Hybrid Metaheuristic Optimization and Deep Learning Models ‎for Accurate Skin Lesion Detection and Classification

  • Authors

    • G Vijayakumari Assistant Professor, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    • U. Rajasekaran Assistant Professor, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    • M Prakash Assistant Professor, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    • S. Jayabratha Assistant Professor, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    • D. Viswanathan Assistant Professor, Department of Computer Applications, M P Nachimuthu M Jaganathan Engineering College, Erode, Tamilnadu, ‎India‎
    • T. Velmurugan Assistant Professor, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    • J. C. Gayathri UG Student, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    • R. Karthieswari UG Student, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    • M. ‎ Sathishkumar UG Student, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    • W. Shameena UG Student, Department of ECE, Kangeyam Institute of Technology, Tiruppur, Tamilnadu, India
    https://doi.org/10.14419/gjm5eh06

    Received date: May 28, 2025

    Accepted date: June 27, 2025

    Published date: July 8, 2025

  • Skin Lesion Segmentation; HAM10000 Dataset; Graph Cut Segmentation (GCS); Fuzzy C-Means Clustering (FCM); Feature Selection; Particle ‎Swarm Optimization Algorithm (PSOA);Sparrow Search Algorithm (SSA);Vision Transformer (ViT)‎.

  • Abstract

    Skin cancer detection through medical imaging plays a crucial role in early diagnosis and treatment. In this study, we focus on segmenting ‎lesions from the HAM10000 dataset using region-based techniques such as Graph Cut Segmentation (GCS) and Fuzzy C-means clustering ‎‎(FCM). Accurate segmentation is essential for extracting meaningful features, which directly impact the classification performance. To ‎enhance feature selection, we integrate two metaheuristic optimization algorithms—Particle Swarm Optimization Algorithm (PSOA) and ‎Sparrow Search Algorithm (SSA). Additionally, propose a hybrid optimization model that combines these techniques to improve feature ‎selection efficiency and enhance the overall classification process. For classification, we compare the performance of a Vision Transformer ‎‎(ViT) with traditional Convolutional Neural Networks (CNNs), specifically ResNet and EfficientNet, for binary classification of skin ‎lesions. Transformers have demonstrated significant potential in vision tasks due to their self-attention mechanism, which captures long-‎range dependencies in images. The proposed methodology is evaluated based on segmentation accuracy, feature selection efficiency, and ‎classification performance. Then assess multiple evaluation metrics to compare the effectiveness of each technique, ensuring a ‎comprehensive analysis of their impact. The study aims to provide valuable insights into how different segmentation, optimization, and ‎classification methods contribute to improved skin lesion analysis‎.

  • References

    1. Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Deep learning for skin lesion classification: A com-prehensive review. Nature, 542(7639), 115-118. https://doi.org/10.1038/nature21056.
    2. Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022). Vision transformers for medical image analysis: A survey. Medical Image Analysis, 75, 102317.
    3. Holzinger, A., Langs, G., Denk, H., Zatloukal, K., & Müller, H. (2019). Explainable AI in healthcare: Interpreting deep learning models for clinical decision-making. Nature Machine Intelligence, 1(1), 53-61.
    4. Sheller, M. J., Reina, G. A., Edwards, B., Martin, J., & Bakas, S. (2020). Federated learning in medical applications: Challenges and future direc-tions. arXiv preprint arXiv:1912.04977.
    5. Liu, Y., Jain, A., Eng, C., Way, D. H., Lee, K., Bui, P., & Norcliffe-Brown, W. (2020). Enhancing dermatological disease classification with multi-modal data fusion. Journal of Medical Imaging, 7(1), 014001.
    6. Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A., Ciompi, F., Ghafoorian, M., & van der Laak, J. A. (2017). Automated disease detection using convolutional neural networks: A comparative study. Medical Image Analysis, 42, 60-88. https://doi.org/10.1016/j.media.2017.07.005.
    7. Shorten, C., & Khoshgoftaar, T. M. (2019). Improving medical image classification with data augmentation and transfer learning. Journal of Big Data, 6(1), 60. https://doi.org/10.1186/s40537-019-0197-0.
    8. Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Applications of Grad-CAM in medical image interpretation: A review. Proceedings of the IEEE International Conference on Computer Vision, 618-626. https://doi.org/10.1109/ICCV.2017.74.
    9. Tschandl, P., Rosendahl, C., & Kittler, H. (2020). Deep learning in dermatology: Current trends, challenges, and future prospects. The Lancet Digi-tal Health, 2(7), e368-e375.
    10. Topol, E. J. (2019). Towards deployable AI in medical diagnosis: Bridging the gap between research and clinical practice. Nature Medicine, 25(1), 44-56.
    11. Manole, I., Butacu, A.-I., Bejan, R. N., & Tiplica, G.-S. (2024). Enhancing Dermatological Diagnostics with EfficientNet: A Deep Learning Ap-proach. Bioengineering, 11(8), 810. https://doi.org/10.3390/bioengineering11080810.
    12. Khadija Shahzad, Muhammad Wasim, Ivan Miguel Pires, Nuno M. Garcia,Multi- classification of skin lesions using a deep learning-based convolu-tional neural network, Procedia Computer Science, Volume 241,2024. https://doi.org/10.1016/j.procs.2024.08.085.
    13. Vipin Venugopal, Navin Infant Raj, Malaya Kumar Nath, Norton Stephen,A deep neural network using modified EfficientNet for skin cancer de-tection in dermoscopic images, Decision Analytics Journal, Volume 8,2023,100278,ISSN 2772-6622 https://doi.org/10.1016/j.dajour.2023.100278.
    14. Viknesh, C. K., Kumar, P. N., Seetharaman, R., & Anitha, D. (2023). Detection and Classification of Melanoma Skin Cancer Using Image Pro-cessing Technique. Diagnostics, 13(21), 3313. https://doi.org/10.3390/diagnostics13213313.
    15. Aliyu Tetengi Ibrahim, Mohammed Abdullahi, Armand Florentin Donfack Kana, Mohammed Tukur Mohammed, Ibrahim Hayatu Hassan, Categor-ical classification of skin cancer using a weighted ensemble of transfer learning with test time augmentation, Data Science and Management,2024. https://doi.org/10.1016/j.dsm.2024.10.002.
    16. Bello, A., Ng, S.-C., & Leung, M.-F. (2024). Skin Cancer Classification Using Fine-Tuned Transfer Learning of DENSENET-121. Applied Scienc-es, 14(17), 7707. https://doi.org/10.3390/app14177707.
    17. Azeem, M., Kiani, K., Mansouri, T., & Topping, N. (2024). SkinLesNet: Classification of Skin Lesions and Detection of Melanoma Cancer Using a Novel Multi-Layer Deep Convolutional Neural Network. Cancers, 16(1), 108. https://doi.org/10.3390/cancers16010108.
    18. Vardasca, R., Mendes, J. G., & Magalhaes, C. (2024). Skin Cancer Image Classification Using Artificial Intelligence Strategies: A Systematic Re-view. Journal of Imaging, 10(11), 265. https://doi.org/10.3390/jimaging10110265.
    19. Tahir, M., Naeem, A., Malik, H., Tanveer, J., Naqvi, R. A., & Lee, S.-W. (2023). DSCC_Net: Multi-Classification Deep Learning Models for Diag-nosing of Skin Cancer Using Dermoscopic Images. Cancers, 15(7), 2179. https://doi.org/10.3390/cancers15072179.
    20. Gouda, W., Sama, N. U., Al-Waakid, G., Humayun, M., & Jhanjhi, N. Z. (2022). Detection of Skin Cancer Based on Skin Lesion Images Using Deep Learning. Healthcare, 10(7), 1183. https://doi.org/10.3390/healthcare10071183.
    21. Kavitha, M. (2023). Beamforming techniques for optimizing massive MIMO and spatial multiplexing. National Journal of RF Engineering and Wireless Communication, 1(1), 30-38.
    22. ASIF, M., BARNABA, M., RAJENDRA BABU, K., OM PRAKASH, P., & KHAMURUDDEEN, S. K. (2021). Detection and tracking of theft vehicle. International Journal of Communication and Computer Technologies, 9(2), 6-11. https://doi.org/10.31838/ijccts/09.02.02.
    23. Kulkarni, S., & Ravi, J. N. (2024). Smart Ways to Catch the Abutment DRCs at IP Level. Journal of VLSI Circuits and Systems, 6(1), 51–54. https://doi.org/10.31838/jvcs/06.01.08.

  • Downloads

  • How to Cite

    Vijayakumari, G. ., Rajasekaran, U. . ., Prakash , M. ., Jayabratha , S. ., Viswanathan , D. ., Velmurugan , T. ., Gayathri , J. C. ., Karthieswari , R. ., Sathishkumar , M. ‎, & Shameena, W. . (2025). Hybrid Metaheuristic Optimization and Deep Learning Models ‎for Accurate Skin Lesion Detection and Classification. International Journal of Basic and Applied Sciences, 14(SI-1), 251-257. https://doi.org/10.14419/gjm5eh06