Magnetic resonance imaging (MRI) brain tumor segmentation is critical for diagnosis and treatment planning, but remains challenging due to blurry boundaries and class imbalance. Although deep learning models like U-Net have set benchmarks, they often face limitations in modeling complex feature interactions and require substantial computational resources. This paper introduces Quantum U-Net, a novel hybrid quantum-classical architecture that augments the classical U-Net by replacing its final convolutional layer with a tailored quantum convolutional layer. This layer utilizes amplitude encoding to map 64-channel feature maps onto the state of 6 qubits, followed by a parameterized strongly entangling layer to exploit quantum superposition and entanglement for enhanced multi-channel feature fusion. We employ a two-stage training strategy: pre-training a classical U-Net for 50 epochs, freezing its parameters, and then fine-tuning the integrated quantum layer for 30 epochs. Evaluated on the Brain Tumor Segmentation dataset, our hybrid model achieves a Dice coefficient of 0.806, a significant 6.2% relative improvement over the baseline classical U-Net (Dice: 0.759). This work validates the potential of quantum-enhanced models to improve performance in medical image segmentation and provides a practical blueprint for hybrid quantum-classical architectures in resource-intensive domains.
Magnetic resonance imaging (MRI) brain tumor segmentation is critical for diagnosis and treatment planning, but remains challenging due to blurry boundaries and class imbalance. Although deep learning models like U-Net have set benchmarks, they often face limitations in modeling complex feature interactions and require substantial computational resources. This paper introduces Quantum U-Net, a novel hybrid quantum-classical architecture that augments the classical U-Net by replacing its final convolutional layer with a tailored quantum convolutional layer. This layer utilizes amplitude encoding to map 64-channel feature maps onto the state of 6 qubits, followed by a parameterized strongly entangling layer to exploit quantum superposition and entanglement for enhanced multi-channel feature fusion. We employ a two-stage training strategy: pre-training a classical U-Net for 50 epochs, freezing its parameters, and then fine-tuning the integrated quantum layer for 30 epochs. Evaluated on the Brain Tumor Segmentation dataset, our hybrid model achieves a Dice coefficient of 0.806, a significant 6.2% relative improvement over the baseline classical U-Net (Dice: 0.759). This work validates the potential of quantum-enhanced models to improve performance in medical image segmentation and provides a practical blueprint for hybrid quantum-classical architectures in resource-intensive domains.
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.
Abstract Precise segmentation of brain tumors from multi-modal magnetic resonance imaging (MRI) scans remains a challenging requirement for clinical diagnosis and treatment planning. This paper introduces a hybrid quantum-classical architecture that places a six-qubit variational quantum circuit (VQC) inside a 3D U-Net encoder-decoder. Rather than replacing the entire bottleneck, the VQC operates as a squeeze-and-excitation style channel attention block: global-average-pooled channel descriptors are angle-encoded into qubits, passed through two Strongly Entangling Layers, and the resulting measurements are applied as multiplicative channel weights. This noisy intermediate-scale quantum (NISQ)-compatible design uses only two layers and 36 parameters, so the quantum overhead per forward pass is confined to a single channel vector. For uncertainty estimation, we combine Monte Carlo Dropout entropy with quantum measurement variance to produce per-voxel confidence maps. Evaluated on Brain Tumor Segmentation 2020 with nine model variants, with test-time augmentation and adaptive thresholding, the proposed architecture reaches a mean Dice of 0.7812, HD95 of 23.87 (necrotic/non-enhancing core), 2.46 (ED), and 10.47 (ET), and an expected calibration error (ECE) of 0.0655—matching the strongest classical baseline on Dice while cutting ECE by roughly 20%. All stable quantum variants outperform their classical counterparts in calibration, confirming that quantum measurement stochasticity provides an additional, complementary uncertainty signal beyond dropout alone.
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.
Brain tumor detection from MRI images is a critical and challenging task in medical diagnostics, where early identification greatly improves treatment outcomes. This paper presents a Hybrid Quantum– Classical Convolutional Neural Network (HQCNN) that integrates the strengths of ResNet-18 and a Variational Quantum Circuit for efficient and accurate tumor classification. The proposed model first employs ResNet-18 as a classical feature extractor, where 17 convolutional layers and pooling operations capture both low-level and high-level spatial features from MRI images. The final fully connected layer of ResNet-18 is replaced by a quantum processing layer implemented using PennyLane. In this layer, the extracted classical features are encoded onto qubits using RY rotation gates, while CNOT gates introduce entanglement between them, forming a VQC with trainable parameters. After quantum computation, Pauli-Z measurements convert the processed quantum states back into classical values, which are passed to a final fully connected layer for binary classification as Tumor or No Tumor. The hybrid integration of classical CNN feature learning with quantum entanglement– based representation enhances model generalization and interpretability. Experimental analysis demonstrates that the proposed HQCNN achieved 94.65% accuracy, outperforming traditional CNN models and confirming the potential of hybrid quantum–classical architectures for reliable and interpretable medical image diagnosis.
Accurate classification of brain tumors from MRI scans is critical for effective treatment planning. This study presents a Hybrid Quantum Convolutional Neural Network (HQCNN) that integrates quantum feature-encoding circuits with depth-wise separable convolutional layers to analyze images from a publicly available brain tumor dataset. Evaluated on this dataset, the HQCNN achieved 99.16% training accuracy and 91.47% validation accuracy, demonstrating robust performance across varied imaging conditions. The quantum layers capture complex, non-linear relationships, while separable convolutions ensure computational efficiency. By reducing both parameter count and circuit depth, the architecture is compatible with near-term quantum hardware and resource-constrained clinical environments. These results establish a foundation for integrating quantum-enhanced models into medical-imaging workflows with minimal changes to existing software platforms. Future work will extend evaluation to multi-center cohorts, assess real-time inference on quantum simulators and hardware, and explore integration with surgical-planning systems.
The problem of classifying brain tumours using magnetic resonance imaging (MRI) is a fundamental one in the field of computeraided diagnosis, since although many commonly employed convolutional neural network (CNN) architectures provide high accuracy they contain a large number of parameters, which has led to a search for more compact network designs. In this paper a hybrid quantum–classical approach is proposed that combines a lightweight CNN feature extractor with a trainable variational quantum circuit (VQC) in order to carry out four-class brain tumour classification. The MRI images are resized to 128 by 128 pixels and then processed by a small three-block CNN that reduces each image to an 8-dimensional feature vector. This vector is put into an 8-qubit quantum register by means of angle embedding and then acted on by a variational circuit composed of strongly entangling layers, by measuring each qubit in the Pauli-Z basis. The quantum features thus obtained are then fed into classical dense layers that categorise the images as glioma, meningioma, pituitary tumour or no tumour. The framework was tested on the Brain Tumor MRI dataset (7,200 images) and compared with a classical CNN baseline that was trained under the same conditions. The hybrid model reached a test accuracy of 76.88%, as compared to 72.31% for the classical baseline an improvement of 4.57 percentage points together with corresponding increases in macro-averaged precision, recall and F1-score. Notably, the hybrid model needed only 72 additional trainable parameters when compared to the classical baseline. The fact that the quantum layer was assessed using a noiseless simulator rather than on actual quantum hardware means that these results should be seen as indicating the feasibility of using compact quantum feature transformations for medical image classification rather than as showing a quantum advantage.