Leukemia Detection using Quantum Machine Learning

Abstract

Leukemia is a critical blood-related health problem for which early diagnosis is a key aspect in the survival of the patient. Computer-assisted diagnosis using microscopic white blood cell images has received significant attention because the conventional manual approach is too time-consuming. In this paper, a hybrid Quantum Machine Learning-based approach for the classification of leukemia is presented. In the first place, the microscopic white blood cell images are preprocessed using resizing, normalization, and denoising techniques. Then, Principal Component Analysis is applied for dimensionality reduction. The reduced feature vectors are then mapped onto a quantum system using a Variational Quantum Circuit-based Quantum Neural Network.The presented method also validates the possibility of quantum-assisted learning in biomedical image diagnosis. Additionally, it offers a glimpse of how well a hybrid model would perform under Noisy Intermediate-Scale Quantum (NISQ) conditions. The experimental results are achieved using standard performance parameters such as accuracy, precision, recall, and F1-score. This method indicates how a hybrid model of QML can perform in a computationally simpler manner. This paper also indicates the potential of a quantum-classical system in future clinical applications for leukemia screening and diagnosis.

Introduction

The text presents a hybrid quantum–classical machine learning approach for leukemia detection using microscopic white blood cell (WBC) images.

It begins by explaining that leukemia is a serious blood disorder traditionally diagnosed through manual microscopic examination, which is slow and requires expert pathologists. To improve this, the study proposes an automated system using Quantum Machine Learning (QML) combined with classical preprocessing techniques.

The proposed method uses a hybrid pipeline: WBC images are first preprocessed (resizing, noise removal, normalization, contrast enhancement), then transformed into feature vectors. Since quantum systems cannot handle high-dimensional data directly, PCA (Principal Component Analysis) is used to reduce feature size. The reduced features are then encoded into quantum states and classified using two models: a Quantum Neural Network (QNN) based on variational quantum circuits and a Quantum Support Vector Machine (QSVM) using quantum kernels.

The study also highlights that classical deep learning methods like CNNs perform well but require large datasets and high computation. In contrast, quantum approaches can reduce complexity and improve efficiency, especially for small or medium datasets. The literature review shows growing interest in hybrid quantum–classical models for medical imaging, but also identifies challenges like noise, hardware limitations, and lack of scalable systems.

The dataset used is the ALL (Acute Lymphoblastic Leukemia) microscopic image dataset, containing labeled normal and leukemia WBC images. It undergoes preprocessing and augmentation before training.

Finally, the system is implemented using Python with tools like OpenCV, scikit-learn, Qiskit, and PennyLane, and deployed using Streamlit for a web-based interface.

Conclusion

In this work, a new QML-based approach is developed to detect leukemia through microscopic images of white blood cells. As shown in the above figure, the approach consists of image processing, feature extraction, reduction through PCA, and finally the use of quantum-classical models to classify the data. In the tested models, the best model is the QNN, which outperformed the QSVM in terms of accuracy, precision, recall, and F1-score The system includes a visualization interface that provides real-time predictions with confidence scores, demonstrating practical applicability for preliminary clinical screening. The modular workflow ensures that each stage can be independently optimized, making it adaptable for future enhancements in quantum computing and medical imaging.

References

[1] M. F. Shahriyar and G. Tanbhir, “Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine,” Proceedings of IEEE International Conference on Next Generation Intelligent Systems (NCIM), 2025, pp. 1-6, doi:10.1109/NCIM.2025.11160179. [2] C. Long, S. Wang, and L. Zhu, “Hybrid Quantum-Classical Convolutional Neural Networks for Medical Image Classification,” Scientific Reports, vol. 15, article 31780, 2025, doi:10.1038/s41598-025-13417-1. [3] M. Priyadharshini, J. Mathew, and R. S. Kumar, “QBrainNet: Enhanced Quantum Intelligence for Medical Diagnostics,” Frontiers in Medicine, 2025, doi:10.3389/fmed.2025.1677234. [4] Idzikowski, R. “A Survey on Quantum Machine Learning Applications in Medical Imaging.” Applied Sciences, vol. 16, no. 3, 2026, doi:10.3390/app16031630. [5] R.S. Gupta, A. Aggarwal & P. Verma, “A systematic review of quantum machine learning for digital healthcare,” npj Digital Medicine, 2025, doi:10.1038/s41746-025-01597-z. [6] V. S. Naresh and K. Srinivas, \"Benchmarking QSVM and QNN in Hybrid Quantum-Assisted Healthcare,\" Computers in Biology and Medicine, 2025, doi:10.1016/j.compbiomed. 2025.1024583. [7] S. Prajapat, “Combination of Quantum Computing & Deep Learning for Medical Image Analysis: Hybrid Quantum CNN (QCNN) &ResNet,” Mathematics, vol. 13, no. 19, 2025, doi: 10.3390/math13193148. [8] Y. Chen, \"An Innovative Quantum-Classical Image Classification System Based on Variational Quantum Algorithms,\" Quantum Information Processing, 2024, doi:10.1007/s11128-024-04566-9. [9] A. Hafeez, A. Munir, and H. Ullah, \"H-QNN: Hybrid Quantum-Classical Neural Network for Image Classification,\" AI, vol. 5, no. 3, 2024. doi:10.3390/ai5030070. [10] A. Senokosov, D. Abramov, and N. Belov, \"Quantum Machine Learning for Image Classification,\" Quantum Machine Intelligence, 2024. [11] W. Feng, \"A Hybrid Quantum and Classical Computing Technique for Improved Analysis of Brain Images,\" ACM Transactions on Computing for Healthcare, 2025, doi:10.1145/3788211. [12] Y. Li, X. Cheng, and H. Zhou, \"A Distributed Hybrid Quantum Convolutional Neural Network for Medical Images,\" arXiv preprint, 2025, arXiv:2501.06225. [13] Md. Farhan Shahriyar and G. Tanbhir, \"Advancements and Challenges in Quantum Machine Learning for Medical Image Classification: A Comprehensive Review,\" arXiv preprint, 2025, arXiv:2504.13910. [14] L. Wei, J. Zhou, and F. Liu, \"Quantum Machine Learning in Medical Image Analysis: A Survey,\" Scientific Literature, 2026. [15] R. S. Gupta, L. K. Singh, and A. S. Khatri, “Systematic Review of Quantum Machine Learning Algorithms in Healthcare,” Medical Systems, 2025, doi:10.1007/s10916-025-01597-z. [16] D. Sudha and R. Kumar, “Enhanced Deep Learning and Quantum Variational Classifier Frameworks,” Computers in Medicine and Science, 2025, doi:10.1016/j.smhl.2025.01.6508. [17] F. Díaz-Padilla, J. González, and M. Torres, “Variational Quantum Classifiers for Leukemia Detection Using PCA Medical Datasets,” IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 1, 2024, doi:10.1109/JBHI.2023.3245679. [18] M. Schuld, A. Narayanan, and E. Harrow, “Quantum Learning Models for Classification Problems,” npj Quantum Information, vol. 8, 2024, doi:10.1038/s41534-024-00573-2. [19] P. K. Dutta, S. Bhattacharya, and N. Zaman, “Quantum-Inspired Feature Selection Techniques for Biomedical Data,” IEEE Access, vol. 13, 2025, doi:10.1109/ACCESS.2025.3054492. [20] T. Nguyen and Y. Chen, “Quantum Convolutional Neural Networks for Hematological Cancer Detection,” Quantum Machine Intelligence, vol. 5, no. 1, 2023, doi:10.1007/s42484-023-00045-y. [21] A. Mishra, R. Gupta, and S. Verma, “Quantum Neural Networks for Cancer Diagnosis Using Medical Imaging Data,” Quantum Machine Intelligence, vol. 5, no. 2, 2023, doi:10.1007/s42484-023-00063-w. [22] M. P. Rana, S. K. Singh, and R. K. Tiwari, “Deep Learning Models for Leukemia Detection: A Review,” IEEE Reviews in Biomedical Engineering, 2024, doi:10.1109/RBME.2024.3197856. [23] C. Zhao, H. Xu, and F. Wei, “Medical Image Classification Using Hybrid Deep Learning and Quantum Kernels,” IEEE Transactions on Neural Networks and Learning Systems, 2025, doi:10.1109/TNNLS.2025.3156893. [24] A. Yadav, D. Sharma, and P. Kumar, “Quantum Kernel Methods for Medical Image Feature Mapping,” IEEE Transactions on Medical Imaging, 2025, doi:10.1109/TMI.2025.3127965. [25] S. Roy and P. Das, “Comparative Evaluation of Quantum and Classical Learning Models for Biomedical Data Classification,” IEEE Transactions on Emerging Topics in Computational Intelligence, 2025, doi:10.1109/TETCI.2025.3174298.

Copyright

Copyright © 2026 Mrs. M. Aruna, Boya Ravi Teja, Burri Manideep Reddy, Lekkala Abhilash Reddy. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.