Research Paper Volume 12, Issue 7 pp 6206—6224
Application of Generalized Split Linearized Bregman Iteration algorithm for Alzheimer's disease prediction
- 1 Department of Radiology, Aerospace Center Hospital, Beijing 100049, China
- 2 Deepwise AI lab, Beijing 100080, China
- 3 Beijing Huading Jialiang Technology Co, Beijing 100000, China
- 4 Department of Radiology, Xuanwu Hospital of Capital Medical University, Beijing 100053, China
- 5 Yanjing Medical College, Capital Medical University, Beijing 101300, China
received: November 5, 2019 ; accepted: February 25, 2020 ; published: April 5, 2020 ;https://doi.org/10.18632/aging.103017
How to Cite
Copyright © 2020 Zheng et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY 3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
In this paper, we applied a novel method for the detection of Alzheimer’s disease (AD) based on a structural magnetic resonance imaging (sMRI) dataset. Specifically, the method involved a new classification algorithm of machine learning, named Generalized Split Linearized Bregman Iteration (GSplit LBI). It combines logistic regression and structural sparsity regularizations. In the study, 57 AD patients and 47 normal controls (NCs) were enrolled. We first extracted the entire brain gray matter volume values of all subjects and then used GSplit LBI to build a predictive classification model with a 10-fold full cross-validation method. The model accuracy achieved 90.44%. To further verify which voxels in the dataset have greater impact on the prediction results, we ranked the weight parameters and obtained the top 6% of the model parameters. To verify the generalization of model prediction and the stability of feature selection, we performed a cross-test on the Alzheimer's Disease Neuroimaging Initiative (ADNI) and a Chinese dataset and achieved good performances on different cohorts. Conclusively, based on the sMRI dataset, our algorithm not only had good performance in a local cohort with high accuracy but also had good generalization of model prediction and stability of feature selection in different cohorts.
AD: Alzheimer disease; sMRI: structural magnetic resonance imaging; GSplit LBI: Generalized Split Linearized Bregman Iteration; NC: normal control; ADNI: Alzheimer's disease Neuroimaging Initiative; ROI: region of interest; MCI: mild cognitive impairment; SVM: support vector machine; LDA: linear discriminant analysis; LPBM: spatially augmented linear programming boosting method; MLDA: Maximum uncertainty Linear Discriminant Analysis; TV +l1: Total Variation with l1 penalty;; n2GFL: Nonnegative Generalized Fused Lasso; MMSE: mini-mental state examination; CDR: clinical dementia rating; GM: gray matter; sMCI: stable MCI; pMCI: progressive MCI; PET: positron emission tomography; CSF: cerebrospinal fluid; DARTEL: Diffeomorphic Anatomical Registration Exponentiated Lie Algebra; WM: white matter; MNI: Montreal Neurological Institute; ROC: receiver operating characteristic curve; AUC: area under the curve; M1: motor cortex area; MTG: middle temporal gyrus; ANG: angular gyrus; SMG: supramarginal gyrus; IT: inferior temporal gyrus; STG: superior temporal gyrus; PCUN: precuneus; CAL: calcarine fissure and surrounding cortex; THA: thalamus; fMRI: functional magnetic resonance imaging; rs-fMRI: resting state functional magnetic resonance imaging; SMN: sensorimotor.