用于轻度认知障碍识别的多任务融合稀疏学习
Multi-task fused sparse learning for mild cognitive impairment identification.
作者信息
Yang Peng, Ni Dong, Chen Siping, Wang Tianfu, Wu Donghui, Lei Baiying
机构信息
School of Biomedical Engineering, Shenzhen University, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, Shenzhen, Guangdong, China.
Department of Geriatric Psychiatry, Shenzhen Kangning Hospital, and Shenzhen Mental Health Center, Shenzhen, Guangdong, China.
出版信息
Technol Health Care. 2018;26(S1):437-448. doi: 10.3233/THC-174587.
BACKGROUND
Brain functional connectivity network (BFCN) has been widely applied to identify biomarkers for the brain function understanding and brain diseases analysis.
OBJECTIVE
Building a biologically meaningful brain network is a crucial work in these applications. For this task, sparse learning has been widely applied for the network construction. If multiple time-point data is added to the brain imaging application, the disease progression pattern in the longitudinal analysis can be better revealed.
METHODS
A novel longitudinal analysis for MCI classification is devised based on resting-state functional magnetic resonating imaging (rs-fMRI). Specifically, this paper proposes a novel multi-task learning method to integrate fused penalty by regularization. In addition, a novel objective function is developed for fused sparse learning via smoothness constraint.
RESULTS
The proposed method achieves the best classification performance with an accuracy of 95.74% for baseline and 93.64% for year 1 data.
CONCLUSIONS
The experimental results show that our proposed method achieves quite promising classification performance.
背景
脑功能连接网络（BFCN）已被广泛应用于识别生物标志物，以帮助理解脑功能和分析脑部疾病。
目的
构建具有生物学意义的脑网络是这些应用中的一项关键工作。对于此任务，稀疏学习已被广泛应用于网络构建。如果将多个时间点的数据添加到脑成像应用中，则可以更好地揭示纵向分析中的疾病进展模式。
方法
基于静息态功能磁共振成像（rs-fMRI）设计了一种用于MCI分类的新型纵向分析方法。具体而言，本文提出了一种新型的多任务学习方法，通过正则化来整合融合惩罚。此外，还通过平滑约束开发了一种用于融合稀疏学习的新型目标函数。
结果
所提出的方法实现了最佳分类性能，基线准确率为95.74%，第1年数据准确率为93.64%。
结论
实验结果表明，我们提出的方法实现了非常有前景的分类性能。
Zotero 插件