| 研究概要 |
Dementia is an age-related cognitive decline, which is indicated by an early degeneration of cortical and sub-cortical structures. Characterizing those morphological changes can help understand the disease development and contribute to early prediction and prevention.
Nonlinear dynamics, geostatistics and chaos were used to extract structural features of the brains on magnetic resonance imaging (MRI). These features were used to train hidden Markov models (HMM) for pattern classification. The proposed HMM have succeeded in recognition of individual who has mild Alzheimer's disease and achieved better classification accuracy compared to other related methods using different features and classifiers.
The findings from this research will allow individual classification to support the early diagnosis and prediction of dementia. By using the brain MRI-based HMM developed in our proposed research, it will be more efficient, robust and can be easily used by clinicians as a computer-aid tool for validating imaging bio-markers for early prediction of dementia.
|
