Alzheimer’s disease (AD) is a neurodegenerative disorder that affects a wide range of individuals worldwide. It is of utmost importance to detect AD at an earlier stage and diagnose it to manage the disease effectively. Detecting AD using traditional methodologies is not cost-effective and time-consuming because of the clinical tests and neuroimaging methods involved. Over the last few years, quantum computing and deep learning (DL) have become practical approaches for detecting and diagnosing AD. Unlike conventional methods, quantum computing allows for faster solving complex and entangled computable problems. DL models have a high potential for automatically learning and extracting pertinent features even from larger datasets. Hence, a new approach combining multiple concepts such as deep neural network (DNN), quantum computing, simulated annealing (SA) optimisation, and Haralick feature extraction has been proposed in this work for detecting AD. A quantum deep neural network (QDNN) is introduced in this article to take over the extraordinary computational capability of quantum systems. Haralick feature extraction is implemented in this study to extract the texture features from the medical images, resulting in a rich feature set for the model. The dataset used in this study, The Best Alzheimer’s MRI Dataset contains 11,519 axial MRI images in .jpg format with a resolution of 128 × 128 pixels, categorised into four balanced classes—no impairment, very mild impairment, mild impairment, and moderate impairment—each comprising 2,560 images. To optimise the Haralick features from medical images and to enhance the model’s learning process with optimised parameters, a new feature-specific simulated annealing method (FSSA) has been introduced in this article. The experimental results proved that our model achieved an accuracy of 98%, a precision of 99%, a sensitivity of 97%, and a specificity of 98%. The results achieved in this study are better than the traditional model’s performance, and thus better in all performance metrics. The results indicated that the proposed QDNN model is a good framework for AD detection.
S et al. (Tue,) studied this question.