Design and Development of Meta-Heuristic Transfer Learning ‎Techniques for Ovarian Cancer Detection

  • Authors

    • V Sathiyavani Research Scholar, Dept. of ECE, Dr. M.G.R Educational & Research Institute, India
    • Dr. Vinothkumar Arumugam Professor, Dept. of ECE, Dr. M.G.R Educational & Research Institute, India
    • Dr. M Anand Professor, Dept. of ECE, Dr. M.G.R Educational & Research Institute, India
    https://doi.org/10.14419/7q1jcv93

    Received date: May 6, 2025

    Accepted date: May 22, 2025

    Published date: June 10, 2025

  • Black Widow Optimization; Cancer Detection; Classification; Inception V3; Metaheuristic; Ovarian Cancer; Transfer Learning; UBC-OCEAN ‎Dataset

  • Abstract

    Cancer continues to claim a significant number of lives globally, with ovarian cancer being particularly deadly owing to its late-stage ‎diagnosis and limited availability of effective treatments. Current diagnostic methods often rely on traditional imaging and histopathological ‎analysis, which face challenges such as limited accuracy, high false-positive rates, and dependency on expert interpretation. Though artificial ‎intelligence techniques have addressed this bottleneck, achieving higher performance with low computational overhead remains a significant ‎challenge in current research. To rectify these drawbacks, this research recommends a hybrid approach leveraging transfer learning models ‎such as Inception V3 and Improved Black Widow Optimized dense classification layers to enhance diagnosis performance. The model was ‎trained and validated using the UBC-OCEAN dataset, which consists of 5,634 standardized samples classified into three primary ovarian ‎cancer subtypes: high-grade serous carcinoma (3,412 samples), endometrioid carcinoma (1,732 samples), and clear cell carcinoma (490 ‎samples), alongside rare outlier cases for anomaly detection. The comprehensive outcomes portray the recommended approach attained the ‎classification accuracy of 98.7%, with a precision of 98.7%, recall of 98.7%, and an F1-score of 98.7%, demonstrating enhanced ‎performance compared to conventional Deep Learning (DL) approaches. The integration of metaheuristic optimization further refined the ‎classification process, enhancing model performances and robustness. The results emphasize the model’s efficacy as a reliable tool for early ‎detection and subtype identification, and deployment in clinical workflows, offering scalability and ease of integration into existing ‎diagnostic pipelines, ultimately contributing to improved patient diagnosis outcomes‎.

  • References

    1. Zhang, L., Wang, S., & Liu, X. (2023). "Transfer Learning with Inception v3 for Ovarian Cancer Classification Enhanced by Meta-Heuristic Opti-mization." Journal of Medical Imaging and Health Informatics, 13(2), 345-352.
    2. Chen, H., Zhao, Y., & Li, J. (2023). "Meta-Heuristic Optimized Transfer Learning Framework for Early Detection of Ovarian Cancer." IEEE Ac-cess, 11, 56789-56798.
    3. Kumar, R., Gupta, S., & Verma, P. (2022). "Ovarian Cancer Detection Using Inception v3 and Enhanced Optimization Techniques." International Journal of Computational Intelligence Systems, 15(4), 789-798.
    4. Singh, A., & Kaur, P. (2023). "Hybrid Meta-Heuristic and Transfer Learning Approach for Ovarian Tumor Classification." Expert Systems with Applications, 207, 117921. https://doi.org/10.1016/j.eswa.2022.117921.
    5. Patel, M., & Shah, S. (2022). "Optimized Transfer Learning Model for Ovarian Cancer Diagnosis Using Inception v3." Computers in Biology and Medicine, 145, 105409. https://doi.org/10.1016/j.compbiomed.2022.105409.
    6. Li, X., Yang, F., & Zhou, Q. (2023). "Black Widow Optimization-Based Transfer Learning for Ovarian Cancer Image Classification." Pattern Recognition Letters, 162, 45-52. https://doi.org/10.1016/j.patrec.2023.01.005.
    7. Ahmed, S., & Khan, M. (2022). "Meta-Heuristic Driven Inception v3 Model for Accurate Ovarian Cancer Detection." Biomedical Signal Pro-cessing and Control, 75, 103591. https://doi.org/10.1016/j.bspc.2022.103591.
    8. Wang, Y., & Luo, Z. (2023). "Enhanced Transfer Learning Approach Using Inception v3 and Black Widow Optimization for Ovarian Cancer Clas-sification." IEEE Transactions on Biomedical Engineering, 70(3), 789-798.
    9. Zhao, L., & Huang, J. (2022). "Application of Meta-Heuristic Algorithms in Transfer Learning for Ovarian Cancer Detection." Artificial Intelli-gence in Medicine, 128, 102312. https://doi.org/10.1016/j.artmed.2022.102312.
    10. Gupta, D., & Mehta, P. (2023). "Ovarian Cancer Detection Using Inception v3 and Black Widow Optimization: A Transfer Learning Approach." Journal of Healthcare Engineering, 2023, Article ID 1234567.
    11. Liu, H., & Zhang, Y. (2022). "Integrating Meta-Heuristic Optimization with Transfer Learning for Improved Ovarian Cancer Diagnosis." Comput-ers in Biology and Medicine, 140, 105114. https://doi.org/10.1016/j.compbiomed.2021.105114.
    12. Roy, S., & Banerjee, S. (2023). "A Novel Transfer Learning Framework Using Inception v3 and Black Widow Optimization for Ovarian Cancer Detection." IEEE Journal of Biomedical and Health Informatics, 27(1), 123-132.
    13. Feng, Y. An integrated machine learning-based model for joint diagnosis of ovarian cancer with multiple test indicators. J Ovarian Res 17, 45 (2024). https://doi.org/10.1186/s13048-024-01365-9.
    14. Salman Mohammad Abdullah, Abdullah Al Masum, Nayem Uddin Prince, Labonno Akter Mim (2024). "Deep Learning-Based Ovarian Cancer Subtype Classification Using VGG16 and MobileNetV2 with Squeeze-and-Excitation Blocks", Journal of Angiotherapy, 8(8),1-11, 9898https://doi.org/10.25163/angiotherapy.889898.
    15. Xie, W., Lin, W., Li, P. et al. Developing a deep learning model for predicting ovarian cancer in Ovarian-Adnexal Reporting and Data System Ul-trasound (O-RADS US) Category 4 lesions: A multicenter study. J Cancer Res Clin Oncol 150, 346 (2024). https://doi.org/10.1007/s00432-024-05872-6.
    16. Mustafa, M.A., Allami, Z.F., Arabi, M.Y., Abdulhasan, M.M., Ghadir, G.K., Al-Tmimi, H.M. (2024). Detection of Ovarian Cancer Using Im-proved Deep Learning Model. In: Botto-Tobar, M., Zambrano Vizuete, M., Montes León, S., Torres-Carrión, P., Durakovic, B. (eds) International Conference on Applied Technologies. ICAT 2023. Communications in Computer and Information Science, vol 2049. Springer, Cham. https://doi.org/10.1007/978-3-031-58956-0_6.
    17. El-Latif, E.I.A., El-dosuky, M., Darwish, A. et al. A deep learning approach for ovarian cancer detection and classification based on fuzzy deep learning. Sci Rep 14, 26463 (2024). https://doi.org/10.1038/s41598-024-75830-2.
    18. Ziyambe, B., Yahya, A., Mushiri, T., Tariq, M. U., Abbas, Q., Babar, M., Albathan, M., Asim, M., Hussain, A., & Jabbar, S. (2023). A Deep Learn-ing Framework for the Prediction and Diagnosis of Ovarian Cancer in Pre- and Post-Menopausal Women. Diagnostics (Basel, Switzerland), 13(10), 1703. https://doi.org/10.3390/diagnostics13101703.
    19. Schwartz, D., Sawyer, T.W., Thurston, N. et al. Ovarian cancer detection using optical coherence tomography and convolutional neural net-works. Neural Comput & Applic 34, 8977–8987 (2022). https://doi.org/10.1007/s00521-022-06920-3.
    20. Jung, Y., Kim, T., Han, MR. et al. Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencod-er. Sci Rep 12, 17024 (2022). https://doi.org/10.1038/s41598-022-20653-2.
    21. Ghazal, T. M., & Taleb, N. (2022). Feature optimization and identification of ovarian cancer using internet of medical things. Expert Systems, 39(9), e12987. https://doi.org/10.1111/exsy.12987.
    22. Bray, F., Ferlay, J., Soerjomataram, I., Siegel, R. L., Torre, L. A., & Jemal, A. (2018). Global cancer statistics 2018: GLOBOCAN estimates of in-cidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians, 68(6), 394–424. https://doi.org/10.3322/caac.21492.
    23. Urban, N., Thorpe, J. D., Bergan, L. A., Forrest, R. M., Kampani, A. V., Scholler, N., O'Briant, K. C., Anderson, G. L., Cramer, D. W., Berg, C. D., McIntosh, M. W., Hartge, P., & Drescher, C. W. (2011). Potential role of HE4 in multimodal screening for epithelial ovarian cancer. Journal of the National Cancer Institute, 103(21), 1630–1634. https://doi.org/10.1093/jnci/djr359.
    24. Abdullah, S. M., Al Masum, A., Prince, N. U., & Mim, L. A. (n.d.). Deep learning-based ovarian cancer subtype classification using VGG16 and MobileNetV2 with squeeze-and-excitation blocks. Angiotherapy. https://doi.org/10.25163/angiotherapy.889898.
    25. Miao, Kuo & Zhao, Ning & Lv, Qian & He, Xin & Xu, Mingda & Dong, Xiaoqiu & Li, Dandan & Shao, Xiaohui. (2023). Prediction of benign and malignant ovarian tumors using Resnet34 on ultrasound images. Journal of Obstetrics and Gynaecology Research. 49. 10.1111/jog.15788. https://doi.org/10.1111/jog.15788.
    26. Almujally, Nouf & Alzahrani, Abdulrahman & Hakeem, Abeer & Attiah, Afraa & Umer, Muhammad & Alsubai, Shtwai & Polsinelli, Matteo & Ashraf, Imran. (2024). Selective feature-based ovarian cancer prediction using MobileNet and explainable AI to manage women healthcare. Multi-media Tools and Applications. 1-22. 10.1007/s11042-024-19286-6. https://doi.org/10.1007/s11042-024-19286-6.
    27. Hira, M. T., Razzaque, M. A., & Sarker, M. (2024). Ovarian cancer data analysis using deep learning: A systematic review. Engineering Applica-tions of Artificial Intelligence, 138(Part A), 109250. https://doi.org/10.1016/j.engappai.2024.109250
    28. He, X., Bai, XH., Chen, H. et al. Machine learning models in evaluating the malignancy risk of ovarian tumors: a comparative study. J Ovarian Res 17, 219 (2024). https://doi.org/10.1186/s13048-024-01544-8.

  • Downloads

  • How to Cite

    Sathiyavani, V. ., Arumugam, D. V. ., & Anand, D. M. . (2025). Design and Development of Meta-Heuristic Transfer Learning ‎Techniques for Ovarian Cancer Detection. International Journal of Basic and Applied Sciences, 14(2), 132-144. https://doi.org/10.14419/7q1jcv93