ICA-Based Automatic Classification of Magnetic Resonance Images from ADNI Data
This paper proposes a novel method of automatic classification of magnetic resonance images based on independent component analysis (ICA). The ICA-based method is composed of three steps. First, all magnetic resonance imaging (MRI) scans are aligned and normalized by statistical parametric mapping. Then FastICA is applied to the pre-processed images for extracting specific neuroimaging components as potential classifying feature. Finally, the separated independent coefficients are fed into a classifying machine that discriminates among Alzheimers patients, and mild cognitive impairment, and control subjects. In this study, the MRI data is selected from the Alzheimers Disease Neuroimaging Initiative databases. The experimental results show that our method can successfully differentiate subjects with Alzheimers disease and mild cognitive impairment from normal controls.
Alzheimers disease mild cognitive impairment magnetic resonance imaging independent component analysis support vector machine
Wenlu Yang Xinyun Chen Hong Xie Xudong Huang
Department of Electronic Engineering, Shanghai Maritime University,Shanghai 200135, China Department Department of Electronic Engineering, Shanghai Maritime University,Shanghai 200135, China Department of Radiology, Brigham and Womens Hospital,and Harvard Medical School, Boston, MA, USA
国际会议
无锡
英文
340-347
2010-09-17（万方平台首次上网日期，不代表论文的发表时间）