Alzheimer's disease usually has an incubation period, which is a slow and irreversible process, and is common in mental disorders clinically. Because of the irreversible damage and death of brain cells, the medical community has not yet found an effective method to treat the disease, so early diagnosis and early prediction of Alzheimer's disease are critical. This article aims to study the diagnosis of Alzheimer's disease based on supporting tensor machine algorithms and 3D brain white matter images. This paper proposes a classification method based on the third-level tensor method. The method takes the gray matter gray level of the MRI image as the feature, extracts the gray level of each voxel of the gray matter, and obtains the third-level gray level tensor. Tensor-based independent component analysis is used to obtain the independent components of the third-level grayscale tensor; in order to reduce the feature dimension, the support tensor machine is used to convert the tensor feature into a vector feature, and then the recursive feature elimination method is used to obtain the effective The main characteristics. The experimental results of this paper show that compared with traditional vector space machine learning, the algorithm proposed in this paper will use the original high-order tensor image as input data, which improves the consistency of data structure information by 15%. In addition, it supports the deletion of recursive features and tensor The machine-combined feature selection algorithm effectively eliminates redundant information and selects the best subset, which improves the performance of the classifier by 23%. It can effectively identify patients with AD and MCI.

Hashash Mostafa. Alzheimer's Disease Diagnosis Based on Supporting Tensor Machine Algorithm and 3D Brain White Matter Images. International Journal of Health and Pharmaceutical Medicine (2023), Vol. 4, Issue 1: 44-57. https://doi.org/10.38007/IJHPM.2023.040105.

[1]Tylee D S, Kikinis Z, Quinn T P, et al. Machine-learning classification of 22q11.2 deletion syndrome: A diffusion tensor imaging study. Neuroimage Clinical, 2017, 15(C):832-842.

[2]Kahali S, Adhikari S K, Sing J K. Convolution of 3D Gaussian surfaces for volumetric intensity inhomogeneity estimation and correction in 3D brain MR image data. IET Computer Vision, 2018, 12(3):288-297.

[3]Agustín Riquelme, Marcela Valdés-Tovar, Ugalde O, et al. Potential Use of Exfoliated and Cultured Olfactory Neuronal Precursors for In Vivo Alzheimer's Disease Diagnosis: A Pilot Study. Cellular and Molecular Neurobiology, 2020, 40(1):87-98.

[4]Li S, Zhou Z, Yang N, et al. A Support Tensor Machine Based Algorithm for Distant Failure Prediction in Lung SBRT. International Journal of Radiation Oncology*Biology*Physics, 2017, 99(2):E686-E687.

[5]Biswas S K, Milanfar P. Linear Support Tensor Machine With LSK Channels: Pedestrian Detection in Thermal Infrared Images. IEEE Transactions on Image Processing, 2017, 26(9):4229-4242.

[6]Deng X, Jiang P, Peng X, et al. An Intelligent Outlier Detection Method With One Class Support Tucker Machine and Genetic Algorithm Toward Big Sensor Data in Internet of Things. IEEE Transactions on Industrial Electronics, 2019, 66(6):4672-4683.

[7]Gao X, Fan L, Xu H. Multiple rank multi-linear kernel support vector machine for matrix data classification. International journal of machine learning and cybernetics, 2018, 9(2):251-261.

[8]Xing Y, Wang M, Yang S, et al. Pansharpening With Multiscale Geometric Support Tensor Machine. IEEE Transactions on Geoence and Remote Sensing, 2018, 56(5):2503-2517.

[9]Zhou B, Song B, Hassan M M, et al. Multilinear rank support tensor machine for crowd density estimation. Engineering Applications of Artificial Intelligence, 2018, 72(JUN.):382-392.

[10]Xu P, Yang N, Li S. Diagnosis of Alzheimer's disease based on Support Tensor Machine and 3D brain white matter image. Zhongshan Daxue Xuebao/Acta entiarum Natralium Universitatis Sunyatseni, 2018, 57(2):52-60.

[11]Wang H R, Mu W S, Zhou Z J. A nonlinear ν-twin support tensor machine. Journal of Information Hiding and Multimedia Signal Processing, 2019, 10(1):167-177.

[12]Rodriguez Aldana Y, Hunyadi B, Maranon Reyes E J, et al. Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis. IEEE Journal of Biomedical and Health Informatics, 2019, 23(2):660-671.

[13]Alamdari M M, Khoa N L D, Wang Y, et al. A multi-way data analysis approach for structural health monitoring of a cable-stayed bridge. Structural Health Monitoring, 2019, 18(1):35-48.

[14]Xu P, Yang N, Li S. Diagnosis of Alzheimer's disease based on Support Tensor Machine and 3D brain white matter image. Zhongshan Daxue Xuebao/Acta entiarum Natralium Universitatis Sunyatseni, 2018, 57(2):52-60.

[15]Yokota Y, Fushimi Y, Okada T, et al. Evaluation of image quality of pituitary dynamic contrast-enhanced MRI using time-resolved angiography with interleaved stochastic trajectories (TWIST) and iterative reconstruction TWIST (IT-TWIST). Journal of Magnetic Resonance Imaging, 2020, 51(5):1497-1506.

[16]Kumar P S J, Yung Y, Huan T L. Neural Network Based Decision Trees using Machine Learning for Alzheimer's Diagnosis. International Journal of Computer & Information Sciences, 2017, 4(11):63-72.

[17]Fang X, Liu Z, Xu M. Ensemble of deep convolutional neural networks based multi-modality images for Alzheimer's disease diagnosis. IET Image Processing, 2020, 14(2):318-326.

[18]Karami V, Nittari G, Amenta F. Neuroimaging computer-aided diagnosis systems for Alzheimer's disease. International Journal of Imaging Systems & Technology, 2019, 29(1):83-94.

[19]Sun L, Fan Z, Yue T, et al. Additive nanomanufacturing of lab-on-a-chip fluorescent peptide nanoparticle arrays for Alzheimer's disease diagnosis. Bio Design & Manufacturing, 2018, 1(3):182-194.

[20]Bjerke M, Engelborghs S, Perry G, et al. Cerebrospinal Fluid Biomarkers for Early and Differential Alzheimer's Disease Diagnosis. Journal of Alzheimers Disease, 2018, 62(3):1199-1209.

[21]Fasano F, Mitolo M, Gardini S, et al. Combining Structural Magnetic Resonance Imaging and Visuospatial Tests to Classify Mild Cognitive Impairment. Current Alzheimer Research, 2018, 15(3):237-246.

[22]Kalron A, Menascu S, Givon U, et al. Is the walk ratio a window to the cerebellum in multiple sclerosis? A structural magnetic resonance imaging study. European Journal of Neurology, 2020, 27(3):454-460.

[23]Yu Q, Huang K, Zhu Y, et al. Preliminary results of computer-aided diagnosis for magnetic resonance imaging of solid breast lesions. Breast Cancer Research and Treatment, 2019, 177(2):419-426.

[24]Misawa M, Kudo S E, Mori Y, et al. Accuracy of computer-aided diagnosis based on narrow-band imaging endocytoscopy for diagnosing colorectal lesions: comparison with experts. International Journal of Computer Assisted Radiology and Surgery, 2017, 12(5):1-10.

[25]Karami V, Nittari G, Amenta F. Neuroimaging computer-aided diagnosis systems for Alzheimer's disease. International Journal of Imaging Systems & Technology, 2019, 29(1):83-94.

[26]Gao Y, Geras K J, Lewin A A, et al. New Frontiers: An Update on Computer-Aided Diagnosis for Breast Imaging in the Age of Artificial Intelligence. American Journal of Roentgenology, 2019, 212(2):300-307.