|
|
|
| A Novel Computer Aided Alzheimer′s Analysis Approach Based on Regions of Interests of PiB PET Images |
| Duan Huoqiang Shu Xinghui Xu Jun Jiang Jiehui#* |
| 1Institute of Biomedical Engineering, School of Communication and Information Technology, Shanghai University, Shanghai 200444, China |
|
|
|
|
Abstract Alzheimer′s disease (AD) is an irreversible neurodegenerative disease. PiB PET imaging can be used for AD diagnosis in the early stage. However, AD clinical diagnosis based on PiB PET technology is mainly based on visual assessment currently, which relies on the subjective experience of radiologists, leading to inaccurate and inadequate results. This study therefore proposed a computer aided AD diagnosis (CAAD) approach. The CAAD approach applied 3D thresholding-lattice boltzmann model foramyloid-beta (Aβ) ROIs segmentation, PCA method for feature extraction, and SVM with polynomial kernel for AD classification. In order to verify the CAAD approach, comparison experiments were carried out by selecting a total of 149 PiB PET datasheets from ADNI database and PET center of HuashanHospital (Shanghai). Results showed that the average accuracy rate of ROIs segmentation was 91.53%±3.0% in term of Dice coefficient. Besides, the classification accuracy of the novel CAAD approach for AD-healthy control (HC), mild cognitive impairment (MCI)\|HC and AD/MCI-HC achieved 87.01%, 93.04% and 91.95%, respectively. Compared with the AD diagnosis methods in literatures, the CAAD approach could achieve a better accuracy of about 10% higher. These results indicated that the CAAD approach proposed in this study achieved the excellent performance for AD, MCI and HC classification.
|
|
|
|
|
|
|
|
[1] Kemppainen N, Aalto S, Wilson I, et al. PET amyloid ligand [11C] PIB uptake is increased in mild cognitive impairment [J]. Neurology, 2007, 68(19):1603-1606.
[2] Cohen AD, Klunk WE. Early detection of Alzheimer′s disease using PiB and FDG PET [J]. Neurobiology of Disease. 2014,72:117-122.
[3] Price JC, Klunk WE, Lopresti BJ, et al. Kinetic modeling of amyloid binding in humans using PET imaging and Pittsburgh Compound-B [J]. Journal of Cerebral Blood Flow & Metabolism, 2005, 25(11):1528-1547.
[4] Ng S, Villemagne VL, Berlangieri S, et al. Visual assessment versus quantitative assessment of 11C-PIB PET and 18F-FDG PET for detection of Alzheimer′s disease [J]. Journal of Nuclear Medicine, 2007, 48(4):547-552.
[5] llán IA, Górriz JM, Ramírez J, et al. 18F-FDG PET imaging analysis for computer aided Alzheimer′s diagnosis[J]. Information Sciences, 2011, 181(4):903-916.
[6] Zhang Daoqiang, Wang Yaping, Zhou Luping, et al.Multimodal classification of Alzheimer′s disease and mild cognitive impairment[J]. Neuroimage, 2011, 55(3):856-867.
[7] Jiang Jiehui, Shu Xinghui, Liu Xin, et al. A computed aided diagnosis tool for Alzheimer′s disease based on 11C-PiB PET imaging technique [C]// 2015 IEEE International Conference on Information and Automation. New York:IEEE, 2015: 1963-1968.
[8] Aidos H, Duarte J, Fred A. Identifying regions of interest for discriminating Alzheimer′s disease from mild cognitive impairment[C]//2014 IEEE International Conference on Image Processing (ICIP). Paris:IEEE, 2014: 21-25.
[9] Jiang Jiehui, Shu Xinghui, Yan Zhuangzhi, et al. A novel Aβ segmentation algorithm based on 3D Lattice Boltzmann method [J]. Journal of Medical Imaging and Health Informatics, 2015, 5(8): 1921-1925.
[10] Ziolko S, Weissfeld L, Klunk W, et al. Evaluation of voxel-based methods for the statistical analysis of PIB PET amyloid imaging studies in Alzheimer′s disease [J]. Neuroimage, 2006, 33(1): 94-102.
[11] Sonka M, Hlavac V, Boyle R. Image processing, analysis, and machine vision [M]. New York: Springer US, 2014.
[12] Jones G, Ellis KA, Ames D, et al. Regional dynamics of amyloid-b deposition in healthy elderly, mild cognitive impairment and Alzheimer′s disease: A voxelwise PiB\|PET longitudinal study [J]. Brain, 2012, 135: 2126-2139.
[13] Padilla P, López M, Górriz JM, et al. NMF-SVM based CAD tool applied to functional brain images for the diagnosis of Alzheimer′s disease [J]. IEEE Transactions on Medical Imaging, 2012, 31(2): 207-216.
[14] Zhang Daoqiang, Shen Dinggang, Alzheimer′s Disease Neuroimaging Initiative. Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer′s disease [J]. Neuroimage, 2012, 59(2): 895-907.
[15] Varghese T, Kumari RS, Mathuranath PS, et al. Discrimination between Alzheimer′s disease, mild cognitive impairment and normal aging using ANN based MR brain image segmentation[C]//Proceedings of the International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA). Berlin: Springer International Publishing, 2014: 129-136.
[16] Silverman DHS. Brain 18F-FDG PET in the diagnosis of neurodegenerative dementias: comparison with perfusion SPECT and with clinical evaluations lacking nuclear imaging [J]. Journal of Nuclear Medicine, 2004, 45(4): 594-607.
[17] Patwardhan MB, McCrory DC, Matchar DB, et al.Alzheimer disease: Operating characteristics of PET—A meta-analysis 1 [J]. Radiology, 2004, 231(1): 73-80. |
|
|
|
