Shahid Sumaiya Binte, Kaikaus Maleeha, Kabir Md Hasanul, Yousuf Mohammad Abu, Azad A K M, Al-Moisheer A S, Alotaibi Naif, Alyami Salem A, Bhuiyan Touhid, Moni Mohammad Ali
Institute of Information Technology, Jahangirnagar University, Savar, Dhaka, Bangladesh.
Department of Mathematics and Statistics, College of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia.
Front Bioinform. 2025 Aug 20;5:1567219. doi: 10.3389/fbinf.2025.1567219. eCollection 2025.
Alzheimer's disease (AD) is one of the most common neurodegenerative disabilities that often leads to memory loss, confusion, difficulty in 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 multi-class classification of different AD categories. Four transfer learning-based feature extractors, namely, ResNet152V2, 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 Demented (MoD), Mild Demented (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.
阿尔茨海默病（AD）是最常见的神经退行性疾病之一，常导致记忆力丧失、意识混乱、语言障碍和运动协调困难。尽管已经使用了几种机器学习（ML）和深度学习（DL）算法从磁共振成像（MRI）扫描中识别阿尔茨海默病（AD），但由于相邻类别具有共同特征，AD类别的精确分类仍然具有挑战性。
本研究提出了基于迁移学习的方法，用于从MRI扫描中提取特征，以对不同的AD类别进行多类别分类。四种基于迁移学习的特征提取器，即ResNet152V2、VGG16、InceptionV3和MobileNet，已应用于两个公开可用的数据集（即ADNI和OASIS）以及一个合并了ADNI和OASIS的数据集，每个数据集都有四个类别：中度痴呆（MoD）、轻度痴呆（MD）、极轻度痴呆（VMD）和非痴呆（ND）。
结果表明，改进的ResNet152V2是四种迁移学习方法中最优的特征提取器。接下来，通过使用改进的ResNet152V2作为特征提取器，融合Inception和ResNet架构，提出了一种基于卷积神经网络的模型，即“IncepRes”，用于AD类别的多类别分类。结果表明，我们提出的模型在ADNI、OASIS和合并数据集上分别达到了96.96%、98.35%和97.13%的标准准确率，优于其他竞争的DL结构。
我们希望我们提出的框架可以自动对各种AD类别进行精确分类，从而能够对与AD相关的认知和功能障碍提供及时的管理和治疗。
