Sharma Sarang, Gupta Sheifali, Gupta Deepali, Altameem Ayman, Saudagar Abdul Khader Jilani, Poonia Ramesh Chandra, Nayak Soumya Ranjan
Chitkara Institute of Engineering and Technology, Chitkara University, Punjab 140401, India.
Department of Computer Science and Engineering, College of Applied Studies and Community Services, King Saud University, Riyadh 11533, Saudi Arabia.
Diagnostics (Basel). 2022 Jul 29;12(8):1833. doi: 10.3390/diagnostics12081833.
Alzheimer's disease (AD) is a degenerative condition of the brain that affects the memory and reasoning abilities of patients. Memory is steadily wiped out by this condition, which gradually affects the brain's ability to think, recall, and form intentions. In order to properly identify this disease, a variety of manual imaging modalities including CT, MRI, PET, etc. are being used. These methods, however, are time-consuming and troublesome in the context of early diagnostics. This is why deep learning models have been devised that are less time-intensive, require less high-tech hardware or human interaction, continue to improve in performance, and are useful for the prediction of AD, which can also be verified by experimental results obtained by doctors in medical institutions or health care facilities. In this paper, we propose a hybrid-based AI-based model that includes the combination of both transfer learning (TL) and permutation-based machine learning (ML) voting classifier in terms of two basic phases. In the first phase of implementation, it comprises two TL-based models: namely, DenseNet-121 and Densenet-201 for features extraction, whereas in the second phase of implementation, it carries out three different ML classifiers like SVM, Naïve base and XGBoost for classification purposes. The final classifier outcomes are evaluated by means of permutations of the voting mechanism. The proposed model achieved accuracy of 91.75%, specificity of 96.5%, and an F1-score of 90.25. The dataset used for training was obtained from Kaggle and contains 6200 photos, including 896 images classified as mildly demented, 64 images classified as moderately demented, 3200 images classified as non-demented, and 1966 images classified as extremely mildly demented. The results show that the suggested model outperforms current state-of-the-art models. These models could be used to generate therapeutically viable methods for detecting AD in MRI images based on these results for clinical prospective.
阿尔茨海默病（AD）是一种大脑退行性疾病，会影响患者的记忆和推理能力。这种疾病会逐渐破坏记忆，进而逐步影响大脑的思考、回忆和形成意图的能力。为了准确识别这种疾病，人们使用了多种手动成像方式，包括CT、MRI、PET等。然而，在早期诊断的背景下，这些方法既耗时又麻烦。这就是为什么设计了深度学习模型，它们耗时较少，所需的高科技硬件或人工干预较少，性能不断提高，并且可用于AD的预测，医疗机构或医疗保健设施中的医生所获得的实验结果也可以验证这一点。在本文中，我们提出了一种基于混合人工智能的模型，该模型在两个基本阶段结合了迁移学习（TL）和基于排列的机器学习（ML）投票分类器。在实施的第一阶段，它包括两个基于TL的模型：即用于特征提取的DenseNet-121和Densenet-201，而在实施的第二阶段，它使用三种不同的ML分类器（如支持向量机、朴素贝叶斯和极端梯度提升）进行分类。最终的分类器结果通过投票机制的排列进行评估。所提出的模型准确率达到91.75%，特异性为96.5%，F1分数为90.25。用于训练的数据集来自Kaggle，包含6200张照片，其中包括896张分类为轻度痴呆的图像、64张分类为中度痴呆的图像、3200张分类为非痴呆的图像以及1966张分类为极轻度痴呆的图像。结果表明，所建议的模型优于当前的最先进模型。基于这些结果，这些模型可用于生成在MRI图像中检测AD的具有治疗可行性的方法，以供临床参考。
