Neurodegenerative diseases are a group of progressive disorders that affect the nervous system, characterized by a gradual deterioration in mental and physical functions.In the domain of neurodegenerative diseases, Alzheimer's disease (AD) and Parkinson's disease (PD) are some of the most prevalent diseases that are very difficult to diagnose in advance stages.In order to address the issue of the present methods that are currently practiced for the diagnosis of neurodegenerative diseases, a novel diagnostic approach, termed as Neuro-Q-Net, is proposed in the developmental work of this study that possesses the capability to diagnose more than one neurodegenerative disease at a time using the Fluorodeoxyglucose Positron Emits Scan images taken from the brain of a human.In order to address the issue of unavailability of imbalanced scans in the domain of medicine, the utilization of a novel approach in computer science, termed as a Generational Adversarial Network (Gan), is suggested that assist in generating highquality images to increase the efficiency of neural networks.We use deep convolutional neural networks for feature identification, followed by Quantum Machine Learning.Our experiments show that this approach outperforms existing models in accuracy, specificity, and sensitivity.The proposed system offers an effective clinical tool for diagnosing neuro-degenerative illnesses.
Neurodegenerative diseases are a group of progressive disorders that affect the nervous system, characterized by a gradual deterioration in mental and physical functions.In the domain of neurodegenerative diseases, Alzheimer's disease (AD) and Parkinson's disease (PD) are some of the most prevalent diseases that are very difficult to diagnose in advance stages.In order to address the issue of the present methods that are currently practiced for the diagnosis of neurodegenerative diseases, a novel diagnostic approach, termed as Neuro-Q-Net, is proposed in the developmental work of this study that possesses the capability to diagnose more than one neurodegenerative disease at a time using the Fluorodeoxyglucose Positron Emits Scan images taken from the brain of a human.In order to address the issue of unavailability of imbalanced scans in the domain of medicine, the utilization of a novel approach in computer science, termed as a Generational Adversarial Network (Gan), is suggested that assist in generating highquality images to increase the efficiency of neural networks.We use deep convolutional neural networks for feature identification, followed by Quantum Machine Learning.Our experiments show that this approach outperforms existing models in accuracy, specificity, and sensitivity.The proposed system offers an effective clinical tool for diagnosing neuro-degenerative illnesses.
Abstract Parkinson’s disease (PD) involves a slowly advancing neurological condition that profoundly impairs motor as well as cognitive abilities, making prompt and precise diagnosis essential for successful treatment. Diagnosing PD using MRI images is difficult because of subtle changes within the brain and imbalanced datasets. While existing methods such as traditional Machine Learning (ML) and Deep Learning (DL) have made progress, they often struggle to capture important features and effectively handle limited data . To resolve these concerns, this work suggests a combined approach starting with generating additional MRI images using a Deep Convolutional Generative Adversarial Network (DCGAN) to balance the dataset. The feature extraction from these images is performed using the InceptionV3 model. These features are then enhanced by a Pyramid Attention Network (PAN), which helps to concentrate on the data’s most pertinent sections. Finally, the enhanced features are classified using a Variational Quantum Classifier (VQC) with amplitude encoding, which leverages quantum-inspired ML techniques to improve classification performance. This pipeline achieved an overall accuracy of 82.04%, outperforming earlier models. The results demonstrate the feasibility of integrating quantum-inspired models within a hybrid framework for PD classification from MRI scans.
‘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 is a progressive and degenerative brain disorder causing impairment in memory and cognitive function. It is the most common form of Dementia and the prevalence of Alzheimer’s disease (AD) increases with each decade of life. This usually starts in late middle age to old age resulting in progressive memory loss, impaired thinking, disorientation and changes in personality. Neurons are first lost in the hippocampus (the brain’s centre for memory and learning), and presence of neurofibrillary tangles and plaques containing beta-amyloid cells. Owing to the progressive nature of the disease and the complex structure of the brain, the exact causes, mechanisms and how Alzheimer’s spread is not completely understood thereby inhibiting in the production of a cure for the disease. Quantum Machine Learning (QML) is a promising area of research for the detection and diagnosis of Alzheimer’s disease. PET scan helps in diagnosing Alzheimer’s by detecting the amyloid plaques and tau tangles. It reveals areas with reduced metabolism, which helps differentiate Alzheimer’s from other conditions. Quantum computing provides a more efficient model for different disease classification tasks than classical machine learning approaches. In this study, we propose a model based on quantum machine learning classifiers to classify Alzheimer’s disease. This showcases the feasibility of Quantum enhanced classification and detection of AD for extremely limited medical datasets.
The prompt detection of neurodegenerative diseases (NDDs) like Alzheimer's Disease (AD), Mild Cognitive Impairment (MCI), and Parkinson's Disease (PD) is essential yet difficult. This research proposes a hybrid quantum-classical machine learning methodology to categorize NDD using multimodal brain imaging data.ADNI and PPMI datasets' MRI, PET, and fMRI images were preprocessing by Python-based tools such as Scikit-image, SimpleITK, and FreeSurfer via Nipype. Major steps were denoising, registration, normalization, segmentation, and extraction of features from structural and functional imaging. Training was done with a Quantum Support Vector Machine (QSVM) using Qiskit's ZZFeatureMap and QuantumKernel and compared with a conventional SVM. Performance measures-precision, recall, F1-score, class accuracy, AUC, and 10-fold cross-validation-were calculated. QSVM performed better than the standard SVM on all metrics, with 91.25% overall accuracy and macro F1-score of 0.913 as opposed to 87.75% and 0.879 for the SVM. The results validate QSVM's advantage in handling complex, high-dimensional neuroimaging data and its relevance to aiding clinical diagnosis. Keywords: Quantum Machine Learning, Neuroimaging, QSVM, Alzheimer’s Disease, Parkinson’s Disease, Multimodal Classification
The population aged 60 years is rapid increased to 20% of the total Indian population according to the statistics. Alzheimer is a disease which is a neurogenerative disorder. It is considered as the major cause of dementia. India is in critical scenario that faces increase in the elder population suffering from dementia. Hence, there arise a need for early diagnosis of Alzheimer disease (AD) in order to improve the patient’s mental health condition. Though, the existing diagnostic methods are accurate and fast computing, there arise a need to propose a model that aids in improved accuracy and reducing the computational time for early prediction of AD.The proposed model uses Enhanced variational Quantum Network(VAQ) that aids in improving the potential of AD in terms of accuracy and time complexity is designed to decide the feature extraction by processing the huge voluminous images and then fed the outcome into the classifier model. Alzheimer disease neuroimaging stage I and stage II are the datasets considered for applying VAQ for AD prediction. Both stage I and stage II dataset were combined together in order to process the resource efficiently for the diagnosis performs feature extraction and then the results been fed as input to the Quantum classifier. The classifier processes the data and classify the images as no dement, mild dement, average dement, very mild dement. The results are compared with already existing Convolutional Neural Network model (CNN) and Ensemble Classifier.
A novel technique in early Parkinson's disease diagnosis with the use of a quantum long short-term memory model is described in this paper. Quantum computing, therefore, coupled with deep learning, seeks to improve the accuracy as well as efficiency of classifying traditional LSTM models, which even becomes more critical in cases of neurodegenerative diseases like Parkinson's disease, where diagnostics at an early stage would be helpful. The model was tested heavily on public datasets and compared with traditional deep learning models, which were significantly outperformed by this model with its superior accuracy and precision and recall rates. Furthermore, the computation time hugely became lower and thus possibly may revolutionize diagnostic procedures. These innovations will eventually establish quantum machine learning in medicine at a more accurate and faster diagnosis pace. Future development will focus on expanding the quantum LSTM so it can be more generally applicable to various situations for other medical conditions. Researchers believe that the configuration of the quantum layers should be modified, and this model will be extended to other deep learning models to have a more comprehensive and versatile tool in diagnosis for Parkinson's disease and perhaps other medical uses. The ultimate vision in the long term would be to use quantum-based models, not only for early detection but also improvement in prediction and personalization of treatment to revolutionize health care and thereby improve patient outcomes with neurodegenerative diseases.