使用因子分析进行特征选择，以使用 18F-FDG PET 图像诊断阿尔茨海默病。
Feature selection using factor analysis for Alzheimer's diagnosis using 18F-FDG PET images.
机构信息
Department of Signal Theory, Networking and Communications, ETSIIT 18071, University of Granada, Granada, Spain.
出版信息
Med Phys. 2010 Nov;37(11):6084-95. doi: 10.1118/1.3488894.
Abstract
PURPOSE
This article presents a computer-aided diagnosis technique for improving the accuracy of the early diagnosis of Alzheimer's disease (AD). Two hundred and ten 18F-FDG PET images from the ADNI initiative [52 normal controls (NC), 114 mild cognitive impairment (MCI), and 53 AD subjects] are studied.
METHODS
The proposed methodology is based on the selection of voxels of interest using the t-test and a posterior reduction of the feature dimension using factor analysis. Factor loadings are used as features for three different classifiers: Two multivariate Gaussian mixture model, with linear and quadratic discriminant function, and a support vector machine with linear kernel.
RESULTS
An accuracy rate up to 95% when NC and AD are considered and an accuracy rate up to 88% and 86% for NC-MCI and NC-MCI,AD, respectively, are obtained using SVM with linear kernel.
CONCLUSIONS
Results are compared to the voxel-as-features and a PCA- based approach and the proposed methodology achieves better classification performance.
摘要
目的
本文提出了一种计算机辅助诊断技术，以提高阿尔茨海默病（AD）早期诊断的准确性。本研究使用了 ADNI 倡议的 210 个 18F-FDG PET 图像[52 名正常对照（NC），114 名轻度认知障碍（MCI）和 53 名 AD 患者]。
方法
该方法基于使用 t 检验选择感兴趣的体素，以及使用因子分析对特征维度进行后向缩减。因子负荷用作三种不同分类器的特征：两个多元高斯混合模型，具有线性和二次判别函数，以及具有线性核的支持向量机。
结果
使用线性核支持向量机，当考虑 NC 和 AD 时，准确率高达 95%，对于 NC-MCI 和 NC-MCI-AD，准确率分别高达 88%和 86%。
结论
将结果与体素特征和基于 PCA 的方法进行比较，该方法实现了更好的分类性能。
相似文献
1
Feature selection using factor analysis for Alzheimer's diagnosis using 18F-FDG PET images.使用因子分析进行特征选择，以使用 18F-FDG PET 图像诊断阿尔茨海默病。
Med Phys. 2010 Nov;37(11):6084-95. doi: 10.1118/1.3488894.
2
Potential Clinical Value of Multiparametric PET in the Prediction of Alzheimer's Disease Progression.多参数PET在预测阿尔茨海默病进展中的潜在临床价值
PLoS One. 2016 May 16;11(5):e0154406. doi: 10.1371/journal.pone.0154406. eCollection 2016.
3
Optimization of Statistical Single Subject Analysis of Brain FDG PET for the Prognosis of Mild Cognitive Impairment-to-Alzheimer's Disease Conversion.用于轻度认知障碍向阿尔茨海默病转化预后评估的脑氟代脱氧葡萄糖正电子发射断层显像统计单受试者分析的优化
J Alzheimers Dis. 2016;49(4):945-959. doi: 10.3233/JAD-150814.
4
Reduced hippocampal metabolism in MCI and AD: automated FDG-PET image analysis.轻度认知障碍和阿尔茨海默病中海马代谢降低：自动氟代脱氧葡萄糖正电子发射断层扫描（FDG-PET）图像分析
Neurology. 2005 Jun 14;64(11):1860-7. doi: 10.1212/01.WNL.0000163856.13524.08.
5
18F-FDG Is a Superior Indicator of Cognitive Performance Compared to 18F-Florbetapir in Alzheimer's Disease and Mild Cognitive Impairment Evaluation: A Global Quantitative Analysis.18F-FDG 在阿尔茨海默病和轻度认知障碍评估中比 18F-氟比他滨更能准确反映认知表现：一项全球定量分析。
J Alzheimers Dis. 2019;70(4):1197-1207. doi: 10.3233/JAD-190220.
6
A Classification Algorithm by Combination of Feature Decomposition and Kernel Discriminant Analysis (KDA) for Automatic MR Brain Image Classification and AD Diagnosis.基于特征分解与核判别分析（KDA）组合的分类算法在自动磁共振脑图像分类与 AD 诊断中的应用。
Comput Math Methods Med. 2019 Dec 30;2019:1437123. doi: 10.1155/2019/1437123. eCollection 2019.
7
Concordance between (99m)Tc-ECD SPECT and 18F-FDG PET interpretations in patients with cognitive disorders diagnosed according to NIA-AA criteria.根据美国国立衰老研究所-阿尔茨海默病协会（NIA-AA）标准诊断的认知障碍患者中，（99m）锝-双半胱乙酯单光子发射计算机断层扫描（（99m）Tc-ECD SPECT）与18F-氟代脱氧葡萄糖正电子发射断层扫描（18F-FDG PET）解读结果的一致性。
Int J Geriatr Psychiatry. 2014 Oct;29(10):1079-86. doi: 10.1002/gps.4102. Epub 2014 Mar 29.
8
Effects of imaging modalities, brain atlases and feature selection on prediction of Alzheimer's disease.成像模态、脑图谱和特征选择对阿尔茨海默病预测的影响。
J Neurosci Methods. 2015 Dec 30;256:168-83. doi: 10.1016/j.jneumeth.2015.08.020. Epub 2015 Aug 28.
9
Classification of Alzheimer's disease from FDG-PET images using favourite class ensembles.使用偏好类集成方法从氟代脱氧葡萄糖正电子发射断层扫描（FDG-PET）图像中对阿尔茨海默病进行分类。
Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:2477-80. doi: 10.1109/EMBC.2013.6610042.
10
Joint Assessment of Quantitative 18F-Florbetapir and 18F-FDG Regional Uptake Using Baseline Data from the ADNI.使用 ADNI 的基线数据联合评估定量 18F-氟比他派和 18F-FDG 区域摄取。
J Alzheimers Dis. 2018;62(1):399-408. doi: 10.3233/JAD-170833.
引用本文的文献
1
Evaluation of Neuro Images for the Diagnosis of Alzheimer's Disease Using Deep Learning Neural Network.使用深度学习神经网络评估神经影像以诊断阿尔茨海默病。
Front Public Health. 2022 Feb 7;10:834032. doi: 10.3389/fpubh.2022.834032. eCollection 2022.
2
Body fat prediction through feature extraction based on anthropometric and laboratory measurements.基于人体测量学和实验室测量的特征提取进行体脂预测。
PLoS One. 2022 Feb 22;17(2):e0263333. doi: 10.1371/journal.pone.0263333. eCollection 2022.
3
Striatal Dopamine Release in Response to Morphine: A [C]Raclopride Positron Emission Tomography Study in Healthy Men.纹状体多巴胺对吗啡的释放：健康男性[C]放射性配体正电子发射断层扫描研究。
Biol Psychiatry. 2019 Sep 1;86(5):356-364. doi: 10.1016/j.biopsych.2019.03.965. Epub 2019 Mar 15.
4
Latent Representation Learning for Alzheimer's Disease Diagnosis With Incomplete Multi-Modality Neuroimaging and Genetic Data.基于不完全多模态神经影像学和遗传数据的阿尔茨海默病诊断的潜在表示学习。
IEEE Trans Med Imaging. 2019 Oct;38(10):2411-2422. doi: 10.1109/TMI.2019.2913158. Epub 2019 Apr 25.
5
Protein-protein interaction sites prediction by ensemble random forests with synthetic minority oversampling technique.基于集成随机森林和合成少数过采样技术的蛋白质-蛋白质相互作用位点预测。
Bioinformatics. 2019 Jul 15;35(14):2395-2402. doi: 10.1093/bioinformatics/bty995.
6
Histogram-Based Features Selection and Volume of Interest Ranking for Brain PET Image Classification.基于直方图的特征选择与脑PET图像分类的感兴趣体积排序
IEEE J Transl Eng Health Med. 2018 Mar 16;6:2100212. doi: 10.1109/JTEHM.2018.2796600. eCollection 2018.
7
Biomarkers of Eating Disorders Using Support Vector Machine Analysis of Structural Neuroimaging Data: Preliminary Results.使用支持向量机分析结构神经影像数据的饮食失调生物标志物：初步结果
Behav Neurol. 2015;2015:924814. doi: 10.1155/2015/924814. Epub 2015 Nov 18.
8
Subspace Regularized Sparse Multitask Learning for Multiclass Neurodegenerative Disease Identification.用于多类神经退行性疾病识别的子空间正则化稀疏多任务学习
IEEE Trans Biomed Eng. 2016 Mar;63(3):607-18. doi: 10.1109/TBME.2015.2466616. Epub 2015 Aug 11.
9
Canonical feature selection for joint regression and multi-class identification in Alzheimer's disease diagnosis.阿尔茨海默病诊断中联合回归和多类识别的规范特征选择
Brain Imaging Behav. 2016 Sep;10(3):818-28. doi: 10.1007/s11682-015-9430-4.
10
2014 Update of the Alzheimer's Disease Neuroimaging Initiative: A review of papers published since its inception.阿尔茨海默病神经影像学计划2014年更新：自启动以来发表论文综述
Alzheimers Dement. 2015 Jun;11(6):e1-120. doi: 10.1016/j.jalz.2014.11.001.
本文引用的文献
1
Modeling the effect of Alzheimer's disease on mortality.模拟阿尔茨海默病对死亡率的影响。
Int J Biostat. 2007;3(1):Article 13. doi: 10.2202/1557-4679.1083.
2
Computer-aided diagnosis of Alzheimer's disease using support vector machines and classification trees.使用支持向量机和分类树进行阿尔茨海默病的计算机辅助诊断。
Phys Med Biol. 2010 May 21;55(10):2807-17. doi: 10.1088/0031-9155/55/10/002. Epub 2010 Apr 22.
3
Forecasting the global burden of Alzheimer's disease.预测阿尔茨海默病的全球负担。
Alzheimers Dement. 2007 Jul;3(3):186-91. doi: 10.1016/j.jalz.2007.04.381.
4
SVM-based computer-aided diagnosis of the Alzheimer's disease using t-test NMSE feature selection with feature correlation weighting.基于支持向量机的阿尔茨海默病计算机辅助诊断，采用t检验归一化均方误差特征选择与特征相关加权法。
Neurosci Lett. 2009 Sep 25;461(3):293-7. doi: 10.1016/j.neulet.2009.06.052. Epub 2009 Jun 21.
5
Automatic selection of ROIs in functional imaging using Gaussian mixture models.使用高斯混合模型在功能成像中自动选择感兴趣区域
Neurosci Lett. 2009 Aug 28;460(2):108-11. doi: 10.1016/j.neulet.2009.05.039. Epub 2009 May 18.
6
Categorical and correlational analyses of baseline fluorodeoxyglucose positron emission tomography images from the Alzheimer's Disease Neuroimaging Initiative (ADNI).对阿尔茨海默病神经影像倡议（ADNI）的基线氟脱氧葡萄糖正电子发射断层扫描图像进行分类和相关性分析。
Neuroimage. 2009 May 1;45(4):1107-16. doi: 10.1016/j.neuroimage.2008.12.072. Epub 2009 Jan 21.
7
Multicenter standardized 18F-FDG PET diagnosis of mild cognitive impairment, Alzheimer's disease, and other dementias.多中心标准化18F-FDG PET对轻度认知障碍、阿尔茨海默病及其他痴呆症的诊断
J Nucl Med. 2008 Mar;49(3):390-8. doi: 10.2967/jnumed.107.045385. Epub 2008 Feb 20.
8
Spatial patterns of brain atrophy in MCI patients, identified via high-dimensional pattern classification, predict subsequent cognitive decline.通过高维模式分类识别出的轻度认知障碍（MCI）患者脑萎缩的空间模式，可预测其随后的认知衰退。
Neuroimage. 2008 Feb 15;39(4):1731-43. doi: 10.1016/j.neuroimage.2007.10.031. Epub 2007 Nov 1.
9
Visual assessment versus quantitative assessment of 11C-PIB PET and 18F-FDG PET for detection of Alzheimer's disease.11C-PIB PET和18F-FDG PET用于检测阿尔茨海默病的视觉评估与定量评估
J Nucl Med. 2007 Apr;48(4):547-52. doi: 10.2967/jnumed.106.037762.
10
A comparison of classification methods for differentiating fronto-temporal dementia from Alzheimer's disease using FDG-PET imaging.
Stat Med. 2004 Jan 30;23(2):315-26. doi: 10.1002/sim.1719.
Zotero 插件