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.
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.
Parkinson's disease (PD) is a progressive neuro-degenerative condition with an urgent need for timely and pinpoint diagnosis for adequate treatment. Despite potential for prediction with traditional machine learning techniques, PD data remains difficult to solve for traditional machine learning techniques due to the high computational complexity and the nature of data. We introduce in this work a Hybrid Quantum-Classical AI Framework that combines advantages of QC and provide benefits in predictive accuracy as well as computational efficiency for real time Parkinson's disease detection. We use classical deep learning models in conjunction with Variational Quantum Circuits (VQC) to perform efficient feature extraction and classification of biomedical signals: speech and its recordings, gait analysis, and EEG data. We evaluate the performance of our proposed framework against deep learning models that are standard and based on the accuracy, precision, recall and processing time. Our experimental results suggest that our hybrid quantum classical model outperforms classical methods for both accuracy and efficiency, demonstrating the potential of quantum machine learning (QML) in healthcare. This work gives a taste of the quantum revolution realized in medical diagnostics and paves the way for what could in the future be quantum enhanced disease prediction.
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.
Parkinson disease (PD) is a neurological progressive disease that mainly impacts on speech, motor coordination and mobility, which causes a major reduction in the quality of life of patients. Timely and proper diagnosis is paramount to effective treatment, managing the symptoms, and monitoring the disease. As more biomedical data including voice signals and EEG recordings have become accessible, machine learning (ML) and artificial intelligence (AI) methods have been popular in automated PD detection. Traditional methods have shown good results through the use of Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), BiLSTM, Random Forest, and the Quantum Generative Adversarial Networks (QGAN). Nevertheless, these models are usually said to be limited by being computationally expensive, relying on large labeled datasets, the inability to deal with high-dimensional sequential data, limited ability to learn long-range temporal interactions, and the vanishing gradient problem. In order to cope with these issues, this paper presents a new Quantum Transformer-based system of Parkinson’s disease detection. The suggested model encodes voice features into quantum states and uses quantum self-attention mechanisms to effectively express the long-range dependencies and subtle interactions of feature. The hybrid quantum-classical learning architecture is applied to merge the benefits of quantum computation and the benefits of efficient classical optimization methods. According to experimental findings, the proposed Quantum Transformer is always more accurate, precise, and has a higher recall and F1-score than the existing models. Also, the model has lower value of losses, consistent convergence, and it has minimized overfitting. These results demonstrate that quantum-enhanced transformer-based architectures can be a reliable scalable solution to the clinical decision-support systems of the future that can be used to detect Parkinson’s disease early and accurately.
Introduction: Parkinson's disease (PD) is a progressive neurodegenerative disorder caused by the loss of dopaminergic neurons in the substantia nigra, presenting with motor and non-motor symptoms in roughly 2-3% of the global population above age 60. Early detection is difficult because symptoms are subtle and often indistinguishable from normal aging. The MDS-UPDRS rating scale, the current clinical standard, is time-intensive, subjective, and requires experienced clinicians. Most computational approaches are unimodal and do not use image and structured clinical data in combination. Methods: We propose a hybrid quantum-classical dual-track multimodal network that classifies PD patients and healthy controls from hand-drawn spiral and meander patterns. The first track, the Topological Visual-Spatial Feature Encoder Network (TVSFE), uses a ghost module-based CNN with Cross-Dimensional Attention Bottleneck (CDAB) blocks incorporating coordinate attention, squeeze-and-excitation, and triplet attention, followed by a quantum variational circuit with amplitude embedding. The second track, the Variational Quantum Feature Mapping Network (VQFMN), encodes structured clinical and demographic data through RY rotation gates and strongly entangling layers. Outputs from both tracks are concatenated and passed through fully connected layers for classification. Results: On the HandPD test set, the model achieved 97.28% accuracy, 96.60% precision, 96.62% recall, and 96.54% F1-score, outperforming all CNN, transformer, and ML-based baselines compared. Five-fold cross-validation produced a mean accuracy of 96.58%. On the NewHandPD dataset, accuracy, precision, recall, and F1-score were all 95.45%. Discussion: The quantum-classical fusion outperforms both single-modality and fully classical variants. Grad-CAM localizes the spatial image regions driving classification and the perturbation-based sensitivity analysis identifies Root Mean Square (RMS) and age as the most influential structured features. Both together make the model's reasoning traceable at the modality level, which is important for decision-making.
Parkinson's disease is a progressive neurological disorder.Speech, gait, and handwriting often change before a specialist can confirm the diagnosis.Clinics still depend heavily on observation, which takes time and can vary between doctors.Recent papers combine machine learning with quantum and hybrid quantum-classical models to improve screening from multimodal data.This review covers eight studies (2023-2026) that use Quantum LSTM, variational quantum circuits, quantum neural networks, quantum-inspired SVM, and metaheuristic feature selection for PD detection.We note which biomarkers each work uses, the accuracy or AUC reported, and repeated limits: simulation-only runs, public datasets, and weak clinical follow-up.A shared pipeline is summarised.Quantum AI may help earlier detection, but surveyed systems are not yet ready for routine hospital use without hardware noise tests and longer patient studies.
Classification of brain tumors from Magnetic Resonance Imaging (MRI) is a critical step in clinical diagnosis and treatment planning. While Convolutional Neural Networks (CNNs) achieve strong performance in medical imaging, they often suffer from class imbalance and limited generalization when trained on small datasets. This paper proposes a hybrid Convolutional Neural Network–Variational Quantum Classifier (CNN–VQC) framework for multiclass brain tumor classification. MRI scans are first preprocessed and normalized, after which an EfficientNet-B0 backbone extracts deep feature representations. Class imbalance is then addressed directly in the feature space by combining the Synthetic Minority Over-sampling Technique with Tomek-link cleaning (SMOTE-TOMEK), followed by Principal Component Analysis (PCA) for dimensionality reduction to enable quantum encoding. Finally, a variational quantum circuit coupled with a softmax layer performs the classification. The framework is evaluated on two benchmark datasets: the Kaggle Brain Tumor MRI dataset (Nickparvar, 7,023 images, four classes) and the Figshare Brain Tumor Dataset (Cheng et al., 3,064 images, three classes). Across five stratified runs, the proposed model attains accuracies of 94.8±0.4% and 93.1±0.5% respectively, with macro F1-scores of 0.941 and 0.927, outperforming EfficientNet-B0, ResNet-18, and standalone VQC baselines with statistically significant margins (paired t-test, p<0.01). Additional analyses of computational complexity, inference latency, and noisy quantum simulation demonstrate the practical feasibility of the proposed approach on near-term quantum hardware.