Automatic classification on Alzheimer’s Disease based on Hippocampus features from T1-MRI brain image
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In Alzheimer’s disease (AD), the hippocampus is among the first structures, which is affected, due to the neuropil and neurofibrillary tangle thread deposition, which eventually results in a neuronal loss. Moreover, recently a large number of magnetic resonance imagining studies have stated that AD patients has get smaller hippocampus volume as compared to healthy subjects. Hippocampal magnetic resonance imaging volumetric is a potential biomarker for an AD but is hindered by the limitation of manual segmentation and low visualization because of its small structure. To solve that problems, most image analyst used to Freesurfer and FSL for automatic segmentation of brain structures. In this paper, we apply to extract hippocampus region using Freesurfer (v.6.0) automated toolbox for early diagnosis of AD subjects with different groups. a total 158 baseline subjects were used for the experiment, from which 38 patients belong to AD, 46 patients belong to MCIs (stable-MCI, not converted to AD after 18th month of periods) and 36 patients belong to MCIc (converted-MCI, converted to AD within 18th month of periods), and remaining 38 patients belong to elderly normal subjects (NC), and all these subjects were downloaded from Alzheimer’s disease Neuroimaging Initiative database (ADNI). We used the gained hippocampal volumes to discriminate between AD, MCIs, MCIc, and elderly controls (NC) patients. Here, for dimensionality reduction purpose we have used manifold learning based ‘isometric feature mapping’ ISOMAP technique, which only selects the important feature from a bunch of features and later random forest and softmax classifier were used to classify the binary classification problems.
Abstract
In Alzheimer’s disease (AD), the hippocampus is among the first structures, which is affected, due to the neuropil and neurofibrillary tangle thread deposition, which eventually results in a neuronal loss. Moreover, recently a large number of magnetic resonance imagining studies have stated that AD patients has get smaller hippocampus volume as compared to healthy subjects. Hippocampal magnetic resonance imaging volumetric is a potential biomarker for an AD but is hindered by the limitation of manual segmentation and low visualization because of its small structure. To solve that problems, most image analyst used to Freesurfer and FSL for automatic segmentation of brain structures. In this paper, we apply to extract hippocampus region using Freesurfer (v.6.0) automated toolbox for early diagnosis of AD subjects with different groups. a total 158 baseline subjects were used for the experiment, from which 38 patients belong to AD, 46 patients belong to MCIs (stable-MCI, not converted to AD after 18th month of periods) and 36 patients belong to MCIc (converted-MCI, converted to AD within 18th month of periods), and remaining 38 patients belong to elderly normal subjects (NC), and all these subjects were downloaded from Alzheimer’s disease Neuroimaging Initiative database (ADNI). We used the gained hippocampal volumes to discriminate between AD, MCIs, MCIc, and elderly controls (NC) patients. Here, for dimensionality reduction purpose we have used manifold learning based ‘isometric feature mapping’ ISOMAP technique, which only selects the important feature from a bunch of features and later random forest and softmax classifier were used to classify the binary classification problems.
참고문헌 (17)
- Alzheimer’s Disease International World Alzheimer Report 2010The Global Economic Impact of Dementia, "A. Wimo", 56~ (2010)
- C. Wattmo, "Risk Factors That Affect Life Expectancy in Alzheimer’s Disease : A 15-Year Follow-Up", Dement. Geriatr. Cogn. Disord, 38(5–6), pp.286~299 (2014)
- M. W. Weiner, "The Alzheimer’s Disease Neuroimaging Initiative: A review of papers published since its inception", Alzheimers Dement., 8(1), pp.S1~S68 (2012)
- M. Lebreton, "A Critical Role for the Hippocampus in the Valuation of Imagined Outcomes", PLoS Biol, 11(10), pp.e1001684~ (2013)
- H. Braak, "Neuropathological stageing of Alzheimer-related changes", Acta Neuropathol. (Berl.), 82(4), pp.239~259 (1991)
- C. R. Jack, "A", T, Neurology, pp.2016, 87(5)[DOI]
- C. R. Jack, "Steps to standardization and validation of hippocampal volumetry as a biomarker in clinical trials and diagnostic criterion for Alzheimer’s disease", Alzheimers Dement, 7(4), pp.474.e4~485.e4 (2011)
- B. Thyreau, "Segmentation of the hippocampus by transferring algorithmic knowledge for large cohort processing", Med. Image Anal, 43, pp.214~228 (2018)
- R. Seiger, "Cortical Thickness Estimations of FreeSurfer and the CAT12 Toolbox in Patients with Alzheimer’s Disease and Healthy Controls : Cortical Thickness of FreeSurfer and CAT12", J. Neuroimaging, 28(5), pp.515~523 (2018)
- J. L. Winterburn, "A novel in vivo atlas of human hippocampal subfields using highresolution 3T magnetic resonance imaging", NeuroImage, 74, pp.254~265 (2013)
- B. Fischl, "Whole Brain Segmentation", Neuron, 33(3), pp.341~355 (2002)
- R. Cuingnet, "Automatic classification of patients with Alzheimer’s disease from structural MRI : A comparison of ten methods using the ADNI database", NeuroImage, 56(2), pp.766~781 (2011)
- D. Zhang, "Multimodal classification of Alzheimer’s disease and mild cognitive impairment", NeuroImage, 55(3), pp.856~867 (2011)
- Y. Cho, "Individual subject classification for Alzheimer’s disease based on incremental learning using a spatial frequency representation of cortical thickness data", NeuroImage, 59(3), pp.2217~2230 (2012)
- M. W. Weiner, "2014 Update of the Alzheimer’s Disease Neuroimaging Initiative : A review of papers published since its inception", Alzheimers Dement, 11(6), pp.e1~e20 (2015)
- Tin Kam Ho, "The random subspace method for constructing decision forests", IEEE Trans. Pattern Anal. Mach. Intell, 20(8), pp.832~844 (1998)
- Y. Gupta, "Alzheimer’s Disease Diagnosis Based on Cortical and Subcortical Features", J. Healthc. Eng, 2019, pp.1~13 (2019)