Multitemplate-based brain morphometric pattern analysis using magnetic resonance imaging has recently been proposed for automatic diagnosis of Alzheimer's disease (AD) and its prodromal stage (ie, mild cognitive impairment or MCI). In such methods, multiview morphological patterns generated from multiple templates are used as feature representation for brain images. This chapter presents some of the latest advancements in multitemplate-based multiview learning for AD and MCI diagnosis. We will first present a multiview feature representation method by employing multiple templates. Then we will discuss how to make use of those multiview representations for effective diagnosis of AD and MCI. Specifically, we will introduce four multiview learning methods for AD/MCI classification, and demonstrate that these methods can further promote the disease diagnosis performance.
|Title of host publication||Machine Learning and Medical Imaging|
|Number of pages||39|
|Publication status||Published - 2016 Aug 9|
- Alzheimer's disease
- Disease diagnosis
- Multiview representation
ASJC Scopus subject areas