Wei Chen
ABSTRACT
Alzheimer’s disease, a prevalent form of dementia, is a progressive, long-term and irreversible neurological disorder. With the growing elderly population, there has been a significant rise in the number of individuals affected by Alzheimer’s disease, which will bring serious social and economic burdens to countries all over the world. Therefore, it is crucial to identify and diagnose Alzheimer’s disease and its current disease stage promptly and accurately to facilitate prompt intervention and treatment. This paper proposes an ensemble model that combines the convolutional neural network (ResNet50, DenseNet121, EfficientNet_B0) and Transformer architectures (Vision Transformer, TransFG) to predict Alzheimer’s disease patients and their current disease stage. The ensemble model exhibits impressive classification accuracy, with 98.91% accuracy, a Micro Area Under the Curve (micro-AUC) of 0.9996, and a macro-AUC of 0.9995. And the ensemble model accurately differentiates Alzheimer’s disease cases and their current disease stages. The proposed ensemble model exhibits classification accuracies of 99.06%, 99.11%, 97.78%, and 100% for healthy control, very mild, mild, and moderate cases respectively. By utilizing this ensemble model, healthcare professionals can rely on a more accurate prediction tool for Alzheimer’s disease and its current disease stage, which enables them to devise personalized treatment plans and nursing measures for affected patients.
- D Australia, S Baker, S Banerjee, 2019. Alzheimer’s Disease International World Alzheimer Report 2019: Attitudes to Dementia. Alzheimer’s Disease International; Alzheimer’s Disease International: London, UK (2019).Google Scholar
- Kaj Blennow, Mony J de Leon, and Henrik Zetterberg. 2006. Alzheimer’s disease. The Lancet 368, 9533 (2006), 387–403.Google Scholar
- Rémi Cuingnet, Emilie Gerardin, Jérôme Tessieras, Guillaume Auzias, Stéphane Lehéricy, Marie-Odile Habert, Marie Chupin, Habib Benali, Olivier Colliot, Alzheimer’s Disease Neuroimaging Initiative, 2011. Automatic classification of patients with Alzheimer’s disease from structural MRI: a comparison of ten methods using the ADNI database. neuroimage 56, 2 (2011), 766–781.Google Scholar
- Jeffrey Cummings, Garam Lee, Aaron Ritter, and Kate Zhong. 2018. Alzheimer’s disease drug development pipeline: 2018. Alzheimer’s & Dementia: Translational Research & Clinical Interventions 4 (2018), 195–214.Google Scholar
- Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).Google Scholar
- Bruno Dubois, Howard H Feldman, Claudia Jacova, Steven T DeKosky, Pascale Barberger-Gateau, Jeffrey Cummings, André Delacourte, Douglas Galasko, Serge Gauthier, Gregory Jicha, 2007. Research criteria for the diagnosis of Alzheimer’s disease: revising the NINCDS–ADRDA criteria. The Lancet Neurology 6, 8 (2007), 734–746.Google ScholarCross Ref
- Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, and Changhu Wang. 2022. Transfg: A transformer architecture for fine-grained recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 852–860.Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.Google ScholarCross Ref
- Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. 2017. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4700–4708.Google ScholarCross Ref
- Clifford R Jack Jr, David A Bennett, Kaj Blennow, Maria C Carrillo, Billy Dunn, Samantha Budd Haeberlein, David M Holtzman, William Jagust, Frank Jessen, Jason Karlawish, 2018. NIA-AA research framework: toward a biological definition of Alzheimer’s disease. Alzheimer’s & Dementia 14, 4 (2018), 535–562.Google Scholar
- Jianping Jia, Cuibai Wei, Shuoqi Chen, Fangyu Li, YI Tang, Wei Qin, Lina Zhao, Hongmei Jin, Hui Xu, Fen Wang, 2018. The cost of Alzheimer’s disease in China and re-estimation of costs worldwide. Alzheimer’s & Dementia 14, 4 (2018), 483–491.Google Scholar
- Sergey Korolev, Amir Safiullin, Mikhail Belyaev, and Yulia Dodonova. 2017. Residual and plain convolutional neural networks for 3D brain MRI classification. In 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017). IEEE, 835–838.Google ScholarCross Ref
- AV Lebedev, Eric Westman, GJP Van Westen, MG Kramberger, Arvid Lundervold, Dag Aarsland, H Soininen, I Kłoszewska, P Mecocci, M Tsolaki, 2014. Random Forest ensembles for detection and prediction of Alzheimer’s disease with a good between-cohort robustness. NeuroImage: Clinical 6 (2014), 115–125.Google ScholarCross Ref
- Bing Yan Lim, Khin Wee Lai, Khairunnisa Haiskin, KA Kulathilake, Zhi Chao Ong, Yan Chai Hum, Samiappan Dhanalakshmi, Xiang Wu, and Xiaowei Zuo. 2022. Deep learning model for prediction of progressive mild cognitive impairment to Alzheimer’s disease using structural MRI. Frontiers in Aging Neuroscience 14 (2022), 876202.Google ScholarCross Ref
- Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen Awm Van Der Laak, Bram Van Ginneken, and Clara I Sánchez. 2017. A survey on deep learning in medical image analysis. Medical image analysis 42 (2017), 60–88.Google Scholar
- Lisa Mosconi, Wai H Tsui, Karl Herholz, Alberto Pupi, Alexander Drzezga, Giovanni Lucignani, Eric M Reiman, Vjera Holthoff, Elke Kalbe, Sandro Sorbi, 2008. Multicenter standardized 18F-FDG PET diagnosis of mild cognitive impairment, Alzheimer’s disease, and other dementias. Journal of nuclear medicine 49, 3 (2008), 390–398.Google ScholarCross Ref
- Emma Nichols and Theo Vos. 2021. The estimation of the global prevalence of dementia from 1990-2019 and forecasted prevalence through 2050: an analysis for the Global Burden of Disease (GBD) study 2019. Alzheimer’s & Dementia 17 (2021), e051496.Google Scholar
- Modupe Odusami, Rytis Maskeliūnas, Robertas Damaševičius, and Tomas Krilavičius. 2021. Analysis of features of Alzheimer’s disease: Detection of early stage from functional brain changes in magnetic resonance images using a finetuned ResNet18 network. Diagnostics 11, 6 (2021), 1071.Google ScholarCross Ref
- Rafael B Pereira, Alexandre Plastino, Bianca Zadrozny, and Luiz HC Merschmann. 2018. Correlation analysis of performance measures for multi-label classification. Information Processing & Management 54, 3 (2018), 359–369.Google ScholarDigital Library
- Philip Scheltens, Kaj Blennow, Monique MB Breteler, Bart De Strooper, Giovanni B Frisoni, Stephen Salloway, and Wiesje Maria Van der Flier. 2016. Alzheimer’s disease. The Lancet 388, 10043 (2016), 505–517.Google ScholarCross Ref
- Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105–6114.Google Scholar
- Theo Vos, Stephen S Lim, Cristiana Abbafati, Kaja M Abbas, Mohammad Abbasi, Mitra Abbasifard, Mohsen Abbasi-Kangevari, Hedayat Abbastabar, Foad Abd-Allah, Ahmed Abdelalim, 2020. Global burden of 369 diseases and injuries in 204 countries and territories, 1990–2019: a systematic analysis for the Global Burden of Disease Study 2019. The Lancet 396, 10258 (2020), 1204–1222.Google ScholarCross Ref
- Tayyabah Yousaf, George Dervenoulas, and Marios Politis. 2018. Advances in MRI methodology. International review of neurobiology 141 (2018), 31–76.Google ScholarCross Ref
Index Terms
- Ensemble Model for Predicting Alzheimer's Disease and Disease Stages with CNN and Transformer Models
Recommendations
Diagnosis of Alzheimer's disease using Naive Bayesian Classifier
In the world of modern medicine, though there is lot of medical achievements, some diseases still continue to pest the human race. Unfortunately, dementia is one such disease. All over the world, a large number of people are suffering from dementia. ...
A Hybrid Deep Learning model for predicting the early Alzheimer’s Disease stages using MRI
SETN '22: Proceedings of the 12th Hellenic Conference on Artificial IntelligenceThe continuous evolution of technology in Biomedicine has given satisfactory answers for several complex diseases. Alzheimer’s disease (AD), one of the major neurodegenerative diseases that cause dementia, belongs to this category. So far, no cure ...
Everyday Patient-Care Technologies for Alzheimer's Disease
The Alzheimer's Association has stimulated collaboration and scientific advancement in preventing and treating Alzheimer's disease by bringing together leading researchers developing technological approaches offering promise in this area. This year, the ...
Comments