A calibrated SVM based on weighted smooth GL1/2 for Alzheimer's disease prediction. (May 2023)

• Record Type: Journal Article
• Authors: Wang, Jinfeng; Huang, Shuaihui; Wang, Zhiwen; Huang, Dong; Qin, Jing; Wang, Hui; Wang, Wenzhong; Liang, Yong
• Is Part Of: Computers in biology and medicine. Volume 158(2023)
• Publication Date: 2023-05
• Subjects: Alzheimer's disease -- Calibrated SVM -- Sparse regularization -- Weighted smooth GL1/2; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2023.106752
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Alzheimer's disease (AD) is currently one of the mainstream senile diseases in the world. It is a key problem predicting the early stage of AD. Low accuracy recognition of AD and high redundancy brain lesions are the main obstacles. Traditionally, Group Lasso method can achieve good sparseness. But, redundancy inside group is ignored. This paper proposes an improved smooth classification framework which combines the weighted smooth G L 1 / 2 ( w S G L 1 / 2 ) as feature selection method and a calibrated support vector machine (cSVM) as the classifier. w S G L 1 / 2 can make intra-group and inner-group features sparse, in which the group weights can further improve the efficiency of the model. cSVM can enhance the speed and stability of model by adding calibrated hinge function. Before feature selecting, an anatomical boundary-based clustering, called as ac-SLIC-AAL, is designed to make adjacent similar voxels into one group for accommodating the overall differences of all data. The c S V M model is fast convergence speed, high accuracy and good interpretability on AD classification, AD early diagnosis and MCI transition prediction. In experiments, all steps are tested respectively, including classifiers' comparison, feature selection verification, generalization verification and comparing with state-of-the-art methods. The results are supportive and satisfactory. The superior of the proposed model are verified globally. At the same time, the algorithm can point out the important brain areas in the MRI, which has important reference value for the doctor's predictive work. The source code and data is available at http://github.com/Hu-s-h/c-SVMForMRI . Highlights: An innovative template called as ac-SLIC-AAL is adopted for dividing more detailed brain regions, which provide a fine division of brain regions by hierarchical clustering. A weighted S G L 1 / 2 method call as w S G L 1 / 2 is proposed. A group sparsity weight for S G L 1 / 2 is designed to improve the efficiency of group sparsity. An improved classification framework is constructed, which is based on a calibrated SVM (cSVM) combined with w S G L 1 / 2, called as c S V M − w S G L 1 / 2, to improve convergence speed and extract important regions.