DocumentCode :
3141861
Title :
3D texture analysis of hippocampus based on MR images in patients with alzheimer disease and mild cognitive impairment
Author :
Li, Xin ; Xia, Hong ; Zhou, Zhen ; Tong, Longzheng
Author_Institution :
Sch. of Biomed. Eng., Capital Med. Univ., Beijing, China
Volume :
1
fYear :
2010
fDate :
16-18 Oct. 2010
Firstpage :
1
Lastpage :
4
Abstract :
Alzheimer´s disease (AD) is the most common type of dementia. Mild cognitive impairment (MCI) is considered as a transition stage between normal aging and dementia. In this study, 3D texture analysis was performed on magnetic resonance images (MRI) of 12 early AD patients, 12 MCI patients and 12 normal controls. Texture features of the hippocampus were extracted from gray level co-occurrence matrix and run length matrix, and were tested significant differences among three groups. Meanwhile the correlation between texture features and MMSE scores were calculated. The results showed that texture features including entropy, grey level nonuniformity and run length nonuniformity in hippocampus were significantly different among groups, and they were correlated with MMSE scores. The study suggested that 3D texture analysis could describe the pathological changes of hippocampus in patients with early AD and MCI, and could be helpful to early diagnosis of AD.
Keywords :
biomedical MRI; brain; cognition; diseases; feature extraction; image texture; medical image processing; neurophysiology; 3D texture analysis; Alzheimer disease; MRI; entropy; gray level co-occurrence matrix; grey level nonuniformity; hippocampus; magnetic resonance imaging; mild cognitive impairment; texture feature extraction; Alzheimer´s disease; Correlation; Entropy; Hippocampus; Magnetic resonance imaging; Three dimensional displays; 3D texture analysis; Alzheimer´s disease (AD); Magnetic resonance images (MRI); Mild cognitive impairment (MCI);
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6495-1
Type :
conf
DOI :
10.1109/BMEI.2010.5639520
Filename :
5639520
Link To Document :
بازگشت