Abstract
Discrepancies between the estimated brain age from brain structural MRI and the chronological age have been associated with a broad spectrum of neurocognitive disorders. The performance of brain age estimation heavily depends on predefined or hand-crafted features. Although 3D convolutional neural network (CNN) based approaches have been proposed, they require high computational cost, large memory load, and numerous images. Coupling a pre-trained 2D CNN for transfer learning with a well-established relevance vector machine for regression approach can greatly enhance the capabilities of the model. Several important strategies, including feature transfer learning, 3D feature concatenation, and dimensionality reduction were taken. The estimated brain age was modeled by structural magnetic resonance imaging (sMRI) from 594 normal healthy older individuals (age 50–90 years). We proposed and manifested a pre-trained AlexNet as a robust feature extractor. Also, the considerable cost of developing a 3D CNN was avoided by applying 3D feature concatenation and data reduction. The proposed method achieves superior performance with a mean absolute error of 4.51 years for old subjects. The predicted brain age also demonstrated high test-retest reliability (intra-class correlation coefficient of 0.979). The effectiveness and robustness of the proposed model were well studied. The proposed approach can compete with or even outperform those state-of-the-art approaches, and feature transfer learning strategy can introduce new perspectives to some well-established brain age prediction models with predefined or hand-crafted features.
Similar content being viewed by others
References
Ashburner J (2007) A fast diffeomorphic image registration algorithm. NeuroImage 38(1):95–113. https://doi.org/10.1016/j.neuroimage.2007.07.007
Ball G, Adamson C, Beare R, Marc SL (2017) Modelling neuroanatomical variation during childhood and adolescence with neighbourhood-preserving embedding. Sci Rep 7(1):17796. https://doi.org/10.1038/s41598-017-18253-6
Cole JH, Franke K (2017) Predicting Age Using Neuroimaging: Innovative Brain Ageing Biomarkers. Trends Neurosci 40(12):681–690. https://doi.org/10.1016/j.tins.2017.10.001
Cole JH, Leech R, Sharp DJ (2015) Prediction of brain age suggests accelerated atrophy after traumatic brain injury. Ann Neurol 77(4):571–581. https://doi.org/10.1002/ana.24367
Cole JH, Annus T, Wilson LR, Remtulla R, Hong YT, Fryer TD, Acosta-Cabronero J, Cardenas-Blanco A, Smith R, Menon DK, Zaman SH, Nestor PJ, Holland AJ (2017) Brain-predicted age in down syndrome is associated with b-amyloid deposition and cognitive decline. Neurobiol Aging 56:41–49. https://doi.org/10.1016/j.neurobiolaging.2017.04.006
Cole JH, Poudel RPK, Tsagkrasoulis D, Caan MWA, Steves C, Spector TD, Montana G (2017) Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker. NeuroImage 163:115–124. https://doi.org/10.1016/j.neuroimage.2017.07.059
Cole JH, Ritchie SJ, Bastin ME, Valdés Hernández MC, Muñoz Maniega S, Royle N, Corley J, Pattie A, Harris SE, Zhang Q, Wray NR, Redmond P, Marioni RE, Starr JM, Cox SR, Wardlaw JM, Sharp DJ, Deary IJ (2017) Brain age predicts mortality. Mol Psychiatry 23(5):1385–1392. https://doi.org/10.1038/mp.2017.62
Cole JH, Underwood J, Caan MW, Francesco DD, Van Zoest RA, Leech R, Wit FW, Portegies P, Geurtsen GJ, Schmand BA, Van Der Loeff MFS, Franceschi C, Sabin CA, Majoie CB, Winston A, Reiss P, Sharp DJ (2017) Increased brain-predicted aging in treated HIV disease. Neurology 88(14):1349–1357. https://doi.org/10.1212/WNL.0000000000003790
Franke K, Ziegler G, Klöppel S, Gaser C (2010) Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: exploring the influence of various parameters. NeuroImage 50(3):883–892. https://doi.org/10.1016/j.neuroimage.2010.01.005
Franke K, Luders E, May A, Gaser C (2012) Brain maturation: Predicting individual BrainAGE in children and adolescents using structural MRI. NeuroImage 63(3):1305–1312. https://doi.org/10.1016/j.neuroimage.2012.08.001
Franke K, Gaser C, Manor B, Novak V (2013) Advanced BrainAGE in older adults with type 2 diabetes mellitus. Front Aging Neurosci 5:90. https://doi.org/10.3389/fnagi.2013.00090
Franke K, Hagemann G, Schleussner E, Gaser C (2015) Changes of individual BrainAGE during the course of the menstrual cycle. NeuroImage 115:1–6. https://doi.org/10.1016/j.neuroimage.2015.04.036
Grajauskas LA, Siu W, Medvedev G, Guo H, D’Arcy RCN, Song X (2019) MRI-based evaluation of structural degeneration in the ageing brain: Pathophysiology and assessment. Ageing Res Rev 49:67–82. https://doi.org/10.1016/j.arr.2018.11.004
Harada CN, Love MCN, Triebel K (2013) Normal Cognitive Aging. Clin Geriatr Med 29(4):737–752. https://doi.org/10.1016/j.cger.2013.07.002
Holzinger A, Langs G, Denk H, Zatloukal K, Mueller H (2019) Causability and explainability of artificial intelligence in medicine. Wiley Interdiscip Rev Data Min Knowl Discov 9(4):e1312. https://doi.org/10.1002/widm.1312
Hotelling H (1933) Analysis of a complex of statistical variables into principal components. J Educ Psychol 24(6):417–441. https://doi.org/10.1037/h0071325
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp 675–678. https://doi.org/10.1145/2647868.2654889
Khundrakpam BS, Tohka J, Evans AC (2015) Prediction of brain maturity based on cortical thickness at different spatial resolutions. NeuroImage 111:350–359. https://doi.org/10.1016/j.neuroimage.2015.02.046
Kolenic M, Franke K, Hlinka J, Matejka M, Capkova J, Pausova Z, Uher R, Alda M, Spaniel F, Hajek T (2018) Obesity, dyslipidemia and brain age in first-episode psychosis. J Psychiatr res 99:151–158. https://doi.org/10.1016/j.jpsychires.2018.02.012
Koutsouleris N, Davatzikos C, Borgwardt S, Gaser C, Bottlender R, Frodl T, Falkai P, Riecher-Rössler A, Möller HJ, Pantelis MRC, Meisenzahl E (2013) Accelerated brain aging in schizophrenia and beyond: a neuroanatomical marker of psychiatric disorders. Schizophr Bull 40(5):1140–1153. https://doi.org/10.1093/schbul/sbt142
Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60(6):84–90. https://doi.org/10.1145/3065386
Lancaster J, Lorenz R, Leech R, Cole JH (2018) Bayesian optimization for neuroimaging pre-processing in brain age classification and prediction. Front Aging Neurosci 10:28. https://doi.org/10.3389/fnagi.2018.00028
Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, Van Der Laak JA, Van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88. https://doi.org/10.1016/j.media.2017.07.005
Miller KL, Alfaro-Almagro F, Bangerter NK, Thomas DL, Yacoub E, Xu J, Bartsch AJ, Jbabdi S, Sotiropoulos SN, Andersson JLR, Griffanti L, Douaud G, Okell TW, Weale P, Dragonu I, Garratt S, Hudson S, Collins R, Jenkinson M, Matthews PM, Smith SM (2016) Multimodal population brain imaging in the UK Biobank prospective epidemiological study. Nat Neurosci 19(11):1523–1536. https://doi.org/10.1038/nn.4393
Nenadic I, Dietzek M, Langbein K, Sauer H, Gaser C (2017) BrainAGE score indicates accelerated brain aging in schizophrenia, but not bipolar disorder. Psychiat Res-Neuroim 266:86–89. https://doi.org/10.1016/j.pscychresns.2017.05.006
O’sullivan S, Heinsen H, Grinberg LT, Chimelli L Jr, Do Nascimento Saldiva EA, Jeanquartier PH, Jean-Quartier F, Da Graca Morais Martin C, Sajid M, Holzinger MI A (2019) The role of artificial intelligence and machine learning in harmonization of high-resolution post-mortem MRI (virtopsy) with respect to brain microstructure. Brain Informatics 6(1):1–12. https://doi.org/10.1186/s40708-019-0096-3
Pardoe HR, Kuzniecky R (2017) NAPR: a cloud-based framework for neuroanatomical age prediction. Neuroinformatics 16(1):43–49. https://doi.org/10.1007/s12021-017-9346-9
Pardoe HR, Cole JH, Blackmon K, Thesen T, Kuzniecky R (2017) Structural brain changes in medically refractory focal epilepsy resemble premature brain aging. Epilepsy Res 133:28–32. https://doi.org/10.1016/j.eplepsyres.2017.03.007
Razavian AS, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp 806–813. https://doi.org/10.1109/CVPRW.2014.131
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252. https://doi.org/10.1007/s11263-015-0816-y
Salthouse TA (2019) Trajectories of normal cognitive aging. Psychol Aging 34(1):17–24. https://doi.org/10.1037/pag0000288
Schnack HG, Van Haren NEM, Nieuwenhuis M, Pol HEH, Cahn W, Kahn RS (2016) Accelerated brain aging in schizophrenia: a longitudinal pattern recognition study. Am J Psychiat 173(6):607–616. https://doi.org/10.1176/appi.ajp.2015.15070922
Tipping ME (2000) The relevance vector machine. Adv Neural Inf Process Syst 1(12):652–658
Wang B, Pham TD (2011) MRI-based age prediction using hidden Markov models. J Neurosci Methods 199(1):140–145. https://doi.org/10.1016/j.jneumeth.2011.04.022
Wang J, Dai D, Li M, Hua J, He H (2012) Human Age Estimation with Surface-Based Features from MRI Images. International Workshop on Machine Learning in Medical Imaging, pp 111–118. https://doi.org/10.1007/978-3-642-35428-1_14
Zhao Y, Klein A, Castellanos FX, Milham MP (2019) Brain age prediction: Cortical and subcortical shape covariation in the developing human brain. NeuroImage 202:116149. https://doi.org/10.1016/j.neuroimage.2019.116149
Acknowledgements
This research was financially supported by grants from National Natural Science Foundation of China (81971683),Natural Science Foundation of Beijing Municipality (L182010) and the Scientific Research General Project of Beijing Municipal Education Committee (KM201810005033).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
None declared.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lin, L., Zhang, G., Wang, J. et al. Utilizing transfer learning of pre-trained AlexNet and relevance vector machine for regression for predicting healthy older adult’s brain age from structural MRI. Multimed Tools Appl 80, 24719–24735 (2021). https://doi.org/10.1007/s11042-020-10377-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10377-8