Novel Deep Learning for Multi-class Classification of Alzheimer's in Disability using MRI Datasets

Mohammad Ali Moni^1,2*Sumaiya Binte Shahid³Maleeha Kaikaus³Md. Hasanul Kabir³Mohammad Abu Yousuf^3*AKM Azad⁴A. S. Al-Moisheer⁵Naif Alotaibi⁴Dr. Salem A. Alyami⁴Touhid Bhuiyan²

• ¹The University of Queensland, Brisbane, Australia
• ²Daffodil International University, Dhaka, Dhaka, Bangladesh
• ³Jahangirnagar University, Dhaka, Dhaka, Bangladesh
• ⁴Department of Mathematics and Statistics, College of Science, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi Arabia
• ⁵Jouf University, Sakakah, Al Jawf, Saudi Arabia

Alzheimer's disease (AD) is one of the most common neuro-degenerative disabilities that often leads to memory loss, confusion, difficulty with language, and trouble with motor coordination. Although several machine learning (ML) and deep learning (DL) algorithms have been utilized to identify Alzheimer's disease (AD) from MRI scans, precise classification of AD categories remains challenging as neighbouring categories share common features. This study proposes transfer learning-based methods for extracting features from MRI scans for multiclass classification of different AD categories. Four transfer learning-based feature extractors, namely, ResNet152, VGG16, InceptionV3, and MobileNet have been employed on two publicly available datasets (i.e., ADNI and OASIS) and a Merged dataset combining ADNI and OASIS, each having four categories: Moderate(MoD), Mild (MD), Very Mild Demented (VMD), and Non-Demented (ND). Results suggest the Modified ResNet152V2 as the optimal feature extractor among the four transfer learning methods. Next, by utilizing the modified ResNet152V2 as a feature extractor, a Convolutional Neural Network-based model, namely the 'IncepRes', is proposed by fusing the Inception and ResNet architectures for multiclass classification of AD categories. The results indicate that our proposed model achieved a standard accuracy of 96.96% , 98.35% and 97.13% for ADNI, OASIS and Merged datasets, respectively, outperforming other competing DL structures.We hope that our proposed framework may automate the precise classifications of various AD categories, and thereby can offer the prompt management and treatment of cognitive and functional impairments associated with AD.