Predicting clinical scores for Alzheimer's disease based on joint and deep learning

被引：49

作者：

Lei, Baiying ^{[1
]}

Liang, Enmin ^{[1
]}

Yang, Mengya ^{[1
]}

Yang, Peng ^{[1
]}

Zhou, Feng ^{[2
]}

Tan, Ee-Leng ^{[3
]}

Lei, Yi ^{[4
]}

Liu, Chuan-Ming ^{[5
]}

Wang, Tianfu ^{[1
]}

Xiao, Xiaohua ^{[4
]}

Wang, Shuqiang ^{[6
]}

机构：

[1] Shenzhen Univ, Sch Biomed Engn, Guangdong Key Lab Biomed Measurements & Ultrasoun, Natl Reg Key Technol Engn Lab Med Ultrasound,Hlth, Shenzhen 518060, Peoples R China

[2] Univ Michigan, Dept Ind & Mfg Syst Engn, Dearborn, MI 48128 USA

[3] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore

[4] Shenzhen Univ, Affiliated Hosp 1, Hlth Sci Ctr, Shenzhen 518035, Peoples R China

[5] Natl Taipei Univ Technol, Comp Sci & Informat Engn, Taipei, Taiwan

[6] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518000, Peoples R China

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2022年 / 187卷

基金：

中国国家自然科学基金;

关键词：

Alzheimer's disease; Feature selection; Deep learning; Independently recurrent neural network; Score prediction; DIAGNOSIS; MRI; SHRINKAGE; SELECTION; ATROPHY; IMAGES; MODEL;

D O I：

10.1016/j.eswa.2021.115966

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Alzheimer's disease (AD) is a progressive neurodegenerative disease that often grows in middle-aged and elderly people with the gradual loss of cognitive ability. Presently, there is no cure for AD. Furthermore, the current clinical diagnosis of AD is too time-consuming. In this paper, we design a joint and deep learning framework to predict clinical scores of AD. Specifically, the feature selection method combining group LASSO and correntropy is used to reduce dimensions and screen the features of brain regions related to AD. We explore the multi-layer independently recurrent neural network regression to study the internal connection between different brain regions and the time correlation between longitudinal data. The proposed joint deep learning network studies the relationship between the magnetic resonance imaging and clinical score, and predicts the clinical score. The predicted clinical score values allow doctors to perform early diagnosis and timely treatment of patients' disease condition.

引用

页数：11

共 49 条

[1] Predictive Modeling of Longitudinal Data for Alzheimer's Disease Diagnosis Using RNNs [J].