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

Journal of The Institution of Engineers (India) Series B

Quantum-Based Deep Learning Approach for Brain Tumour MRI Detection

M. Diviya, M. Subramanian, P. Divya, R Utthirakumari

Published Aug 5, 2026• 1 citation
Publisher
DOI
10.1007/s40031-026-01368-8

Related papers

Brain MRI tumour classification using quantum classical convolutional neural net architecture

Rudrajit Choudhuri, Amiya Halder

Neural Computing and Applications•Oct 22, 2022•42 citations

A Quantum Enhanced Deep Learning Approach for Brain Tumor MRI Classification: Effects of Qubit Count and Quantum Depth on Model Performance

Hesham Younis, Zeinab E. Attia, Hesham Ahmed Hefny

Journal of Intelligent Computing and Data Science•Apr 1, 2026•0 citations

Hybrid Quantum-Classical Approach for MRI-Based Brain Tumor Detection and Classification

Harra Nayak, Mahek Trevadia, Reet Dengle +1 more

Control Instrumentation System Conference (CISCON)•Aug 1, 2025•0 citations

Quantum deep learning for brain informatics

Nabil Anan Orka

•Jan 23, 2026•0 citations

Enhanced brain tumour prediction using quantum: a hybrid deep learning approach

K. Valarmathi, N. Aniruddhan, S H V Harsha Vardhan +1 more

Brain tumours are very serious concerns in the health field; they should be diagnosed properly and at the right time to ensure treatment efficacy. While deep learning architectures like ResNet have shown remarkable success in medical imaging, they have their own set of disadvantages, like computational complexity, scalability, and difficulty in processing very high-dimensional medical data. To overcome these hurdles, a hybrid approach has been proposed, combining ResNet with quantum transfer learning, leveraging the embedding to achieve good performance with higher efficiency in the use of quantum computing technology. In this framework, ResNet extracts valuable features from MRI scans, while quantum circuits optimise the classification process, thereby improving performance and generalisation. The quantum component of the proposed model is implemented using the PennyLane framework, enabling seamless integration of quantum circuits with classical deep learning architectures through a hybrid quantum-classical learning paradigm. Extensive experiments show that our hybrid quantum/classical model outperforms all conventional deep learning approaches, achieving higher diagnostic accuracy while minimising computational overhead. Compared to a traditional CNN (a series of neurons processing unstructured data for machine-understandable form) model, which achieves only 82% accuracy, our hybrid model significantly outperforms it with 95% accuracy, representing a 14% increase in classification performance. Results indicate that quantum computing can transform radiology and medical imaging, providing the tools to advance human health and create a future of fast, precise, and scalable diagnostic equipment. This can be considered a huge step forward toward the use of quantum computing in the medical field; it opens another avenue for advanced medical diagnostics and better patient outcomes.

Scientific Reports•Jun 25, 2026•1 citation

MRI Brain Tumor Detection Using Quantum Mechanics and Neural Networks

Warqaa Hashim

Quantum computing provides a powerful solution by using quantum parallelism and state rotations to perform the analysis at a far superior rate. Key contributions of this study include: proposing a multi-layer Quantum Neural Networks (QNN) architecture where classical weights are replaced with quantum gates to achieve scalability learning; showing possible use of quantum entanglement in QNN to find features as edges of the tumour; and comparing the QNN model to conventional and semi-quantum models to prove the effectiveness of the quantum model. The methodology involves Magnetic Resonance Imaging (MRI) brain tumour datasets and normalizes and augments the datasets to achieve good results. Qubit utilization is optimized through amplitude and basis encoding, while QNN layers employ rotation and entanglement gates. The model is trained with simulators available in the Qiskit environment and is tested on quantum devices (D-Wave). The QNN obtained an accuracy of 97.2% for biometric data; moreover, it had 96.5% precision and 98.1% recall, and an AUC-ROC score of 0.98 was higher than the classical and hybrid models. However, problems with quantum hardware and data encoding remain understudied and form the basis of possible subsequent experimentation in the healthcare area.

NTU Journal of Engineering and Technology•Sep 28, 2025•0 citations
Brain tumours are very serious concerns in the health field; they should be diagnosed properly and at the right time to ensure treatment efficacy. While deep learning architectures like ResNet have shown remarkable success in medical imaging, they have their own set of disadvantages, like computational complexity, scalability, and difficulty in processing very high-dimensional medical data. To overcome these hurdles, a hybrid approach has been proposed, combining ResNet with quantum transfer learning, leveraging the embedding to achieve good performance with higher efficiency in the use of quantum computing technology. In this framework, ResNet extracts valuable features from MRI scans, while quantum circuits optimise the classification process, thereby improving performance and generalisation. The quantum component of the proposed model is implemented using the PennyLane framework, enabling seamless integration of quantum circuits with classical deep learning architectures through a hybrid quantum-classical learning paradigm. Extensive experiments show that our hybrid quantum/classical model outperforms all conventional deep learning approaches, achieving higher diagnostic accuracy while minimising computational overhead. Compared to a traditional CNN (a series of neurons processing unstructured data for machine-understandable form) model, which achieves only 82% accuracy, our hybrid model significantly outperforms it with 95% accuracy, representing a 14% increase in classification performance. Results indicate that quantum computing can transform radiology and medical imaging, providing the tools to advance human health and create a future of fast, precise, and scalable diagnostic equipment. This can be considered a huge step forward toward the use of quantum computing in the medical field; it opens another avenue for advanced medical diagnostics and better patient outcomes.
Quantum computing provides a powerful solution by using quantum parallelism and state rotations to perform the analysis at a far superior rate. Key contributions of this study include: proposing a multi-layer Quantum Neural Networks (QNN) architecture where classical weights are replaced with quantum gates to achieve scalability learning; showing possible use of quantum entanglement in QNN to find features as edges of the tumour; and comparing the QNN model to conventional and semi-quantum models to prove the effectiveness of the quantum model. The methodology involves Magnetic Resonance Imaging (MRI) brain tumour datasets and normalizes and augments the datasets to achieve good results. Qubit utilization is optimized through amplitude and basis encoding, while QNN layers employ rotation and entanglement gates. The model is trained with simulators available in the Qiskit environment and is tested on quantum devices (D-Wave). The QNN obtained an accuracy of 97.2% for biometric data; moreover, it had 96.5% precision and 98.1% recall, and an AUC-ROC score of 0.98 was higher than the classical and hybrid models. However, problems with quantum hardware and data encoding remain understudied and form the basis of possible subsequent experimentation in the healthcare area.