Abstract Accurate detection of multiple sclerosis (MS) lesions in magnetic resonance imaging (MRI) requires robust deep learning models to capture subtle spatial and textural features. We introduce hybrid quantum-classical transfer learning algorithms for MS classification using axial and sagittal MRI scans, combining classical convolutional neural networks (CNNs) including EfficientNetB3, ResNet50, DenseNet121 with parameterized quantum circuits to enhance feature representation via entanglement and quantum-specific non-linearities. Quantum layers are trained end-to-end with classical backbones via backpropagation, enabling seamless integration of quantum-enhanced features. For axial MRI, QResNet50 achieved a high accuracy of 97.58% and AUC of 99.31%, while QDenseNet121 reached 97.28% accuracy and 99.13% AUC. For sagittal MRI, classical ResNet50 excelled with 99.15% accuracy and 99.93% AUC, while QEfficientNetB3 improved accuracy (97.46% to 98.30%) but reduced AUC (99.51% to 99.32%), and QDenseNet121 achieved 98.87% accuracy and 99.83% AUC. Hybrid models showed mixed results, with QCNN underperforming, suggesting quantum benefits are architecture-dependent. Despite simulated quantum circuits mitigating hardware limitations, our results demonstrate the potential to enhance diagnostic performance in specific architectures. This work clarifies a foundational step toward quantum-enhanced deep learning for clinical applications, opening research directions in quantum-aware transfer learning and error mitigation for biomedical imaging.
Abstract Accurate detection of multiple sclerosis (MS) lesions in magnetic resonance imaging (MRI) requires robust deep learning models to capture subtle spatial and textural features. We introduce hybrid quantum-classical transfer learning algorithms for MS classification using axial and sagittal MRI scans, combining classical convolutional neural networks (CNNs) including EfficientNetB3, ResNet50, DenseNet121 with parameterized quantum circuits to enhance feature representation via entanglement and quantum-specific non-linearities. Quantum layers are trained end-to-end with classical backbones via backpropagation, enabling seamless integration of quantum-enhanced features. For axial MRI, QResNet50 achieved a high accuracy of 97.58% and AUC of 99.31%, while QDenseNet121 reached 97.28% accuracy and 99.13% AUC. For sagittal MRI, classical ResNet50 excelled with 99.15% accuracy and 99.93% AUC, while QEfficientNetB3 improved accuracy (97.46% to 98.30%) but reduced AUC (99.51% to 99.32%), and QDenseNet121 achieved 98.87% accuracy and 99.83% AUC. Hybrid models showed mixed results, with QCNN underperforming, suggesting quantum benefits are architecture-dependent. Despite simulated quantum circuits mitigating hardware limitations, our results demonstrate the potential to enhance diagnostic performance in specific architectures. This work clarifies a foundational step toward quantum-enhanced deep learning for clinical applications, opening research directions in quantum-aware transfer learning and error mitigation for biomedical imaging.
Accurate and computationally efficient classification of brain tumors from MRI scans is critical for deployment in resource-constrained clinical settings, where conventional deep CNN architectures-despite achieving strong accuracy-often require large parameter counts that limit scalability. This work proposes a hybrid quantum-classical deep learning framework that combines a classical convolutional feature extractor with a variational quantum circuit (VQC) for multi-class tumor classification. Spatial features extracted by the CNN backbone will be dimensionality-reduced and encoded into quantum states using angle encoding; a parameterized quantum circuit will then process these features in a higher-dimensional Hilbert space, leveraging superposition and entanglement to capture non-linear feature correlations. Measurement outputs from the quantum layer will be passed to a classical fully connected layer for classification into glioma, meningioma, pituitary tumor, and no-tumor categories. The proposed framework will be evaluated on a publicly available benchmark MRI dataset and benchmarked against state-of-the-art classical CNN architectures in terms of accuracy, precision, recall, F1-score, and parameter efficiency. This study aims to demonstrate that quantum-enhanced layers can achieve competitive classification performance while substantially reducing trainable parameters, offering a practical direction for efficient, quantum-assisted medical image analysis.
The characterization of brain tumors from magnetic resonance imaging (MRI) is crucial for diagnosis, treatment planning, and prognosis. But the analysis of brain tumors based on MRI is still difficult because of the significant intra-tumoral heterogeneity, ambiguous boundaries of lesions, high dimensionality of imaging features, and complicated nonlinear relationships between anatomical structures. While transformer-based deep learning (DL) models have greatly advanced automated tumor analysis, classical feature representations often fail to effectively capture complex feature interactions in pathological images, especially when distinguishing between subtle pathological variations and normal tissue needs to be done efficiently. Recent quantum machine learning (QML) developments indicate that quantum feature encoding can map complex data to exponentially larger Hilbert spaces, leading to a more expressive representation of nonlinear patterns and feature correlations that are challenging to model with conventional architectures. Encouraged by this potential, this study proposes a hybrid quantum-classical framework, named QFormer-Brain, which combines transformer-based segmentation with quantum representation learning for automated brain tumor segmentation and classification. To segment the tumor regions, a Shifted Window UNet Transformers (Swin-UNETR) architecture is first used to capture both local anatomical details and global contextual information through hierarchical self-attention. Then, the deep semantic features of the segmented lesions are mapped to the quantum feature mapping module with angle encoding and variational quantum circuits (VQCs), which can obtain richer nonlinear feature representation by quantum superposition and entanglement mechanisms. The obtained quantum embeddings are then combined with features obtained from the transformer and classified by a Quantum Transformer Classifier. The experiments were performed on the publicly available BraTS 2021 data set using an 8-qubit variational quantum circuit, with 1024 measurement shots and readout-error mitigation, via the IBM Qiskit Aer simulator. The proposed framework achieved a Dice Similarity Coefficient (DSC) of 97.1%, Intersection-over-Union (IoU) of 95.0%, classification accuracy of 98.5%, sensitivity of 98.1%, specificity of 99.0%, and F1-score of 98.3%, outperforming U-Net, nnU-Net, ResNet50, Vision Transformer (ViT), and conventional hybrid Convolutional Neural Network (CNN)-based models. These results show that quantum-inspired representation learning can be efficiently integrated into transformer-based models to boost the discriminative feature extraction from complex MRI data.
Furthermore, the physics and multimodality imaging characteristics of tumors, along with high variability in intensity, morphology and anatomical position of the tumor, make the diagnosis of tumors from magnetic resonance imaging (MRI) still quite difficult. In this study, we introduce a hybrid quantum-classical Quantum Convolutional Neural Network (QCNN) that applies Quantum processing in the localized stage of feature extraction rather than later in the classification stage when most current quantum neural networks (CNNs) are used, for automated tumor detection from multiparametric MRI data. The proposed framework makes use of the BraTS 2021 data set, comprising of T1-weighted, post-contrast T1-weighted (T1Gd), T2-weighted and T2-FLAIR images, along with patient-level partitioning, intensity normalization, tumor relevant slice selection, 4×4/8×8 patch generation, dimensionality reduction, quantum angle encoding, trainable variational quantum transformations and Pauli-Z expectation-value measurements. This produced quantum feature maps which were summed across classical layers, and compared to a standard CNN and transfer learning CNN and CNN with a quantum classifier. The proposed QCNN showed excellent performance with 96% accuracy, 93% sensitivity, 94% specificity, 94% precision, 94% F1-score, AUPRC of 0.94, AUROC of 0.96 and the MCC score is 0.82, which is the best among all the architectures considered. The use of architectural analysis revealed to be an option, since 4-6 qubits, 2-3 quantum layers, angle encoding and linear or ring entanglement prove to be adequate. The results of robustness analysis showed that the performance is degrades progressively as the level of quantum noise is increased but still reached a good AUROC (0.80) in the case of strong quantum noise, and was confirmed by an independent external test with a value of 0.85. The results here show trainable quantum convolution to be one potential approach to localized multimodal representation learning for MRI, and present an indication of the impact of quantum noise, finite shot execution, and dataset shift. The study provides a groundwork for the further expansion of research into the use of quantum-enhanced MRI for analysis, in the form of an experimentally controlled experiments design, in larger independent cohorts of patients and with real quantum infrastructure.
Accurate classification of glioma grades from magnetic resonance imaging (MRI) is essential for clinical decision-making in neuro-oncology. Although deep learning performance has been impressive with classical models, they struggle with high-dimensional medical imaging data and generalise poorly beyond their training data, especially in time- and resource-constrained settings. In light of the aforementioned challenges, we propose QuantumMedDx, a hybrid quantum–classical learning framework for classifying gliomas using MRI. The framework combines quantum feature encoding and variational quantum circuits with classical neural inference to improve diagnostic performance. The base model, QImageNet, uses amplitude-based quantum encoding for writing, entanglement-enabled parameterised quantum circuits (EPQCs) as feature extractors, and classical dense layers for classifying HGG and LGG from multimodal MRI slices. We demonstrate the effectiveness of the proposed approach on the BraTS 2021 benchmark dataset using a patient-aware 5-fold cross-validation protocol. Experimental results show that QuantumMedDx achieves accuracies of 94.12%, 93.30%, and 96.42%; F1-scores of 93.30% and 96.42%; and AUCs of 96.42% and 96.42%, respectively, outperforming conventional CNN, DNN, and SVM baselines. Ablation studies provide additional evidence of the performance improvements enabled by quantum Fourier transform and entanglement layers. Such results suggest that quantum–classical learning can efficiently improve feature extraction and discrimination in medical imaging, thus providing a modular and scalable route towards quantum–inspired clinical decision–support systems of the future.
This research presents a new hybrid model that combines the capabilities of a pre-trained ResNet-50 with a Quantum Neural Network (QNN) to enhance the classification of MRI brain images for tumor recognition. Combining conventional deep learning and quantum computing, this technique competes with traditional models regarding accuracy, speed, and computational effectiveness. The ResNet-50 architecture is the foundation for feature extraction, using its demonstrated ability to handle challenging MRI image data. ResNet-50's linear layer weights are converted into angular parameters to take advantage of the potential of quantum computing, allowing the quantum layer to function within a six-angle depth framework. This unique integration allows the model to efficiently execute binary classification and multi-class tumor detection. The hybrid model outperforms conventional models, providing quicker processing speeds and higher classification accuracy, especially when dealing with high-dimensional and noisy data. The model optimizes 512-dimensional data using four qubits, allowing for improved feature representation and better insights into complicated medical imaging patterns. The quantum layer's resistance to noise enhances the model's accuracy, establishing a new standard for medical diagnostic tools. This novel integration of classical and quantum approaches offers a significant advance in MRI-based tumor identification, providing higher performance and opening the path for next-generation medical imaging systems.
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.