An Age Estimation Method Using 3D-CNN From Brain MRI Images

A specific pattern of morphological changes in the human brain is observed during the process of brain development and healthy aging. The age of subjects can be estimated from brain images by evaluating such patterns. This paper proposes an age estimation method using 3-Dimensional Convolutional Neural Network (3D-CNN) from brain T1-weighted images so as to fully utilize the potential of volume data. Through a set of experiments using over 1,000 T1-weighted images of healthy Japanese, we demonstrate that the proposed method exhibits better performance on age estimation than the conventional methods using handcrafted local features and 2D-CNN.

[1]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[2]  Hiroshi Fukuda,et al.  Voxel-based morphometry of human brain with age and cerebrovascular risk factors , 2004, Neurobiology of Aging.

[3]  Stefan Klöppel,et al.  Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters , 2010, NeuroImage.

[4]  Kazunori Sato,et al.  Age estimation using effective brain local features from T1-weighted images , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[5]  John S. Allen,et al.  Normal neuroanatomical variation due to age: The major lobes and a parcellation of the temporal region , 2005, Neurobiology of Aging.

[6]  Nadim Joni Shah,et al.  Fully-automated detection of cerebral water content changes: Study of age- and gender-related H2O patterns with quantitative MRI , 2006, NeuroImage.

[7]  Kazunori Sato,et al.  Neuroanatomical database of normal Japanese brains , 2003, Neural Networks.

[8]  Benjamin Thyreau,et al.  Correlations among Brain Gray Matter Volumes, Age, Gender, and Hemisphere in Healthy Individuals , 2011, PloS one.

[9]  Jing Hua,et al.  Age estimation using cortical surface pattern combining thickness with curvatures , 2013, Medical & Biological Engineering & Computing.

[10]  Kazunori Sato,et al.  An age estimation method using brain local features for T1-weighted images , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[11]  Dinggang Shen,et al.  Morphological classification of brains via high-dimensional shape transformations and machine learning methods , 2004, NeuroImage.

[12]  N. Tzourio-Mazoyer,et al.  Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain , 2002, NeuroImage.

[13]  C. Fennema-Notestine,et al.  Effects of age on tissues and regions of the cerebrum and cerebellum , 2001, Neurobiology of Aging.

[14]  Kazunori Sato,et al.  Age estimation from brain MRI images using deep learning , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[15]  Karl J. Friston,et al.  A Voxel-Based Morphometric Study of Ageing in 465 Normal Adult Human Brains , 2001, NeuroImage.

[16]  Kazunori Sato,et al.  Brain age estimation from T1-weighted images using effective local features , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[17]  Geraldo F. Busatto,et al.  Age-related gray matter volume changes in the brain during non-elderly adulthood , 2011, Neurobiology of Aging.

[18]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Edward T. Bullmore,et al.  Whole-brain anatomical networks: Does the choice of nodes matter? , 2010, NeuroImage.