深度学习在轻度认知障碍转化与分类中的应用分析  

Application of deep learning to mild cognitive impairment conversion and classification

作　　者：张柏雯 林岚[1] 吴水才[1] 

机构地区：[1]北京工业大学生命科学与生物工程学院,北京100124

出　　处：《医疗卫生装备》2017年第9期105-111,共7页Chinese Medical Equipment Journal

基　　金：国家科技支撑计划课题(2015BAI02B03);国家自然科学基金(71661167001)

摘　　要：介绍了预测轻度认知障碍(mild cognitive impairment,MCI)患者罹患阿尔茨海默症(Alzheimer's disease,AD)的风险对于延缓AD发病的重要意义,简述了广泛用于AD相关疾病研究的ADNI(Alzheimer's disease neuroimaging initiative)数据库,回顾了传统机器学习算法在MCI分类中的运用。用深度学习算法可通过组合低层特征形成更加抽象的高层特征,为解决MCI的转化预测与分类识别提供了新的思路。从有监督和无监督2个方面重点阐述了目前深度学习的方法运用于以结构性磁共振成像(structural magnetic resonance imaging,s MRI)为主的神经影像数据在MCI的分类与转换预测的研究现状,最后分析与讨论了深度学习算法在该领域应用存在的问题,并对其前景进行了展望。Mild cognitive impairment（MCI） is a prodromal stage of dementia. Predicting MCI＇s conversion to Alzheimer＇s disease（AD） plays critical roles in preventing the progression of AD. Alzheimer＇s disease neuroimaging initiative（ADNI） was introduced briefly, which was a widely used neuroimaging database for the study on AD related diseases, and the application of machine learning algorithm was reviewed in MCI classification. Deep learning network, which transforms the original data into a higher level and more abstract expression, has shown great promise in MCI conversion and classification. Two main kinds of deep learning approaches were described, including supervised learning and unsupervised learning, and their new application was discussed in MCI conversion and classification based on structural magnetic resonance imaging（s MRI）.Finally, the current limitations and future trends of deep learning in this area were explored.

关 键 词：深度学习 轻度认知障碍 阿尔茨海默病 结构性磁共振成像 ADNI数据库 

分 类 号：R749.16[医药卫生—神经病学与精神病学] TP181[医药卫生—临床医学]