Brain age is an effective biomarker for diagnosing Alzheimer’s disease (AD). Aimed at the issue that
the existing brain age detection methods are inconsistent with the biological hypothesis that AD is the accelerated
aging of the brain, a mutual information - support vector regression (MI-SVR) brain age prediction model is
proposed. First, the age deviation is introduced according to the biological hypothesis of AD. Second, fitness
function is designed based on mutual information criterion. Third, support vector regression and fitness function
are used to obtain the predicted brain age and fitness value of the subjects, respectively. The optimal age deviation
is obtained by maximizing the fitness value. Finally, the proposed method is compared with some existing brain
age detection methods. Experimental results show that the brain age obtained by the proposed method has better
separability, can better reflect the accelerated aging of AD, and is more helpful for improving the diagnostic
accuracy of AD.
刘玉川1，李浩1，唐宇龙1，梁杜娟2，谭佳3，符玥1，李勇明4
. Brain Age Detection of Alzheimer’s Disease Magnetic Resonance
Images Based on Mutual Information - Support Vector Regression[J]. Journal of Shanghai Jiaotong University(Science), 2025
, 30(1)
: 130
-135
.
DOI: 10.1007/s12204-023-2590-2
[1] ZENG A, JIA L, PAN D, et al. Early prognosis of Alzheimer’s disease based on convolutional neural networks and ensemble learning [J]. Journal of Biomedical Engineering, 2019, 36(5): 711-719 (in Chinese).
[2] GUAN H, TAO C, TAO D. MRI-based Alzheimer’s disease prediction via distilling the knowledge in multimodal data [J]. NeuroImage, 2021, 244: 118586.
[3] TURKSON R E, QU H, MAWULI C B, et al. Classifi- cation of Alzheimer’s disease using deep convolutional spiking neural network [J]. Neural Processing Letters, 2021, 53(4): 2649-2663.
[4] WU H, LUO J, LU X, et al. 3D transfer learning network for classification of Alzheimer’s disease with MRI [J]. International Journal of Machine Learning and Cybernetics, 2022, 13(7): 1997-2011.
[5] ZHANG Y, TENG Q, LIU Y, et al. Diagnosis of Alzheimer’s disease based on regional attention with sMRI gray matter slices [J]. Journal of Neuroscience Methods, 2022, 365: 109376.
[6] RAMZAN F, KHAN M U G, REHMAT A, et al. A deep learning approach for automated diagnosis and multi-class classification of Alzheimer’s disease stages using resting-state fMRI and residual neural networks [J]. Journal of Medical Systems, 2019, 44(2): 37.
[7] LI Y, LI F, ZHU X, et al. Detection of brain age of Alzheimer’s disease based on separability distance criterion and MR image [J]. Journal of Southeast University (Natural Science Edition), 2016, 46(6): 1137-1142 (in Chinese).
[8] IRIMIA A, TORGERSON C M, GOH S, et al. Statistical estimation of physiological brain age as a descriptor of senescence rate during adulthood [J]. Brain Imaging and Behavior, 2015, 9(4): 678-689.
[9] SENDI M S E, SALAT D H, CALHOUN V D. Brain age gap difference between healthy and mild dementia subjects: Functional network connectivity analysis [C]//2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Online: IEEE, 2021: 1636-1639.
[10] BEHESHTI I, MISHRA S, SONE D, et al. T1-weighted MRI-driven brain age estimation in Alzheimer’s disease and Parkinson’s disease [J]. Aging and Disease, 2020, 11(3): 618-628.
[11] POLONI K M, FERRARI R J. A deep ensemble hippocampal CNN model for brain age estimation applied to Alzheimer’s diagnosis [J]. Expert Systems With Applications, 2022, 195: 116622.
[12] PALMA M, TAVAKOLI S, BRETTSCHNEIDER J, et al. Quantifying uncertainty in brain-predicted age using scalar-on-image quantile regression [J]. NeuroImage, 2020, 219: 116938.
[13] LY M, YU G Z, KARIM H T, et al. Improving brain age prediction models: Incorporation of amyloid status in Alzheimer’s disease [J]. Neurobiology of Aging, 2020, 87: 44-48.
[14] LOWE L C, GASER C, FRANKE K, et al. The effect of the APOE genotype on individual BrainAGE in normal aging, mild cognitive impairment, and Alzheimer’s disease [J]. PLoS ONE, 2016, 11(7): e0157514.
[15] NAKANO R, KOBASHI S, BINTE ALAM S, et al. Neonatal brain age estimation using manifold learning regression analysis [C]//2015 IEEE International Conference on Systems, Man, and Cybernetics. Hong Kong: IEEE, 2015: 2273-2276.
[16] DAVATZIKOS C, XU F, AN Y, et al. Longitudinal progression of Alzheimer’s-like patterns of atrophy in normal older adults: The SPARE-AD index [J]. Brain, 2009, 132(8): 2026-2035.
[17] GONNEAUD J, BARIA A T, PICHET BINETTE A, et al. Accelerated functional brain aging in pre-clinical familial Alzheimer’s disease [J]. Nature Communications, 2021, 12: 5346.
[18] LI Y, LI F, WANG P, et al. Estimating the brain pathological age of Alzheimer’s disease patients from MR image data based on the separability distance criterion [J]. Physics in Medicine and Biology, 2016, 61(19): 7162-7186.
[19] GANAIE M A, TANVEER M, BEHESHTI I. Brain age prediction using improved twin SVR [J]. Neural Computing and Applications, 2022. https://doi.org/10.1007/s00521-021-06518-1.
[20] SMOLA A J, SCHOLKOPF B. A tutorial on support vector regression [J]. Statistics and Computing, 2004,14(3): 199-222.
[21] YANG J, WANG S, WU T. Maximum mutual information for feature extraction from graphstructured data: Application to Alzheimer’s disease classification [J]. Applied Intelligence, 2022. https://doi.org/10.1007/s10489-022-03528-x.
[22] PANINSKI L. Estimation of entropy and mutual information [J]. Neural Computation, 2003, 15(6): 1191-1253.
[23] FRANKE K, ZIEGLER G, KLOPPEL S, et al. Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters [J]. NeuroImage, 2010,50(3): 883-892.
