MRI-based age prediction using hidden Markov models

• Published in: Journal of neuroscience methods Vol. 199; no. 1; pp. 140 - 145
• Main Authors: Wang, Bing, Pham, Tuan D.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.07.2011
• Subjects: Age Factors; Age prediction; Aged; Aged, 80 and over; Algorithms; Alzheimer Disease - pathology; Anthropometry - methods; Atrophy; Brain - growth & development; Brain - pathology; Cerebral Cortex - growth & development; Cerebral Cortex - pathology; Cerebrospinal Fluid; Databases, Factual; Female; Hidden Markov models; Humans; Kullback–Leibler divergence; Magnetic Resonance Imaging - methods; Male; Markov Chains; Middle Aged; MRI; Myelin Sheath - ultrastructure; Neurons - ultrastructure; Organ Size; Reference Values; Vector quantization; Wavelet Analysis; Wavelet transforms; Wavelet transforms; Kullback–Leibler divergence; Age prediction; Vector quantization; MRI; Hidden Markov models
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2011.04.022

► Age prediction based on MRI is useful for early diagnosis of neurodegenerative diseases. ► We model the MRI-based structure of the brain using hidden Markov models. ► Experimental results show its superior age prediction with very small training data. 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 disorders such as Alzheimer's disease is reported to be faster than the average speed. Therefore, neurodegenerative disease is considered as accelerated ageing. Accurate detection of accelerated ageing based on the magnetic resonance imaging (MRI) 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. In order to capture the faster structural alterations in the brain with ageing, we propose in this paper a computational approach for modelling the MRI-based structure of the brain using the framework of hidden Markov models, which can be utilized for age prediction. Experiments were carried out on healthy subjects to validate its accuracy and its robustness. The results have shown its ability of predicting the brain age with an average normalized age-gap error of two to three years, which is superior to several recently developed methods for brain age prediction.