Age Estimation from Brain Magnetic Resonance Images Using Deep Learning Techniques in Extensive Age Range

Estimation of human age is important in the fields forensic medicine and detection neurodegenerative diseases brain. Particularly, estimation methods using brain magnetic resonance (MR) images are greatly significant because these not only noninvasive but also do lead to radiation exposure. Although several MR have already been investigated deep learning, there no reports involving younger subjects such as children. This study method T1-weighted (sagittal plane) two-dimensional imaging (MRI) 1000 aged 5–79 (31.64 ± 18.04) years. uses a regression model based on ResNet-50, which estimates chronological (CA) unknown by training corresponding CA. The correlation coefficient, coefficient determination, mean absolute error, root squared error were used evaluation indices this model, results 0.9643, 0.9299, 5.251, 6.422, respectively. present showed same degree those related studies, demonstrating that can be performed for wide range ages with higher accuracy.