Brain Age Estimation From MRI Using Cascade Networks With Ranking Loss

• Published in: IEEE transactions on medical imaging Vol. 40; no. 12; pp. 3400 - 3412
• Main Authors: Cheng, Jian, Liu, Ziyang, Guan, Hao, Wu, Zhenzhou, Zhu, Haogang, Jiang, Jiyang, Wen, Wei, Tao, Dacheng, Liu, Tao
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Age determination; Age differences; Age related diseases; Aging; Alzheimer's disease; Artificial neural networks; Biomarkers; Biomedical imaging; Brain; Brain age estimation; Brain mapping; Brain modeling; Chronology; Cognitive ability; Computer architecture; convolutional neural network; Correlation coefficient; Correlation coefficients; Dementia; dementia classification; Dementia disorders; Estimates; Estimation; Feature maps; Magnetic resonance imaging; Medical imaging; Neural networks; Neurodegenerative diseases; Neuroimaging; Ranking; ranking loss; Support vector machines; Three-dimensional displays; Training

Chronological age of healthy people is able to be predicted accurately using deep neural networks from neuroimaging data, and the predicted brain age could serve as a biomarker for detecting aging-related diseases. In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN),...