Alzheimer’s disease Classification Using Histogram of Oriented Gradient, Transfer Learning, and Capsules Network
Keywords:
Alzheimer’s disease, Histogram of Oriented Gradient, VGG-16, ResNet50, Capsule Network.Abstract
Alzheimer's disease (AD) is a widespread neurodegenerative condition that affects the brain and causes cognitive impairment. This disease falls within the fields of medicine and health care; recently, it has been considered one of the most studied diseases of the nervous system. AD has no cure or any way to slow or stop its progression. Machine learning (ML) techniques, specifically pattern recognition in biomedical sciences from disease diagnosis to treatment, have become one of the important ways that researchers better understand the whole situation and solve complex medical problems. Deep learning (DL) is a powerful machine-learning model for classification while extracting high-level features. The importance of classifying this type of medical data is to develop a predictive classifier system to know the type of disease from the characteristics extracted from the images or to estimate the stage of the disease. The proper choice and the best application of appropriate computer vision methods and techniques to extract important features from the medical image lead to efficient classification. This paper presents a methodology comprising three main phases. Firstly, we preprocess the data using standard computer vision techniques and graphic functions, along with the Histogram of Oriented Gradient (HOG) descriptor, to extract relevant features, accelerate model training, and prevent overfitting. Secondly, we feed these extracted features into two convolutional neural network models, VGG-16 and ResNet50, to extract deep features. We then concatenate these deep features into a single vector. Subsequently, these concatenated features are evaluated using a RandomForestRegressor to select the most relevant ones, reduce the dimensionality of our dataset, and enhance the interpretability and reliability of our model's decisions. Finally, the selected features are utilized as inputs for a CapsNet model to extract spatial features and perform classification. This comprehensive approach leverages the strengths of each technique to achieve robust and accurate classification outcomes. The proposed method provided effective results (94.27%), surpassing several recent experiments on the topic of AD in terms of accuracy, and demonstrated significant value in the early prediction of AD through the evolution of computer vision method and machine learning and its applications in the medical domain.
Downloads
References
S. Saman et T. Ghassem, «Classification of Alzheimer’s Disease Using fMRI Data and Deep Learning Convolutional Neural Networks,» n° %1https://doi.org/10.48550/arXiv.1603.08631, 2016.
S. Saman et T. Ghassem, «DeepAD: Alzheimer’s Disease Classification via Deep Convolutional Neural Networks using MRI and fMRI,» n° %1https://doi.org/10.1101/070441, 2017.
R. Farheen, G. K. Muhammad Usman, R. Asim, I. Sajid, S. Tanzila, R. Amjad et M. Zahid, «A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer’s Disease Stages Using Resting-State fMRI and Residual Neural Networks,» n° %1https://doi.org/10.1007/s10916-019-1475-2, p. 2019.
M. Tanveer, B. Richhariya, R. U. Khan, A. H. Rashid, P. Khanna, M. Prasad, C. T. LinAuthors Info et Claims, «Machine Learning Techniques for the Diagnosis of Alzheimer’s Disease: A Review,» n° %1https://doi.org/10.1145/3344998, 2020.
F. Zhao, X. Fanyu, Q. Xuedan, L. Cai et Y. Lili, «Classification of Alzheimer’s disease based on brain MRI and machine learning,» n° %1https://doi.org/10.1007/s00521-019-04495-0, 2019.
Y. Nagaraj, C. Jae Young et L. Bumshik, «MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer’s Disease: A Survey,» n° %1https://doi.org/10.3390/s20113243, 2020.
L. Siqi, L. Sidong, C. Weidong, P. Sonia, K. Ron et F. Dagan, «Early diagnosis of Alzheimer's disease with deep learning,» n° %110.1109/ISBI.2014.6868045, 2019.
K. Bijen, K. Goo-Rak et L. Ramesh, «Comparative analysis of Alzheimer’s disease classification by CDR level using CNN, feature selection, and machine-learning techniques,» n° %1 https://doi.org/10.1002/ima.2231, 2019.
Z.-d. Iliass, F. Anass, K. E. F. Jamal Riffi, E. B. Ismail, M. Mohamed Adnane et T. Hamid, «Brain tumor classification using features extraction and ensemble learning,» 2025.
G. Ahmed, M. Ghulam et H. M Shamim, «Cervical cancer classification using convolutional neural networks and extreme learning machines,» n° %1https://doi.org/10.1016/j.future.2019.09.015, 2020.
Zine-dine, J. Riffi, E. F. Khalid, M. Mohamed Adnane et T. Hamid, «Brain Tumor Classification using Machine and Transfer Learning,» n° %1DOI: 10.5220/0010762800003101, 2022.
J. Taeho, N. Kwangsik et J. S. Andrew, «Deep Learning in Alzheimer’s Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data,» n° %1https://doi.org/10.3389/fnagi.2019.00220, 2019.
W. Ahmad, P. B. Salehi et G. Gaurav, «Alzheimer’s Disease Diagnosis using Deep Learning Techniques,» n° %1DOI: 10.35940/ijeat.C5345.029320, 2020.
R. S. Iago R., L. S. Gabriela S., d. S. Rodrigo G., d. S. Wellington P. et d. A. F. Roberta A., «Model Based on Deep Feature Extraction for Diagnosis of Alzheimer’s Disease,» n° %110.1109/IJCNN.2019.8852138, 2019.
H. Ruhul Amin, M. Arnab Kumar, N. S. Samarendra, S. P. Babu et K. Debdatta, «A Survey on Classification Algorithms of Brain Images in Alzheimer’s Disease Based on Feature Extraction Techniques,» n° %110.1109/ACCESS.2021.3072559, 2021.
S. Muhammad, A. Shahzad, G. Aziz, N. Aneeta et U. Amina, «Classification of Alzheimer's Disease using Machine Learning Techniques,» n° %110.5220/0007949902960303, 2019.
P. Enrico, B. Lucia, D. C. Maria, H. Valdes, C. Francesca M., G.-C. Victor, A. Devasuda, D. Samuel, M.-M. Susana, J. Dominic et P. Cyril, «Machine learning of neuroimaging for assisted diagnosis of cognitive impairment and dementia: A systematic review. Alzheimer’s,» n° %1https://doi.org/10.1016/j.dadm.2018.07.004, 2018.
M.-P. José María, D. Mahsa, L.-A. María, I.-M. Yasser, Z. Yashar et C. and Alan, «Structural neuroimaging as clinical predictor: A review of machine learning applications,» n° %1https://doi.org/10.1016/j.nicl.2018.08.019, 2018.
L. Geert, K. Thijs, E. B. Babak, A. S. Arnaud Arindra, C. Francesco, G. Mohsen, V. D. L. Jeroen Awm, V. G. Bram et S. and Clara I., «A survey on deep learning in medical image analysis,» n° %1https://doi.org/10.1016/j.media.2017.07.005, 2017.
S. Dinggang, W. Guorong et a. H.-I. Suk, «Deep learning in medical image analysis,» n° %1https://doi.org/10.1146/annurev-bioeng-071516-044442, 2017.
Mehran, A. Hojjat et A. Anahita, «New diagnostic EEG markers of the Alzheimer’s disease using visibility graph,» n° %1https://doi.org/10.1007/s00702-010-0450-3, 2010.
R. Pedro et T. João Paulo, «Artifcial neural networks in the discrimination of Alzheimer’s disease,» n° %1https://doi.org/10.1007/978-3-642-24352-3_29, 2011.
C. Youngsang, S. Joon-Kyung, J. Yong et S. Sung Yong, «Alzheimer’s Disease Neuroimaging Initiative,» 2012.
Y. Jieping, C. Kewei, W. Teresa, L. Jing, Z. Zheng, P. Rinkal, B. Min, J. Ravi, L. Huan et A. Gene, «Heterogeneous data fusion for alzheimer’s disease study,» n° %110.1145/1401890.1402012, 2008.
Z. Daoqiang et S. Dinggang, «Semi-supervised multimodal classifcation of alzheimer’s disease,» n° %1DOI: 10.1109/ISBI.2011.5872715, 2011.
L. Feng, W. Chong-Yaw, C. Huafu et S. and Dinggang, «Inter-modality relationship constrained multimodality multi-task feature selection for Alzheimer’s disease and mild cognitive impairment identifcation,» n° %1https://doi.org/10.1007/978-3-642-40811-3_39, 2014.
T. Tong, G. Katherine, G. Qinquan, C. Liang et R. Daniel, «Multi-modal classifcation of Alzheimer’s disease using nonlinear graph fusion. Pattern Recogn,» n° %1https://doi.org/10.1016/j.patcog.2016.10.009, 2017.
K. Jongin et L. Boreom, «Identifcation of Alzheimer’s disease and mild cognitive impairment using multimodal sparse hierarchical extreme learning machine.,» n° %1https://doi.org/10.1002/hbm.24207, 2018.
S. Heung-Il et S. Dinggang, «Deep learning-based feature representation for AD/MCI classifcation,» n° %1https://doi.org/10.1007/978-3-642-40763-5_72, 2013.
P. Adrien et M. Giovanni, «Predicting Alzheimer’s disease: A neuroimaging study with 3D convolutional neural networks,» n° %1https://doi.org/10.48550/arXiv.1502.02506, 2015.
L. Siqi, L. Sidong, C. Weidong, C. Hangyu, P. Sonia, K. Ron, F. M. Dagan et F. J., «Multimodal neuroimaging feature learning for multiclass diagnosis of Alzheimer’s disease,» n° %110.1109/TBME.2014.2372011, 2015.
H.-A. Ehsan, G. Georgy et E.-B. Ayman, «Alzheimer’s disease diagnostics by a deeply supervised adaptable 3D convolutional network,» n° %1https://doi.org/10.48550/arXiv.1607.00556, 2016.
S. Heung-Il et S. Dinggang, «Deep ensemble sparse regression network for Alzheimer’s disease diagnosis,» n° %1https://doi.org/10.1007/978-3-319-47157-0_14, 2016.
S. Heung-Il, W. Chong-Yaw, L. Seong-Whan et S. Dinggang, «State-space model with deep learning,» n° %1https://doi.org/10.1016/j.neuroimage.2016.01.005, 2016.
D. Christos, M. R. Susan, W. X, P. P, Christopher et M. Clark, «Individual patient diagnosis of AD and FTD via high-dimensional pattern classifcation of MRI,» n° %1https://doi.org/10.1016/j.neuroimage.2008.03.050, 2008.
L. M., R. J., G. J. M., S.-G. D., A. I., S. F. et P. C. G., «Automatic tool for Alzheimer’s disease diagnosis using PCA and bayesian classifcation rules,» n° %1https://doi.org/10.1049/el.2009.0176, 2009.
T. M. et G. Manuel, «A two stage sequential ensemble applied to the classifcation of Alzheimer’s disease based on mri features,» n° %1https://doi.org/10.1007/s11063-011-9200-2, 2012.
C. Andrea, B. Paolo, C. Piero, G. Gianluca, E. Mario, O. Chiara, R. Luca, S. Sandro, R. Guido et B. Roberto, «Local MRI analysis approach in the diagnosis of early and prodromal Alzheimer’s disease,» n° %1https://doi.org/10.1016/j.neuroimage.2011.05.083, 2011.
H. Soheil et M. Mehdi, «Learning in data-limited multimodal scenarios: Scandent decision forests and tree-based features,» n° %1https://doi.org/10.1016/j.media.2016.07.012, 2016.
G. Neha, C. Mahipal Singh et M. B. Rajesh, «A review on Alzheimer’s disease classification from normal controls and mild cognitive impairment using structural MR images,» n° %1https://doi.org/10.1016/j.jneumeth.2022.109745, 2023.
L. S., L. S., C. W., C. H., P. S., K. R., F. D. et F. M. J., «Multimodal neuroimaging feature learning for multiclass diagnosis of Alzheimer’s disease,» n° %110.1109/TBME.2014.2372011, 2015.
L. F., T. L, H. T. K, J. S., S. D. et L. and J., «A robust deep model for improved classification of AD/MCI patients,» n° %1DOI: 10.1109/JBHI.2015.2429556, 2015.
B. T. et R. Tam, «Manifold learning of brain MRIs by deep learning,» n° %1https://doi.org/10.1007/978-3-642-40763-5_78, 2013.
S. N., H. G., S. I. et S. R., «Dropout: A simple way to prevent neural networks from overfitting,» 2014.
Karim, B.-P. Jenny et A. Karim, «Classification of sMRI for Alzheimer’s disease Diagnosis with CNN: Single Siamese Networks with 2D+ε Approach and Fusion on ADNI,» n° %1https://doi.org/10.1145/3078971.3079010, pp. 494 - 498, 2017.
S. Heung-Il, L. Seong-Whan et S. Dinggang, «Subclass-based multi-task learning for Alzheimer’s disease diagnosis,» n° %1 https://doi.org/10.3389/fnagi.2014.00168, 2014.
Y. S. Holtzman et D. M., «Interplay between innate immunity and Alzheimer disease: APOE and TREM2 in the spotlight,» n° %1https://doi.org/10.1038/s41577-018-0051-1, 2018.
L. Chunfeng, L. Mingxia, Z. Jun et S. Dinggang, «Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer’s Disease Diagnosis using Structural MRI,» n° %1doi: 10.1109/TPAMI.2018.2889096, 2018.
Z. Xin, H. Liangxiu, Z. Wenyong, S. Liang et Z. Daoqiang, «An Explainable 3D Residual Self-Attention Deep Neural Network For Joint Atrophy Localization and Alzheimer’s Disease Diagnosis using Structural MRI,» n° %110.1109/JBHI.2021.3066832, 2015.
Y. Jianzhou, L. Stephen, K. Sing Bing et T. Xiaoou, «Learning the Change for Automatic Image Cropping.,» Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 971-978, 2013.
M. Kiran, M. Surajit et N. Bhushan kumar, «A review: Data pre-processing and data augmentation techniques.,» n° %1https://doi.org/10.1016/j.gltp.2022.04.020, 2022.
D. ping Tian, «A Review on Image Feature Extraction and Representation Techniques.,» International Journal of Multimedia and Ubiquitous Engineering, Vols. %1 sur %2Vol. 8, No. 4, 2013.
S. Deepak et P. Amer, «Brain tumor classification using deep CNN features via transfer learning.,» n° %1https://doi.org/10.1016/j.compbiomed.2019.103345, 2019.
H. Acharya, R. Mehta et D. Kumar Singh, «Alzheimer Disease Classification Using Transfer Learning,» n° %1doi: 10.1109/ICCMC51019.2021.9418294, 2021.
N. Deepa et S. Chokkalingam, «Optimization of VGG16 utilizing the Arithmetic Optimization Algorithm for early detection of Alzheimer’s disease,» n° %1doi.org/10.1016/j.bspc.2021.103455, 2022.
L. V. Fulton, D. Dolezel, J. Harrop, Y. Yan et C. P. Fulton, «Classification of Alzheimer’s Disease with and without Imagery Using Gradient Boosted Machines and ResNet-50,» n° %1doi.org/10.3390/brainsci9090212, 2019.
R. Venkatesan, J. R. Alex Noel, P. T. Krishnan et N. Ganesh R., «A Customized VGG19 Network with Concatenation of Deep and Handcrafted Features for Brain Tumor Detection.,» n° %1https://doi.org/10.3390/app10103429, 2020.
S. Sara, F. Nicholas et H. Geoffrey E., «Dynamic Routing Between Capsules,» Advances in Neural Information Processing Systems, 2017.
P. R., R. Sumantra Dutta, M. Pravat K. et G. Shantanu, «High-Accuracy Detection of Early Parkinson's Disease through Multimodal Features and Machine Learning.,» n° %1https://doi.org/10.1016/j.ijmedinf.2016.03.001, 2016.
Cosimo, M. Nadia, B. Alessia, H. Amir et M. Francesco C., «A Convolutional Neural Network approach for Classification of Dementia Stages based on 2D-Spectral Representation of EEG recordings,» n° %1https://doi.org/10.1016/j.neucom.2018.09.071, 2018.
Z. Xin, H. Liangxiu, Z. Wenyong, S. Liang et Z. Daoqiang, «An explainable 3D residual self-Attention deep neural network for joint atrophy localization and Alzheimer’s disease diagnosis using structural MRI,» n° %110.1109/JBHI.2021.3066832, 2021.
K. L., R. J., G. J.M. et F. S. A. Brahim, «Initiative AsDN, Early diagnosis of Alzheimer ׳s disease based on partial least squares, principal component analysis and support vector machine using segmented MRI images,» n° %1https://doi.org/10.1016/j.neucom.2014.09.072, 2015.
G. C, Q. Q, I, Y-H, A. Gu et Jakola, «Multiscale Deep Convolutional Networks for Characterization and Detection of Alzheimer’s Disease Using MR Images,» n° %1doi: 10.1109/ICIP.2019.8803731, 2019.
Payan et G. Montana, «Predicting Alzheimer’s Disease: a Neuroimaging Study with 3D Convolutional Neural Networks,» n° %1https://doi.org/10.48550/arXiv.1502.02506, 2015.
J. Rachna, J. Nikita, A. Akshay et J. H. D., «Convolutional Neural Network based Alzheimer’s Disease Classification from Magnetic Resonance Brain Images,» n° %1https://doi.org/10.1016/j.cogsys.2018.12.015, 2018.
S. Daniel, S. Richard, T. Ruslan, V. Rostislav, L. John, S. Daniel et R. & David, «Applying Deep Learning to Predicting Dementia and Mild Cognitive Impairment,» https://doi.org/10.1007/978-3-030-49186-4_26, 2020.
Heta, M. Rutvik et S. Dheeraj Kumar, «Alzheimer Disease Classification Using Transfer Learning.,» n° %110.1109/ICCMC51019.2021.9418294, 2021.
S. Murugan, V. Chandran, S. M. G., G. Xiao-Zhi, E. B. et A. M., «DEMNET: A Deep Learning Model for Early Diagnosis of Alzheimer Diseases and Dementia From MR Images,» n° %110.1109/ACCESS.2021.3090474, 2021.
M. H. Khan et M. and Naimul, «Towards Alzheimer’s Disease Classification through Transfer Learning,» n° %110.1109/BIBM.2017.8217822, 2017.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
