Brain age prediction from MRI images based on a convolutional neural network with MRMR feature selection layer
DOI:
https://doi.org/10.31185/wjcms.296Keywords:
brain age,, MRI images, MRMR algorithm, convolutional neural network.Abstract
An sophisticated medical technique used to diagnose illnesses and brain disorders including multiple sclerosis, Alzheimer's, and other neurological ailments is the ability to predict the biological age of the brain using MRI pictures. To do this, sophisticated algorithms and neural networks are used to scan MRI brain pictures in order to extract different brain properties, including cortical thickness and volume. The brain ages of individuals are determined by matching their characteristics against MRI imaging data collected from other patients. The research employs a new deep learning model named CNN-MRMR which combines features from the Minimum Redundancy Maximum Relevance (MRMR) feature selection approach and Convolutional Neural Network (CNN) technology. MRI images of human brains are initially processed by the convolutional network to extract age-related characteristics. The feature selection layer uses MRMR algorithm which identifies essential characteristics for a target variable while minimizing feature redundancy to select the optimal feature subset. The system employs a regression layer as the final stage to predict brain age by utilizing the selected characteristics. The proposed method for estimating individual brain age attained a prediction accuracy of 90.3%, outperforming results from comparable research studies.
Downloads
References
[1] J. Steffener, C. Habeck, D. O'Shea, Q. Razlighi, L. Bherer, and Y. Stern, "Differences between chronological and brain age are related to education and self-reported physical activity," Neurobiol. Aging, vol. 40, pp. 138–144, Apr. 2016. DOI: https://doi.org/10.1016/j.neurobiolaging.2016.01.014
[2] T. A. Salthouse, "Mental exercise and mental aging: Evaluating the validity of the “use it or lose it” hypothesis," Perspect. Psychol. Sci., vol. 1, no. 1, pp. 68–87, Mar. 2006. DOI: https://doi.org/10.1111/j.1745-6916.2006.00005.x
[3] K. Franke and C. Gaser, "Ten years of BrainAGE as a neuroimaging biomarker of brain aging: what insights have we gained?," Front. Neurol., vol. 10, p. 789, Aug. 2019. DOI: https://doi.org/10.3389/fneur.2019.00789
[4] H. Sajedi and N. Pardakhti, "Age prediction based on brain MRI image: a survey," J. Med. Syst., vol. 43, no. 8, p. 279, Aug. 2019. DOI: https://doi.org/10.1007/s10916-019-1401-7
[5] Y. Wu et al., "Machine Learning and Deep Learning Approaches in Lifespan Brain Age Prediction: A Comprehensive Review," Tomography, vol. 10, no. 8, pp. 1238–1262, Aug. 2024.
[6] Y. Wu et al., "Machine Learning and Deep Learning Approaches in Lifespan Brain Age Prediction: A Comprehensive Review," Tomography, vol. 10, no. 8, pp. 1238–1262, Aug. 2024. DOI: https://doi.org/10.3390/tomography10080093
[7] M. Tanveer et al., "Deep learning for brain age estimation: A systematic review," Inf. Fusion, vol. 96, pp. 130–143, Aug. 2023. DOI: https://doi.org/10.1016/j.inffus.2023.03.007
[8] F. Liem et al., "Predicting brain-age from multimodal imaging data captures cognitive impairment," Neuroimage, vol. 148, pp. 179–188, Mar. 2017. DOI: https://doi.org/10.1016/j.neuroimage.2016.11.005
[9] J. Lee et al., "Deep learning-based brain age prediction in normal aging and dementia," Nat. Aging, vol. 2, no. 5, pp. 412–424, May 2022. DOI: https://doi.org/10.1038/s43587-022-00219-7
[10] C. Yin et al., "Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment," Proc. Natl. Acad. Sci. U.S.A., vol. 120, no. 2, p. e2214634120, Mar. 2023.
[11] D. A. Wood et al., "Accurate brain‐age models for routine clinical MRI examinations," Neuroimage, vol. 249, p. 118871, Apr. 2022. DOI: https://doi.org/10.1016/j.neuroimage.2022.118871
[12] A. M. de Lange et al., "Mind the gap: Performance metric evaluation in brain‐age prediction," Hum. Brain Mapp., vol. 43, no. 10, pp. 3113–3129, Jul. 2022. DOI: https://doi.org/10.1002/hbm.25837
[13] K. M. Poloni, R. J. Ferrari, and Alzheimer’s Disease Neuroimaging Initiative, "A deep ensemble hippocampal CNN model for brain age estimation applied to Alzheimer’s diagnosis," Expert Syst. Appl., vol. 195, p. 116622, Jun. 2022.
[14] P. R. Millar et al., "Predicting brain age from functional connectivity in symptomatic and preclinical Alzheimer disease," Neuroimage, vol. 256, p. 119228, Aug. 2022.
[15] J. Gao et al., "Brain age prediction using the graph neural network based on resting-state functional MRI in Alzheimer's disease," Front. Neurosci., vol. 17, p. 1222751, Jun. 2023. DOI: https://doi.org/10.3389/fnins.2023.1222751
[16] I. Cumplido-Mayoral et al., "Biological brain age prediction using machine learning on structural neuroimaging data: Multi-cohort validation against biomarkers of Alzheimer’s Disease and neurodegeneration stratified by sex," Elife, vol. 12, p. e81067, Apr. 2023.
[17] K. Jusseaume and I. Valova, "Brain age prediction/classification through recurrent deep learning with electroencephalogram recordings of seizure subjects," Sensors, vol. 22, no. 21, p. 8112, Oct. 2022. DOI: https://doi.org/10.3390/s22218112
[18] D. Beck et al., "Cardiometabolic risk factors associated with brain age and accelerated brain ageing," Hum. Brain Mapp., vol. 43, no. 2, pp. 700–720, Feb. 2022. DOI: https://doi.org/10.1002/hbm.25680
[19] Y. Li et al., "Brain connectivity based graph convolutional networks and its application to infant age prediction," IEEE Trans. Med. Imaging, vol. 41, no. 10, pp. 2764–2776, May 2022. DOI: https://doi.org/10.1109/TMI.2022.3171778
[20] Y. Nygate et al., "543 EEG-based deep neural network model for brain age prediction and its association with patient health conditions," Sleep, vol. 44, suppl. 2, pp. A214–A214, May 2021. DOI: https://doi.org/10.1093/sleep/zsab072.541
[21] L. Alzubaidi et al., "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions," J. Big Data, vol. 8, no. 1, pp. 1–74, Dec. 2021. DOI: https://doi.org/10.1186/s40537-021-00444-8
[22] J. Parchami and G. Sarbishaei, "A novel scheme based on information theory and transfer learning for multi classes motor imagery decoding," IET Signal Process., vol. 17, no. 5, p. e12222, May 2023. DOI: https://doi.org/10.1049/sil2.12222
[23] "ABIDE Dataset," [Online]. Available: https://fcon_1000.projects.nitrc.org/indi/abide/
[24] L. Bellantuono et al., "Predicting brain age with complex networks: From adolescence to adulthood," Neuroimage, vol. 225, p. 117458, Jan. 2021. DOI: https://doi.org/10.1016/j.neuroimage.2020.117458
[25] H. Peng, W. Gong, C. F. Beckmann, A. Vedaldi, and S. M. Smith, "Accurate brain age prediction with lightweight deep neural networks," Med. Image Anal., vol. 68, p. 101871, Feb. 2021. DOI: https://doi.org/10.1016/j.media.2020.101871
[26] B. A. Jonsson et al., "Deep learning based brain age prediction uncovers associated sequence variants," bioRxiv, Apr. 4, 2019. [Online]. Available: https://doi.org/10.1101/595801 DOI: https://doi.org/10.1038/s41467-019-13163-9
[27] K. M. Poloni, R. J. Ferrari, and Alzheimer’s Disease Neuroimaging Initiative, "A deep ensemble hippocampal CNN model for brain age estimation applied to Alzheimer’s diagnosis," Expert Syst. Appl., vol. 195, p. 116622, Jun. 2022. DOI: https://doi.org/10.1016/j.eswa.2022.116622
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mustafa Hatem Al Ghariri, Seyed Omid Shahdi

This work is licensed under a Creative Commons Attribution 4.0 International License.