Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Conference on Information, Intelligence, Systems & Applications (IISA)

Quantum Pre-Processing of MRI for use in Brain Cancer Classification

Carson Wolff, Niraj Anil Babar, Glen S. Uehara, Andreas Spanias

Published Jul 1, 2026• 0 citations
Publisher

Abstract

Brain tumors can be fatal to humans, thus early diagnosis is important to begin treatment as soon as possible. This diagnosis is typically done through analysis of Magnetic Resonance Images (MRI). Recently, the analysis of MRI has engaged AI and Deep Learning algorithms, which have shown promise in MRI classification. Classical computing pre-processing has high computational cost, bottlenecks, and generally low efficiency. We propose a Quantum Feature Extraction image pre-processing pipeline for improved performance and efficiency. We develop an MRI pre-processing and feature extraction process and we engage machine learning for classification. We show that classifiers are able to reach key accuracy benchmarks significantly faster when our pre-processing pipeline is employed.

DOI
10.1109/iisa71656.2026.11705538

Related papers

Quantum-Powered Vision Network for Intelligent Brain Analysis

Mayuri Fegade, Vedant Chaudhari, Tejal Bodake +2 more

Brain tumor detection from magnetic resonance imaging (MRI) plays a vital role in early diagnosis and effective treatment planning. However, conventional manual analysis and classical deep learning models often face challenges related to high computational complexity, long training time, and limited scalability when handling high-dimensional medical image data. This project presents a Quantum-Powered Vision Network for Intelligent Brain Analysis, which integrates classical image pre-processing with quantum-assisted machine learning techniques to improve classification performance. The proposed system follows a hybrid quantum–classical workflow that includes MRI image preprocessing, quantum data encoding using unary amplitude encoding, and quantum-assisted learning layers for feature extraction and classification. The model is designed to classify brain MRI images and identify tumor presence and levels efficiently. A structured methodology is implemented, and the working of the system is demonstrated through step-by-step output results. Experimental observations show that the proposed approach achieves reliable classification behavior while maintaining com-putational efficiency compared to purely classical methods. The results highlight the feasibility and potential of quantum-assisted learning techniques in medical image analysis. This project demonstrates that hybrid quantum-classical models can serve as a promising direction for future intelligent healthcare and diagnostic systems.

Multidisciplinary Journal of Research in Engineering and Technology•Jun 15, 2026•0 citations

Unsupervised quantum machine learning and computer vision transformer methods for brain tumor classification

Dylan Couch

The early detection and diagnosis of brain tumors is linked with improved patient quality of life, treatment, and health outcomes.Identifying the presence of brain tumors is typically done using magnetic resonance imaging (MRI) scans.Creating a computerized system to determine whether a patient has a brain tumor, and what kind, remains challenging due to the complexity and visual similarity of brain MRI data.This challenge motivates the creation of methods and systems that can classify patient MRI data automatically without requiring supervised training.We propose a quantum machine learning and computer vision transformer (ViT) framework for unsupervised brain MRI classification.The Quantum Transformer for Clustering MRI (QTCM) framework combines classical computing methods with a quantum ViT to better identify and classify brain tumors in MRI scan data.We demonstrate that a quantum transformer-based system can improve classification rates when compared to similar classical systems.This dissertation also evaluates the role of clustering strategy selection in brain MRI tumor classification.In this study, we introduce DQC1-projected, a method inspired by deterministic quantum computation with one qubit, and compare its performance against several classical clustering algorithms across two public brain MRI benchmarks.The results show that DQC1-projected achieves the strongest performance among the evaluated methods.

•Jan 1, 2026•0 citations

A hybrid quantum-classical framework for MRI-based deep brain tumor segmentation and classification

Naglaa F. Soliman, Prashant Kumar Shukla, Mohamed M. Hassan +4 more

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.

Scientific Reports•Jul 3, 2026•1 citation

Novel Quantum Machine Learning Framework for Brain Tumor Classification from MRI Images

Bharani Dharan K P, Elangovan N, Deepa V. Jose +2 more

This research work discusses three methods for detecting brain tumors using magnetic resonance imaging (MRI) - a pre-trained convolutional neural network (CNN) baseline, a pure quantum machine learning (QML) classifier that utilizes amplitude embedding and variational quantum circuits, and a hybrid of QML with CNN backbone model with a parameterised quantum circuit (PQC). All models were trained and tested on the four-class brain tumor MRI dataset (glioma, meningioma, pituitary, and no tumor) using the same preprocessing and evaluation protocols. The typical classical convolutional neural network (CNN) baseline achieved a test accuracy of 86.1%, with an F1 score of 0.8512. By comparison, the pure QML model provided a rather poor model, achieving limited accuracy of 44.7% and F1 of 0.4320, largely due to issues with shallow variational circuits and amplitude encoding on higher-dimensional data. The hybrid CNN-QML model provided the best results, achieving a test accuracy of 94.9% and an F1 of 0.9469, surpassing the typical classical baseline. These results indicate while standalone QML models are currently limited by the expressivity of quantum circuits and the scalability of their dimensionality, hybrid quantum-classical models can increase medical image classification performance, even when starting from a strong classical baseline.

IEEE Conference on Information and Communication Technology (CICT)•Dec 19, 2025•2 citations

A Hybrid Quantum-Classical Deep Learning Framework for Efficient Brain Tumor Classification Using MRI Images

Sayali Nale, Tejashree Jena, Anita Atiwadkar

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.

International Journal of Innovative Research in Technology•Sep 15, 2026•0 citations

A Hybrid Classical-Quantum Model for Enhanced MRI-Based Brain Tumor Classification Using Transfer Learning and Quantum Neural Networks

Alok Kumar Srivastava, Shiru Sharma, Shadab Hussain +2 more

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.

International Conference on Communication, Security and Artificial Intelligence (ICCSAI)•Apr 4, 2025•11 citations
Brain tumors can be fatal to humans, thus early diagnosis is important to begin treatment as soon as possible. This diagnosis is typically done through analysis of Magnetic Resonance Images (MRI). Recently, the analysis of MRI has engaged AI and Deep Learning algorithms, which have shown promise in MRI classification. Classical computing pre-processing has high computational cost, bottlenecks, and generally low efficiency. We propose a Quantum Feature Extraction image pre-processing pipeline for improved performance and efficiency. We develop an MRI pre-processing and feature extraction process and we engage machine learning for classification. We show that classifiers are able to reach key accuracy benchmarks significantly faster when our pre-processing pipeline is employed.
Brain tumor detection from magnetic resonance imaging (MRI) plays a vital role in early diagnosis and effective treatment planning. However, conventional manual analysis and classical deep learning models often face challenges related to high computational complexity, long training time, and limited scalability when handling high-dimensional medical image data. This project presents a Quantum-Powered Vision Network for Intelligent Brain Analysis, which integrates classical image pre-processing with quantum-assisted machine learning techniques to improve classification performance. The proposed system follows a hybrid quantum–classical workflow that includes MRI image preprocessing, quantum data encoding using unary amplitude encoding, and quantum-assisted learning layers for feature extraction and classification. The model is designed to classify brain MRI images and identify tumor presence and levels efficiently. A structured methodology is implemented, and the working of the system is demonstrated through step-by-step output results. Experimental observations show that the proposed approach achieves reliable classification behavior while maintaining com-putational efficiency compared to purely classical methods. The results highlight the feasibility and potential of quantum-assisted learning techniques in medical image analysis. This project demonstrates that hybrid quantum-classical models can serve as a promising direction for future intelligent healthcare and diagnostic systems.
The early detection and diagnosis of brain tumors is linked with improved patient quality of life, treatment, and health outcomes.Identifying the presence of brain tumors is typically done using magnetic resonance imaging (MRI) scans.Creating a computerized system to determine whether a patient has a brain tumor, and what kind, remains challenging due to the complexity and visual similarity of brain MRI data.This challenge motivates the creation of methods and systems that can classify patient MRI data automatically without requiring supervised training.We propose a quantum machine learning and computer vision transformer (ViT) framework for unsupervised brain MRI classification.The Quantum Transformer for Clustering MRI (QTCM) framework combines classical computing methods with a quantum ViT to better identify and classify brain tumors in MRI scan data.We demonstrate that a quantum transformer-based system can improve classification rates when compared to similar classical systems.This dissertation also evaluates the role of clustering strategy selection in brain MRI tumor classification.In this study, we introduce DQC1-projected, a method inspired by deterministic quantum computation with one qubit, and compare its performance against several classical clustering algorithms across two public brain MRI benchmarks.The results show that DQC1-projected achieves the strongest performance among the evaluated methods.
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.
This research work discusses three methods for detecting brain tumors using magnetic resonance imaging (MRI) - a pre-trained convolutional neural network (CNN) baseline, a pure quantum machine learning (QML) classifier that utilizes amplitude embedding and variational quantum circuits, and a hybrid of QML with CNN backbone model with a parameterised quantum circuit (PQC). All models were trained and tested on the four-class brain tumor MRI dataset (glioma, meningioma, pituitary, and no tumor) using the same preprocessing and evaluation protocols. The typical classical convolutional neural network (CNN) baseline achieved a test accuracy of 86.1%, with an F1 score of 0.8512. By comparison, the pure QML model provided a rather poor model, achieving limited accuracy of 44.7% and F1 of 0.4320, largely due to issues with shallow variational circuits and amplitude encoding on higher-dimensional data. The hybrid CNN-QML model provided the best results, achieving a test accuracy of 94.9% and an F1 of 0.9469, surpassing the typical classical baseline. These results indicate while standalone QML models are currently limited by the expressivity of quantum circuits and the scalability of their dimensionality, hybrid quantum-classical models can increase medical image classification performance, even when starting from a strong classical baseline.
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.
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.