster than the average speed.  Therefore, neurodegenerative
disease is considered as accelerated aging.  Accurate detection of accelerated
ageing of the brain is a relatively new direction of research in computational
neuroscience as it has the potential to offer positive clinical outcome through
early intervention.

References 
[1] T.D. Pham, F. Salvetti, B. Wang, M. Diani, W. Heindel, S. Knecht, H.
Wersching, B.T. Baune, K. Berger, The hidden-Markov brain: comparison and
inference of white matter hyperintensities on magnetic resonance imaging (MRI),
Journal of Neural Engineering, 8 (2011) 016004 . 
[2] B. Wang, T.D. Pham, MRI-based age prediction using hidden Markov models, J.
Neuroscience Methods, 199 (2011) 140