Breast cancer classification with explainable quantum-assisted hybrid learning

Yıl 2025, Cilt: 15 Sayı: 4, 910 - 927, 15.12.2025

İlhan Uysal

https://doi.org/10.17714/gumusfenbil.1715840

https://izlik.org/JA43ZG74JB

Öz

This study proposes an explainable hybrid classification approach for breast cancer diagnosis by integrating classical machine learning algorithms, deep learning architectures, and quantum-assisted models. The analysis was conducted on the Breast Cancer Wisconsin (Diagnostic) dataset, employing classifiers such as Logistic Regression, Random Forest, Extreme Gradient Boosting (XGBoost), TabNet, Variational Quantum Classifier (VQC), and Quantum Kernel Support Vector Classifier (QKSVC). The outputs of these models were combined through a soft voting strategy to construct the final hybrid model. Stratified ten-fold cross-validation demonstrated that the ensemble achieved high performance, with an average AUC of approximately 0.995 and an accuracy level of 0.98. To enhance the transparency of model decisions, explainable artificial intelligence (XAI) techniques such as SHAP, LIME, and Q-MEDLEY were applied. The interpretability analysis revealed that features including texture_worst (worst texture value), concave points_worst (number of the most prominent concave regions along the tumor boundary), and area_se (standard error of tumor area) played a decisive role in the model’s predictions. This research contributes uniquely to the literature by demonstrating the applicability of quantum computing–assisted explainable classification methods to tabular biomedical data. However, the reliance on a single dataset and the evaluation of quantum models within noiseless simulation environments represent key limitations that restrict the generalizability of the findings. Future studies are encouraged to conduct external validation on multi-center, imbalanced, and multi-class datasets, as well as experimental testing on real NISQ (Noisy Intermediate-Scale Quantum) devices. The findings highlight that integrating quantum kernel methods with deep and classical learning paradigms within an explainable framework holds strong potential for delivering reliable and high-performance solutions in clinical decision support systems.

Anahtar Kelimeler

Explainable AI , Ensemble learning , Hybrid model , Quantum machine learning , Breast cancer diagnosis

Açıklanabilir kuantum destekli hibrit öğrenme ile meme kanseri sınıflandırması

https://izlik.org/JA43ZG74JB

Öz

Bu çalışma, meme kanseri tanısına yönelik olarak klasik makine öğrenmesi algoritmaları, derin öğrenme mimarileri ve kuantum destekli modellerin entegrasyonuyla oluşturulan açıklanabilir bir hibrit sınıflandırma yaklaşımı önermektedir. Breast Cancer Wisconsin (Diagnostic) veri seti üzerinde gerçekleştirilen analizde, Lojistik Regresyon, Rastgele Orman, Aşırı Gradyan Artırma (XGBoost), TabNet, Variational Quantum Classifier (VQC) ve Quantum Kernel Support Vector Classifier (QKSVC) gibi farklı sınıflandırıcılar kullanılmış, bu modellerin çıktıları yumuşak oylama (soft voting) yöntemiyle birleştirilerek nihai bir hibrit model oluşturulmuştur. Tabakalı on katlı çapraz doğrulama sonucunda topluluk modeli yaklaşık 0,995 ortalama AUC ve 0,98 doğruluk düzeyiyle yüksek bir başarı göstermiştir. Model kararlarının şeffaflığını artırmak amacıyla SHAP, LIME ve Q-MEDLEY gibi açıklanabilir yapay zekâ yöntemleri uygulanmıştır. Açıklanabilirlik analizlerinde ‘en kötü doku değeri’ (texture_worst), ‘tümör sınırındaki en belirgin içe çökük bölgelerin sayısı’ (concave points_worst) ve ‘tümör alan ölçümü standart hatası’ (area_se) gibi özniteliklerin model kararları üzerinde belirleyici rol oynadığı tespit edilmiştir. Bu araştırma, kuantum bilişim destekli açıklanabilir sınıflandırma yaklaşımlarının tablo formatındaki biyomedikal veriler üzerindeki uygulanabilirliğini ortaya koyarak, literatüre özgün bir katkı sunmaktadır. Tek veri seti kullanılması ve kuantum modellerin gürültüsüz simülasyon ortamında değerlendirilmesi, sonuçların genellenebilirliğini sınırlayan başlıca etmenlerdir. Gelecek çalışmaların çok merkezli, dengesiz ve çok sınıflı veri kümelerinde dış doğrulama yapılması ve gerçek NISQ (gürültülü ara ölçekli kuantum) donanımlarında deneysel testler gerçekleştirmesi önerilmektedir. Bulgular, kuantum çekirdek yöntemleriyle derin ve klasik öğrenme paradigmalarının açıklanabilir bir çerçevede bütünleştirilmesinin, klinik karar destek sistemleri için güvenilir ve yüksek performanslı çözümler sunma potansiyeli taşıdığını ortaya koymaktadır.

Anahtar Kelimeler

Açıklanabilir yapay zekâ , Topluluk öğrenme yaklaşımı , Hibrit model , Kuantum makine öğrenmesi , Meme kanseri tanısı

Kaynakça

• Ahmed, K. A., Humaira, I., Khan, A. R., Hasan, M. S., Islam, M., Roy, A., ... & Xames, M. D. (2025). Advancing breast cancer prediction: Comparative analysis of ML models and deep learning-based multi-model ensembles on original and synthetic datasets. PLoS One, 20(6), e0326221. https://doi.org/10.1371/journal.pone.0326221
• Alawad, D., Katebi, A., Kabir, M., & Hoque, M. (2023). Accurate gene regulatory network inference using ensemble machine learning methods. Bioinformatics Advances, 3 (1), vbad032. https://doi.org/10.1093/bioadv/vbad032
• Alelyani, T., Alshammari, M. M., Almuhanna, A., & Asan, O. (2024, May). Explainable artificial intelligence in quantifying breast Cancer factors: Saudi Arabia context. In Healthcare (Vol. 12, No. 10, p. 1025). MDPI. https://doi.org/10.3390/healthcare12101025
• Arik, S. Ö., & Pfister, T. (2021). Tabnet: Attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35 (8), 6679–6687.
• Arravalli, T., Chadaga, K., Muralikrishna, H., Swathi, K. S., Sampathila, N., Cenitta, D., & Chadaga, R. (2025). Detection of breast cancer using machine learning and explainable artificial intelligence. Scientific Reports, 15, 26931. https://doi.org/10.1038/s41598-025-12644-w
• Benedetti, M., Lloyd, E., Sack, S., & Fiorentini, M. (2019). Parameterized quantum circuits as machine learning models. Quantum Science and Technology, 4 (4), 043001. https://doi.org/10.1088/2058-9565/ab4eb5
• Blank, C., Park, D., Rhee, J., & Petruccione, F. (2020). Quantum classifier with tailored quantum kernel. NPJ Quantum Information, 6(1). https://doi.org/10.1038/s41534-020-0272-6
• Bray, F., Laversanne, M., Sung, H., Ferlay, J., Siegel, R. L., Soerjomataram, I., & Jemal, A. (2024). Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians, 74(3), 229-263. https://doi.org/10.3322/caac.21834
• Cerezo, M., Arrasmith, A., Babbush, R., Benjamin, S. C., Endo, S., Fujii, K., ... & Coles, P. J. (2021). Variational quantum algorithms. Nature Reviews Physics, 3 (9), 625–644. https://doi.org/10.1038/s42254-021-00348-9
• Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
• Chereda, H., Bleckmann, A., Menck, K., Perera-Bel, J., Stegmaier, P., Auer, F., ... & Beißbarth, T. (2021). Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer. Genome medicine, 13(1), 42. https://doi.org/10.1186/s13073-021-00845-7
• Eyüpoğlu, C., & Yavuz, E. (2020). Kanser teşhisi için makine öğrenmesi tekniklerine dayalı yeni bir sınıflandırma metodu. Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi, 7 (2), 1106–1123.
• Ghasemi, A., Hashtarkhani, S., Schwartz, D. L., & Shaban‐Nejad, A. (2024). Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review. Cancer Innovation, 3(5), e136. https://doi.org/10.1002/cai2.136
• Güler, M., Sart, G., Algorabi, Ö., Adıguzel Tuylu, A. N., & Türkan, Y. S. (2025). Breast Cancer Classification with Various Optimized Deep Learning Methods. Diagnostics, 15(14), 1751. https://doi.org/10.3390/diagnostics15141751
• Han, L., & Yin, Z. (2022). A hybrid breast cancer classification algorithm based on meta-learning and artificial neural networks. Frontiers in oncology, 12, 1042964. https://doi.org/10.3389/fonc.2022.1042964
• Homayouni, H., & Mansoori, E. (2017). A novel density-based ensemble learning algorithm with application to protein structural classification. Intelligent Data Analysis, 21 (1), 167–179. https://doi.org/10.3233/IDA-150357
• Islam, T., Sheakh, M. A., Tahosin, M. S., Hena, M. H., Akash, S., Bin Jardan, Y. A., ... & Bourhia, M. (2024). Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI. Scientific Reports, 14(1), 8487. https://doi.org/10.1038/s41598-024-57740-5
• Kaddes, M., Ayid, Y. M., Elshewey, A. M., & Fouad, Y. (2025). Breast cancer classification based on hybrid CNN with LSTM model. Scientific Reports, 15(1), 4409. https://doi.org/10.1038/s41598-025-88459-6
• Krunic, Z., Flöther, F., Seegan, G., Earnest-Noble, N., & Shehab, O. (2022). Quantum kernels for real-world predictions based on electronic health records. Ieee Transactions on Quantum Engineering, 3, 1-11. https://doi.org/10.1109/tqe.2022.3176806
• Kör, H. (2019). Classification of breast cancer by machine learning methods. 4th International Symposium on Innovative Approaches in Engineering and Natural Sciences, 508–511.
• Li, Y., Zhou, R., Xu, R., Hu, W., & Fan, P. (2020). Quantum algorithm for the nonlinear dimensionality reduction with arbitrary kernel. Quantum Science and Technology, 6(1), 014001. https://doi.org/10.1088/2058-9565/abbe66
• Martino, F. D., & Delmastro, F. (2022). Explainable AI for clinical and remote health applications: A survey on tabular and time series data. Artificial Intelligence Review, 56 (6), 5261–5315. https://doi.org/10.1007/s10462-022-10304-3 Munkhdalai, L., Munkhdalai, T., Pham, V., Hong, J., Ryu, K. H., & Theera‐Umpon, N. (2022). Neural network-augmented locally adaptive linear regression model for tabular data. Sustainability, 14 (22), 15273. https://doi.org/10.3390/su142215273
• Munshi, R. M., Cascone, L., Alturki, N., Saidani, O., Alshardan, A., & Umer, M. (2024). A novel approach for breast cancer detection using optimized ensemble learning framework and XAI. Image and Vision Computing, 142, 104910. https://doi.org/10.1016/j.imavis.2024.104910
• Nemade, V., & Fegade, V. (2023). Machine learning techniques for breast cancer prediction. Procedia Computer Science, 218, 1314–1320. https://doi.org/10.1016/j.procs.2023.01.110
• Oztekin, P. S., Katar, O., Omma, T., Erel, S., Tokur, O., Avci, D., ... & Acharya, U. R. (2024). Comparison of explainable artificial intelligence model and radiologist review performances to detect breast cancer in 752 patients. Journal of Ultrasound in Medicine, 43(11), 2051-2068. https://doi.org/10.1002/jum.16535
• Panagiotou, E., Heurich, M., Landgraf, T., & Ntoutsi, E. (2024). Tabcf: Counterfactual explanations for tabular data using a transformer-based VAE. Proceedings of the 5th ACM International Conference on AI in Finance, 274–282. https://doi.org/10.1145/3677052.3698673
• Prajapati, J.B., Paliwal, H., Prajapati, B.G., Saikia, S., Pandey, R. (2023). Quantum Machine Learning in Prediction of Breast Cancer. In: Pandey, R., Srivastava, N., Singh, N.K., Tyagi, K. (eds) Quantum Computing: A Shift from Bits to Qubits. Studies in Computational Intelligence, vol 1085. Springer, Singapore. https://doi.org/10.1007/978-981-19-9530-9_19
• Qasrawi, R., Daraghmeh, O., Qdaih, I., Thwib, S., Polo, S. V., Owienah, H., ... & Atari, S. (2024). Hybrid ensemble deep learning model for advancing breast cancer detection and classification in clinical applications. Heliyon, 10(19). https://doi.org/10.1016/j.heliyon.2024.e38374
• Quinn, H., Sedky, M., Francis, J., & Streeton, M. (2024). A literature review of explainable tabular data. Preprints. https://doi.org/10.20944/preprints202408.0556.v1
• Rebentrost, P., Mohseni, M., & Lloyd, S. (2014). Quantum support vector machine for big data classification. Physical Review Letters, 113 (13), 130503. https://doi.org/10.1103/PhysRevLett.113.130503
• Sahakyan, M., Aung, Z., & Rahwan, T. (2021). Explainable artificial intelligence for tabular data: A survey. IEEE Access, 9 , 135392–135422. https://doi.org/10.1109/ACCESS.2021.3116481
• Shan, Z., Guo, J., Ding, X., Zhou, X., Wang, J., Lian, H., ... & Xu, J. (2022). Demonstration of breast cancer detection using QSVM on IBM quantum processors. https://doi.org/10.21203/rs.3.rs-1434074/v
• Sharma, S., Aggarwal, A. & Choudhury, T. (2018). Breast cancer detection using machine learning algorithms. International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS) 2018 (pp. 114–118). IEEE.
• Vamvakas, A., Tsivaka, D., Logothetis, A., Vassiou, K., & Tsougos, I. (2022). Breast cancer classification on multiparametric MRI–increased performance of boosting ensemble methods. Technology in cancer research & treatment, 21, 15330338221087828. https://doi.org/10.1177/15330338221087828
• Vidić, I., Egnell, L., Jerome, N. P., Teruel, J. R., Sjøbakk, T. E., Østlie, A., ... & Goa, P. E. (2018). Support vector machine for breast cancer classification using diffusion‐weighted MRI histogram features: Preliminary study. Journal of Magnetic Resonance Imaging, 47(5), 1205-1216. https://doi.org/10.1002/jmri.25873
• Wang, P., Hu, X., Li, Y., Liu, Q., & Zhu, X. (2016). Automatic Cell Nuclei Segmentation And Classification Of Breast Cancer Histopathology Images. Signal Processing, 122, 1-13.
• Wolberg, W., Mangasarian, O., Street, N., & Street, W. (1993). Breast Cancer Wisconsin (Diagnostic) [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5DW2B
• Xiang, Q., Li, D., Hu, Z., Yuan, Y., Sun, Y., Zhu, Y., ... & Hua, X. (2024). Quantum classical hybrid convolutional neural networks for breast cancer diagnosis. Scientific Reports, 14(1), 24699. https://doi.org/10.1038/s41598-024-74778-7
• Yang, P., Yang, J., Zhou, B., & Zomaya, A. (2010). A review of ensemble methods in bioinformatics. Current Bioinformatics, 5 (4), 296–308. https://doi.org/10.2174/157489310794072508
• Yıldız, O., Tez, M., Bilge, H. Ş., Akcayol, M. A., & Güler, İ. (2012). Meme kanseri sınıflandırması için veri füzyonu ve genetik algoritma tabanlı gen seçimi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 27(3).