Alzheimer's disease (AD) is a debilitating neurodegenerative condition that affects millions globally, with early diagnosis being crucial for effective intervention and treatment. This project explores Quantum Neural Networks (QNN) combined with Magnetic Resonance Imaging (MRI) data to enhance diagnosis accuracy. This hybrid quantum- classical approach leverages advanced preprocessing techniques, uncovering intricate patterns in MRI data. The study highlights the potential of quantum computing in revolutionizing early-stage Alzheimer's detection, achieving superior performance over traditional methods. Keywords— Alzheimer’s disease, Quantum Computing, MRI, Machine Learning, Quantum Neural Networks
Alzheimer's disease (AD) is a debilitating neurodegenerative condition that affects millions globally, with early diagnosis being crucial for effective intervention and treatment. This project explores Quantum Neural Networks (QNN) combined with Magnetic Resonance Imaging (MRI) data to enhance diagnosis accuracy. This hybrid quantum- classical approach leverages advanced preprocessing techniques, uncovering intricate patterns in MRI data. The study highlights the potential of quantum computing in revolutionizing early-stage Alzheimer's detection, achieving superior performance over traditional methods. Keywords— Alzheimer’s disease, Quantum Computing, MRI, Machine Learning, Quantum Neural Networks
Alzheimer’s disease is neurodegerative disorder that affects memory of a person and also the day to day activities of them. Normally, Alzheimer’s disease can be identified by using the MRI scans which consist of high dimensional data. Traditional machine learning models are filed to give higher accuracy while diagnosing the disease. Quantum technologies plays a vital role and its emerging technologies that produce higher accuracy compared to traditional models. In this study we provide a comprehensive review of quantum technology such as Quantum Machine Learning (QML), Quantum Neural Networks (QNN) and Hybrid Quantum Models. Key factors of this study include early identification of Alzheimer’s disease by utilizing the higher dimension of data like MRI images. Further, this article focuses on the application, limitations such as hardware constraints and scalability of clinical decision support system.
‘Quantum Convolutional Neural Networks’ - QCNN is quantum machine learning model that has the potential of improving the accuracy of Alzheimer’s Disease (AD) diagnosis. Alzheimer’s disease - a neurodegenerative disorder - is considered to be the major cause of Dementia. Early diagnosis of AD is critical for improving patient outcomes. However, current diagnostic methods are often less accurate and time-consuming. QCNNs are able to learn complex features from data, which could be used to identify early signs of AD thereby resulting in an early diagnosis of a disease. This proposed technique will investigate the use of QCNN for AD diagnosis. A QCNN will be trained on a large image dataset from healthy controls & AD patients. The QCNN will then be fine-tuned on a smaller image datasets of patients with suspected AD. The performance of the QCNN will be evaluated on a test dataset of images from patients with suspected AD. This work attempts to design and develop a technique for early disease diagnosis. The QCNN could achieve 88% accuracy in classifying the data(2022) Li et al.[2]. They used a QCNN to diagnose AD from brain functional connectivity data. In another study, by Chen et al.[3], a QCNN could achieve 90% accuracy in classifying the images (2022). So taking inspiration from this, we are proposing to fine tune the QCNN in such a way as to further improve its performance and thereby resulting in more accuracy. The results of the proposed work would highlight the potential of QCNN for AD early diagnosis. If the results are promising, QCNN could be a valuable tool for early diagnosis of Alzheimer’s disease and thereby assists in saving millions of lives.
Alzheimer's disease (AD) presents significant diagnostic challenges owing to the subtle morphological similarities observed in the early stages, with traditional deep learning approaches often struggling to distinguish between the various stages of disease progression via structural Magnetic Resonance Imaging (MRI) data. Quantum computing offers unique advantages for medical image analysis, leveraging superposition and entanglement capabilities to process high-dimensional feature spaces beyond the limits of classical computation. This study introduces a hybrid quantum-classical neural network architecture (HQC-Net) for accurate four-class Alzheimer's disease classification, which uses quantum processing to detect patterns that are often invisible to classical spatial analysis methods. The proposed framework integrates classical feature extractors, including a custom CNN and modified ResNet18, with six-qubit variational quantum circuits that employ multiaxis rotation encoding (RY→RZ→RX), a quantum Fourier transform for spectral decomposition, and multihead attention for effective quantum-classical feature fusion. Comprehensive evaluations were conducted on the Kaggle dataset (5,121 samples) and the OASIS dataset (20,000 samples), incorporating realistic quantum noise modelling, including depolarising, amplitude damping, and phase damping channels. The modified QResNet18 configuration achieved a test accuracy of 99.67%, with perfect discriminative capability (AUC = 1.0000) on the OASIS dataset. Quantum processing demonstrated superior detection of very mild dementia (99.86% accuracy), which is crucial for early intervention. The proposed approach outperformed existing quantum-enhanced methods by 3.57 percentage points while effectively handling the increased diagnostic complexity associated with four-class classification. This study demonstrates a practical quantum advantage for multiclass neuroimaging classification, achieving superior diagnostic accuracy while maintaining computational efficiency and clinical deployment feasibility under current Noisy Intermediate-Scale Quantum (NISQ) hardware constraints.
Alzheimer's disease (AD), a progressive neurodegenerative disorder, presents significant challenges in early diagnosis and treatment. Advancements in Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL), when combined with the power of computation of Quantum Computing (QC), offer promising avenues for the prediction and diagnosis of AD. This literature review surveys twenty research studies exploring the combination of QC with AI/ML/DL for AD prediction and compared through algorithms, evaluation metrics, time for training, datasets separately for ML and DL models. Challenges in current implementations and directions for research work are identified in review summary. The novelty of this review lies in its systematic comparison of quantum-assisted AI models across both machine learning and deep learning paradigms for Alzheimer’s detection, highlighting recent (2020–2024) research progress, performance benchmarks, and open challenges.
Alzheimer’s Disease (AD) first strikes learning regions of the brain and is one of the most prevalent forms of dementia. Early diagnosis is crucial for optimum management of treatment, as the disorder is both irreversible and progressive. The current research outlines an end-to-end approach toward early diagnosis of AD by utilizing the hippocampus and transfer learning. The results of a conventional machine learning model—Convolutional Neural Network (CNN)—are compared to those of a Quantum Convolutional Neural Network (QCNN), an adaptation of the conventional CNN through the use of quantum computing methods like quantum kernel estimation. QCNN achieves greater efficiency in processing high-dimensional data than traditional CNNs. The main symptoms of Alzheimer’s are memory loss and cognitive impairment, caused by the degeneration and death of those neurons related to memory. Mild Cognitive Impairment (MCI) lies between cognition within the range of normality and Alzheimer’s. The early diagnosis of MCI has the potential to decelerate or even prevent the development of Alzheimer’s. In this paper, we have established that the QCNN model reached precision at 0.88 and recall at 0.96, compared to the classic CNN, where precision at 0.80, and recall at 0.84 have been achieved. The results highlight the prospective ability of Quantum Machine Learning (QML) to diagnose Alzheimer’s Disease at an early stage.
Abstract Neuro-imaging data is necessary for timely and correct diagnosis of the disease Alzheimer’s (AD). Early clinical intervention is challenging due to the high-dimensional nature of the images, making it computationally difficult to work on representations, sparse annotated datasets and inter-subject variance. Deep convolutional VGG, ResNet, DenseNet, MobileNet and other neural networks (CNNs) have shown good performance. Diagnostic performance, but they are based on a high number of parameters and require highly trained personnel. Data can often times restrict resilience to data-skimy clinical settings. To address these challenges, the current paper presents a hybrid Quantum Machine Learning (QML) architecture for Alzheimer’s disease Detection and classification based on a combination of classical CNN-based feature extraction and Variational quantum classifier. In the suggested method, diseased, relevant, and compact features are extracted using pre-trained CNN backbones. Data from structural MRI scans is later translated into quantum states and computed. With parameterised variational quantum circuits optimised with a hybrid quantum-classical learning loop. The proposed method has been experimentally evaluated on benchmark datasets of MRI scans of Alzheimer’s patients. The hybrid CNNQML model has a mean classification accuracy of about 93% which is similar to deep CNN models, including ResNet and DenseNet (94%), and much more. Beating lightweight models like MobileNet and shallow CNNs by six percentage points. It is worth noting that the hybrid QML model performs better in conditions with limited training data. Performance degradation is observed in accuracy and AUC for all CNN variants, with up to 5% lower performance to deep CNNs. Cross-validation, confidence interval, paired significance test, and statistical validation. Effect size analysis proves the fact that the hybrid model produces statistically significant performance, as well as cases of clinically meaningful improvements over lightweight CNN baselines. Similar to the state-of-the-art deep networks with significantly reduced trainable parameters in the classification stage. These findings show that hybrid QML is a data-efficient and powerful substitute in the diagnosis of Alzheimer’s. On the whole, this is a work that sets a practical way to integrate quantum machine learning into clinical neuro-imaging pipelines and hybrid settings. QML has supplementary deep-learning enhancement to classics in next-generation Alzheimer’s Decision-support systems.