Journal of Soft Computing and Data Mining

Enhancing Diagnostic Accuracy for Breast Cancer Using Classical-Quantum Hybrid and Transfer Learning Technique

Basheer Riskhan, Roua Alimam, Bakari Salim Mahaba, Dua-e Uswa, Mehdi Gheisari, Siva Raja Sindiramutty

Published Dec 18, 2025• 2 citations

Abstract

The need to have rapid technological solutions is becoming more evident as the information world digitizes and the amount of data around us grows.It is argued that the future of computational systems will be quantum computing, which will be faster and more capable of solving several issues that cannot be solved with current computers.The aim of the current research is to examine the contributions made by quantum transfer learning models in enhancing the detection of breast cancer.Although both classical and deep learning approaches have proved to be effective, they continue to face serious challenges in handling high-dimensional and complex medical data.Quantum computing can be a feasible solution to such complexity.This study presents a hybrid model, which combines a classical pre-trained deep learning model ( ResNet50) with a range of variational quantum circuits-simple, entangled, and more complex.The main goal is to find the best model set up with regard to predictive power and computation time.It has been found that a hybrid model with an entangled variational circuit has an accuracy of 98.46, a precision of 100, and an F1-score of 97.3, which means a better result compared to the standard transfer learning model, which had an accuracy of 94.6, a precision of 97, and an F1-score of 90.4.These results improve upon recent quantum transfer learning studies, such as Azevedo et al. (2022) with 84% accuracy, and align closely with state-of-the-art quantumoptimized models reporting up to 99.3% accuracy, highlighting the effectiveness of our entangled variational approach on ultrasound images.Meanwhile, the traditional transfer learning model was the best in computational resource utilization.

DOI: 10.30880/jscdm.2025.06.02.004

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, 20247 citations

Quantum Transfer Learning for Breast Cancer Detection

Alok Kumar Srivastava, Shadab Hussain, Soinik Ghosh

The paper applies quantum transfer learning for breast cancer detection by working on a dataset comprising 10,000 mammographic images of different demographics. With the assistance of balanced distribution between cases with and without cancer, the proposed quantum model succeeded in making improvements to great heights compared to CNN in the accuracy of diagnostics, sensitivity, and specificity. The model revealed high robustness, minimized false positive and false negative rates, and increased precision, as shown by AUC scores. The evidence here points to quantum computation as the future for improved early detection of breast cancers, hence timely diagnosis leading to better patient outcomes. The study also had apparent ethical and data protection aspects, where anonymized data is used and safe storage to ensure that information about patients is not shared. Although promising, the results must be validated on real-world clinical data sets and across multiple imaging modalities before confirming clinical utility. This work represents the transformative role quantum transfer learning could play in advancing medical imaging technology and diagnostic capabilities.

International Conference on Communication, Security and Artificial Intelligence (ICCSAI)Apr 4, 20251 citation

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, 20250 citations

QUANTUM NEURAL NETWORK FOR BREAST CANCER DETECTION

KANUMURI PUJITHA, CHELIKANI YASASWINI, JAKKA ROSHINI +2 more

Breast cancer is one of the most prevalent and life-threatening diseases affecting women worldwide, and early detection plays a crucial role in improving survival rates and treatment outcomes.Conventional diagnostic methods such as mammography, ultrasound imaging, and histopathological analysis rely heavily on expert interpretation and classical machine learning techniques.Although classical deep learning models, especially Convolutional Neural Networks (CNNs), have demonstrated impressive performance in medical image analysis, they face inherent limitations related to computational complexity, scalability, and the curse of dimensionality when handling large, high-resolution datasets.With the rapid advancement of quantum computing, Quantum Machine Learning (QML) has emerged as a promising paradigm capable of addressing these challenges by leveraging quantum phenomena such as superposition and entanglement.This research explores the application of Quantum Convolutional Neural Networks (Quantum CNNs or QCNNs) for breast cancer detection, aiming to enhance classification accuracy while reducing computational overhead.The proposed approach integrates quantum circuits with classical preprocessing techniques to extract discriminative features from breast cancer datasets, such as mammographic or histopathological images.By encoding image features into quantum states and performing convolution operations through parameterized quantum circuits, the Quantum CNN model is designed to learn complex patterns more efficiently than classical counterparts.The study evaluates the effectiveness of Quantum CNNs in distinguishing between benign and malignant breast tumors and compares its performance with traditional CNN models.The findings highlight the potential of Quantum CNNs to revolutionize medical image analysis by offering faster convergence, improved generalization, and robustness against noise.This research contributes to the growing field of quantumassisted healthcare systems and demonstrates how quantum computing can be harnessed to address critical challenges in breast cancer diagnosis.

International journal of engineering science and advanced technology.Apr 1, 20260 citations

A Novel Hybrid CNN–Quantum Neural Network Framework with Quantum Acceleration and Error Correction for High-Precision Breast Cancer Classification on AI Edge Devices

Senthilkumar Vijayakumar, Shaunak Pai Kane, Selvavaani Senthilkumar +4 more

Breast cancer remains a critical global health challenge, underscoring the need for early and precise diagnostic methodologies. This paper proposes a novel hybrid deep learning framework that integrates Quantum Neural Networks (QNNs) with the ResNet152 architecture and Transfer Learning to enhance breast cancer classification from medical images. Leveraging the feature extraction power of a pre-trained ResNet152 model, the system encodes refined feature representations into a parameterized quantum circuit utilizing Hadamard, CNOT, and Ry gates. Quantum error correction strategies such as Shor’s Code and surface code are incorporated to preserve quantum state fidelity and reduce decoherence-induced errors, thereby enhancing model robustness. Furthermore, quantum transfer learning accelerates training convergence and enriches pattern recognition capability in high-dimensional medical data. The proposed hybrid model achieves a classification accuracy of 97% and a real-time inference rate of 0.032 frames per second when deployed on an AI edge device, validating its efficacy for point-of-care diagnostics. This study underscores the transformative potential of synergizing quantum computing, edge AI, and deep learning to deliver scalable, interpretable, and high-precision diagnostic tools for clinical applications. The promising results open new avenues for integrating quantum technologies into conventional neural architectures to address the challenges of medical imaging and diagnostic intelligence.

IEEE World AI IoT Congress (AIIoT)May 28, 20250 citations

Comparing Classical and Quantum Machine Learning Models for Breast Cancer Classification on the WDBC Dataset

Jovana Gluhovic

Breast cancer is a major health concern, and early detection can make a great difference in treatment and survival rates for breast cancer patients. Machine learning methods have noticeably improved prediction accuracy on high-dimensional medical datasets and have become widely used tools in medical diagnostics. The transition to a quantum computational framework has opened new directions in machine learning research. By using qubits instead of classical bits, quantum models may provide new ways to represent and process complex medical data. In medical diagnostics, this has led to a growing interest in whether quantum approaches can improve classification performance more effectively than classical methods. The purpose of this paper is to compare classical and quantum machine learning models on the task of breast cancer classification and to determine whether quantum models can achieve higher accuracy and faster prediction on a selected dataset. Alongside the main simulator-based experiment, a smaller experiment was performed on a real IBM quantum computer to demonstrate the practical execution of the same task under current hardware constraints. In the practical part of the study, the Wisconsin Diagnostic Breast Cancer (WDBC) dataset was used. This dataset consists of 569 samples with 30 numerical features extracted from digitized fine needle aspirate images and provides a reliable basis for evaluating model performance. A comparative analysis was conducted between classical and quantum machine learning models, including a support vector machine (SVM), an artificial neural network (ANN), a quantum support vector machine (QSVM), and a hybrid quantum-classical neural network (QNN). In the simulator-based experiment, both SVM and ANN achieved an accuracy of 0.956 with an F1-score of 0.965 on the test set, while QSVM reached an accuracy of 0.807 with an F1-score of 0.866 and the Hybrid QNN achieved 0.623 accuracy with an F1-score of 0.677. These quantum and hybrid models also required substantially longer training times than the classical baselines. A small hardware experiment on an IBM quantum device further illustrates both the practical feasibility and the current limitations of executing this classification task on noisy intermediate-scale quantum hardware.

American Journal of Computer Science and TechnologyAug 6, 20260 citations