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

IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA)

Classifying Esophageal Cancer Using a Hybrid Quantum-Classical Neural Network

Walid Abdalla Ramdhan Abdalla

Published May 21, 2023• 7 citations
Publisher

Abstract

Early diagnosis of esophageal cancer is critical for increasing the chances of successful treatment and reducing mortality rates. Traditional machine learning models for diagnosing esophageal lesions use previously collected data on specific local features, but these methods can be slow and computationally intensive. As a result, researchers are exploring alternative training platforms for deep learning models, including quantum computers. These computers can take advantage of the properties of quantum entanglement and superposition to solve complex problems.In this study, we propose a Hybrid Quantum-Classical Neural Network using deep learning and supervised learning techniques in a quantum framework. Our focus is on classifying esophageal cancer to demonstrate the network’s capabilities. We trained a network of two qubits to learn the label of a given dataset and optimize circuit parameters to minimize error. The proposed Hybrid Quantum-Classical Neural Network showed high accuracy in classifying esophageal cancer.

DOI
10.1109/mi-sta57575.2023.10169293

Related papers

Enhanced Hybrid Quantum Neural Network for Breast Cancer Detection

Rezuan Chowdhury Rifat, Md. Tahmid Ul Islam Tonmoy, Rifa Tasniya Aziz +1 more

Early diagnosis of breast cancer is crucial to combat its severity. Yet, it’s a challenging endeavor to tackle via traditional diagnosis methods. Several machine learning architectures have already been proposed to assist medical experts in diagnosis. However, architectural complexity hinders the goal of developing a cost-effective diagnosis model. Recently, quantum computing has become popular in machine learning due to its potential computational benefits. Although quantum computing has yet to show any significant improvement in machine learning due to its limited resources and complexity, it may reduce the computational complexity of machine learning in the future. Therefore, we proposed a novel hybrid classical-quantum machine learning model for breast cancer prediction. We collected the BreastMNIST dataset of 780 benign and malignant full-image mammogram samples. Our task is to create an efficient breast cancer-classifying hybrid machine learning model. The proposed method employs a modified ResNet50 as a feature extractor and a Quantum Neural Network to train on that feature and generate desired predictions. A Convolutional layer is applied as a dimension-reduction technique for features generated through ResNet50. Our architecture proved superior to other state-of-the-art hybrid methods, achieving an accuracy of 69% against 67%. An in-depth comparative analysis has been performed that shows the novelty of our research. This study paves the path for hybrid classical-quantum machine learning research in medical image classification.

International Conference on Computer and Information Technology (ICCIT)•Dec 20, 2024•7 citations

Hybrid Quantum-Classical Neural Network for Breast Cancer Detection

M. T. Rahim, Asad Ali, Tanvir Alam

Breast cancer is among the leading causes of mortality among women worldwide, emphasizing the urgent need for accurate and efficient diagnostic tools. Machine learning-based systems have been heavily investigated in this regard. Quantum computing has garnered considerable attention recently; however, few studies have focused on its application to this specific problem. In this work, we integrate quantum computing principles with classical neural networks (QCNNs) to enhance the detection accuracy and computational efficiency of breast cancer diagnosis using the MedMNIST dataset. The hybrid QCNN framework leverages the power of quantum computing to perform complex feature mapping and extraction while reducing the estimated circuit depth of the quantum circuit compared to pure quantum neural network schemes. The proposed model achieved an accuracy of over 84%, a sensitivity of 82%, and a specificity of 86.0%, outperforming the state-of-the-art model developed for the same purpose. The focus of the study is to improve the accuracy and generalizability of classifying complex mammograms, as opposed to current quantum machine learning models, for practical applications in healthcare. We believe this study will support advancing the prospect of AI-enabled medical diagnosis with state-of-the-art quantum computing principles.

International Conference on Data Science and Its Applications (ICoDSA)•Jul 3, 2025•3 citations

Cancer Detection Using Quantum Neural Networks: A Demonstration on a Quantum Computer

Nilima Mishra, Aradh Bisarya, Shubham Kumar +3 more

Artificial intelligence and machine learning paves the way to achieve greater technical feats. In this endeavor to hone these techniques, quantum machine learning is budding to serve as an important tool. Using the techniques of deep learning and supervised learning in the quantum framework, we are able to propose a quantum neural network and showcase its implementation. We consider the application of cancer detection to demonstrate the working of our quantum neural network. Our focus is to train the network of ten qubits in a way so that it can learn the label of the given data set and optimize the circuit parameters to obtain the minimum error. Thus, through the use of many algorithms, we are able to give an idea of how a quantum neural network can function.

arXiv:1911.00504•Nov 1, 2019•10 citations

Quantum Enhanced Convolutional Neural Networks for Breast Cancer Classification

Puppala Charan Naga Deep, Nancharla Akhila, P. Hemanth

Breast cancer is the second most common type of cancer among women worldwide. About 12.9% of women born in the United States today are expected to develop breast cancer during their lifetimes, equating to a chance of 1 in 8. Early and accurate classification of breast cancer is a vital task in medical imaging, as it significantly affects treatment outcomes and patient survival rates. In this work, a hybrid classical-quantum deep learning model that combines quantum transfer learning using ResNet152 with a dressed quantum network employing Hadamard, CNOT, and Ry gates is proposed. This integration takes advantage of the advanced feature extraction capabilities of ResNet152 along with the computational efficiencies and potential advantages offered by quantum networks. Our model achieves a training accuracy of 90.42% and a validation accuracy of 89.90%, demonstrating the effectiveness of incorporating quantum computing into deep learning workflows. In comparison, the classical ResNet152 achieves a training accuracy of 87.23% and validation accuracy of 85.78%, while ResNet50 reaches 86.89% training and 86.76% validation accuracy. These results underscore the potential of hybrid classical-quantum approaches in the advancement of medical diagnostics and highlight a promising direction to improve performance in complex classification tasks.

International Conference on Data Science and Information System (ICDSIS)•May 16, 2025•0 citations

Quantum classical hybrid convolutional neural networks for breast cancer diagnosis

Qiuyu Xiang, Dongfen Li, Zhikang Hu +6 more

The World Health Organization states that early diagnosis is essential to increasing the cure rate for breast cancer, which poses a danger to women's health worldwide. However, the efficacy and cost limitations of conventional diagnostic techniques increase the possibility of misdiagnosis. In this work, we present a quantum hybrid classical convolutional neural network (QCCNN) based breast cancer diagnosis approach with the goal of utilizing quantum computing's high-dimensional data processing power and parallelism to increase diagnosis efficiency and accuracy. When working with large-scale and complicated datasets, classical convolutional neural network (CNN) and other machine learning techniques generally demand a large amount of computational resources and time. Their restricted capacity for generalization makes it challenging to maintain consistent performance across multiple data sets. To address these issues, this paper adds a quantum convolutional layer to the classical convolutional neural network to take advantage of quantum computing to improve learning efficiency and processing speed. Simulation experiments on three breast cancer datasets, GBSG, SEER and WDBC, validate the robustness and generalization of QCCNN and significantly outperform CNN and logistic regression models in classification accuracy. This study not only provides a novel method for breast cancer diagnosis but also achieves a breakthrough in breast cancer diagnosis and promotes the development of medical diagnostic technology.

Scientific Reports•Oct 21, 2024•58 citations

Medical Image Recognition for Breast Cancer Detection Using Hybrid Quantum-Classical Deep Learning

Thomas Samraj Lawrence, Martin Margala, Prąsun Chakrabarti +2 more

One of the common and maybe fatal diseases harming women all around, breast cancer is one such condition. Accurate medical image analysis allows for early detection, which can greatly increase survival rates. Although they encounter challenges such as high computational expenses, poor data efficiency, and suboptimal feature extraction, conventional deep learning methods have produced promising results. By using quantum parallelism and entanglement to enable more quick and more complex computations, quantum computing provides a new approach to overcome these limitations. This paper intends to propose a hybrid quantum-classical deep learning model for the identification of breast cancer areas in mammographic images. The proposed method combines a quantum convolutional neural network (QCNN) with a classical convolutional neural network (CNN) to benefit from the advantages accompanying both classical and quantum processing. The hybrid model processes the mammogram data using classical pre-processing and quantum convolution layers; classification then follows with fully connected layers followed by classical pooling. The results of the MIAS dataset experiments indicate a classification accuracy of 98.4%, which is superior to the operation of traditional CNN and transfer learning-based models.

International Conference on Emerging Engineering Technologies and Applications (IC-EETA)•Nov 6, 2025•0 citations
Early diagnosis of esophageal cancer is critical for increasing the chances of successful treatment and reducing mortality rates. Traditional machine learning models for diagnosing esophageal lesions use previously collected data on specific local features, but these methods can be slow and computationally intensive. As a result, researchers are exploring alternative training platforms for deep learning models, including quantum computers. These computers can take advantage of the properties of quantum entanglement and superposition to solve complex problems.In this study, we propose a Hybrid Quantum-Classical Neural Network using deep learning and supervised learning techniques in a quantum framework. Our focus is on classifying esophageal cancer to demonstrate the network’s capabilities. We trained a network of two qubits to learn the label of a given dataset and optimize circuit parameters to minimize error. The proposed Hybrid Quantum-Classical Neural Network showed high accuracy in classifying esophageal cancer.
Early diagnosis of breast cancer is crucial to combat its severity. Yet, it’s a challenging endeavor to tackle via traditional diagnosis methods. Several machine learning architectures have already been proposed to assist medical experts in diagnosis. However, architectural complexity hinders the goal of developing a cost-effective diagnosis model. Recently, quantum computing has become popular in machine learning due to its potential computational benefits. Although quantum computing has yet to show any significant improvement in machine learning due to its limited resources and complexity, it may reduce the computational complexity of machine learning in the future. Therefore, we proposed a novel hybrid classical-quantum machine learning model for breast cancer prediction. We collected the BreastMNIST dataset of 780 benign and malignant full-image mammogram samples. Our task is to create an efficient breast cancer-classifying hybrid machine learning model. The proposed method employs a modified ResNet50 as a feature extractor and a Quantum Neural Network to train on that feature and generate desired predictions. A Convolutional layer is applied as a dimension-reduction technique for features generated through ResNet50. Our architecture proved superior to other state-of-the-art hybrid methods, achieving an accuracy of 69% against 67%. An in-depth comparative analysis has been performed that shows the novelty of our research. This study paves the path for hybrid classical-quantum machine learning research in medical image classification.
Breast cancer is among the leading causes of mortality among women worldwide, emphasizing the urgent need for accurate and efficient diagnostic tools. Machine learning-based systems have been heavily investigated in this regard. Quantum computing has garnered considerable attention recently; however, few studies have focused on its application to this specific problem. In this work, we integrate quantum computing principles with classical neural networks (QCNNs) to enhance the detection accuracy and computational efficiency of breast cancer diagnosis using the MedMNIST dataset. The hybrid QCNN framework leverages the power of quantum computing to perform complex feature mapping and extraction while reducing the estimated circuit depth of the quantum circuit compared to pure quantum neural network schemes. The proposed model achieved an accuracy of over 84%, a sensitivity of 82%, and a specificity of 86.0%, outperforming the state-of-the-art model developed for the same purpose. The focus of the study is to improve the accuracy and generalizability of classifying complex mammograms, as opposed to current quantum machine learning models, for practical applications in healthcare. We believe this study will support advancing the prospect of AI-enabled medical diagnosis with state-of-the-art quantum computing principles.
Artificial intelligence and machine learning paves the way to achieve greater technical feats. In this endeavor to hone these techniques, quantum machine learning is budding to serve as an important tool. Using the techniques of deep learning and supervised learning in the quantum framework, we are able to propose a quantum neural network and showcase its implementation. We consider the application of cancer detection to demonstrate the working of our quantum neural network. Our focus is to train the network of ten qubits in a way so that it can learn the label of the given data set and optimize the circuit parameters to obtain the minimum error. Thus, through the use of many algorithms, we are able to give an idea of how a quantum neural network can function.
Breast cancer is the second most common type of cancer among women worldwide. About 12.9% of women born in the United States today are expected to develop breast cancer during their lifetimes, equating to a chance of 1 in 8. Early and accurate classification of breast cancer is a vital task in medical imaging, as it significantly affects treatment outcomes and patient survival rates. In this work, a hybrid classical-quantum deep learning model that combines quantum transfer learning using ResNet152 with a dressed quantum network employing Hadamard, CNOT, and Ry gates is proposed. This integration takes advantage of the advanced feature extraction capabilities of ResNet152 along with the computational efficiencies and potential advantages offered by quantum networks. Our model achieves a training accuracy of 90.42% and a validation accuracy of 89.90%, demonstrating the effectiveness of incorporating quantum computing into deep learning workflows. In comparison, the classical ResNet152 achieves a training accuracy of 87.23% and validation accuracy of 85.78%, while ResNet50 reaches 86.89% training and 86.76% validation accuracy. These results underscore the potential of hybrid classical-quantum approaches in the advancement of medical diagnostics and highlight a promising direction to improve performance in complex classification tasks.
The World Health Organization states that early diagnosis is essential to increasing the cure rate for breast cancer, which poses a danger to women's health worldwide. However, the efficacy and cost limitations of conventional diagnostic techniques increase the possibility of misdiagnosis. In this work, we present a quantum hybrid classical convolutional neural network (QCCNN) based breast cancer diagnosis approach with the goal of utilizing quantum computing's high-dimensional data processing power and parallelism to increase diagnosis efficiency and accuracy. When working with large-scale and complicated datasets, classical convolutional neural network (CNN) and other machine learning techniques generally demand a large amount of computational resources and time. Their restricted capacity for generalization makes it challenging to maintain consistent performance across multiple data sets. To address these issues, this paper adds a quantum convolutional layer to the classical convolutional neural network to take advantage of quantum computing to improve learning efficiency and processing speed. Simulation experiments on three breast cancer datasets, GBSG, SEER and WDBC, validate the robustness and generalization of QCCNN and significantly outperform CNN and logistic regression models in classification accuracy. This study not only provides a novel method for breast cancer diagnosis but also achieves a breakthrough in breast cancer diagnosis and promotes the development of medical diagnostic technology.
One of the common and maybe fatal diseases harming women all around, breast cancer is one such condition. Accurate medical image analysis allows for early detection, which can greatly increase survival rates. Although they encounter challenges such as high computational expenses, poor data efficiency, and suboptimal feature extraction, conventional deep learning methods have produced promising results. By using quantum parallelism and entanglement to enable more quick and more complex computations, quantum computing provides a new approach to overcome these limitations. This paper intends to propose a hybrid quantum-classical deep learning model for the identification of breast cancer areas in mammographic images. The proposed method combines a quantum convolutional neural network (QCNN) with a classical convolutional neural network (CNN) to benefit from the advantages accompanying both classical and quantum processing. The hybrid model processes the mammogram data using classical pre-processing and quantum convolution layers; classification then follows with fully connected layers followed by classical pooling. The results of the MIAS dataset experiments indicate a classification accuracy of 98.4%, which is superior to the operation of traditional CNN and transfer learning-based models.