An Efficient Hybrid Deep Learning Model For Skin Cancer Detection And Comparative Analysis
DOI:
https://doi.org/10.29284/9fg5f242Keywords:
Skin Cancer Detection; Deep Learning; Hybrid Model; Convolutional Neural Network; Medical Image Analysis; HAM10000; EfficientNet; Transfer LearningAbstract
Skin cancer remains one of the most prevalent and life-threatening forms of cancer globally, with early detection being critical for successful treatment outcomes. The rapid advancement of deep learning (DL) in medical image analysis has opened new avenues for automated, accurate, and non-invasive diagnostic tools. This study proposes an efficient hybrid deep learning model for skin cancer detection, leveraging the complementary strengths of a pre-trained Convolutional Neural Network (CNN) for feature extraction and a custom classifier for precise classification. A comprehensive comparative analysis is conducted against state-of-the-art models including VGG16, ResNet50, InceptionV3, and a standalone CNN. The models were trained and evaluated on the publicly available HAM10000 dataset, which comprises over 10,000 dermatoscopic images across seven diagnostic categories. The proposed hybrid model, which integrates a fine-tuned EfficientNetB0 backbone with a multi-head attention mechanism and optimized dense layers, achieved superior performance, with an overall accuracy of 93.8%, precision of 93.2%, recall of 93.5%, and an F1-score of 93.3%. These results significantly outperform the benchmark models, demonstrating the efficacy of the hybrid architecture. The findings underscore the potential of hybrid deep learning approaches in developing robust, automated skin cancer screening systems that can assist clinicians in making faster and more accurate diagnoses, ultimately improving patient outcomes.
References
1. Alwakid, G., Gouda, W., Humayun, M., & Sama, N. (2022). Melanoma detection using deep learning-based classifications. Healthcare, *10*, 2481.
2. Badawy, M., Ramadan, N., & Hefny, H. A. (2023). Healthcare predictive analytics using machine learning and deep learning techniques: a survey. Journal of Electrical Systems and Information Technology, *10*(1), 40.
3. Devarakonda, N., Murthy, M. V. R., Reddy, R. R. C., & Shree Harsha, P. B. L. (2024). Skin Cancer Detection with Metadata Using Deep Learning Strategies. In Shetty, N. R., Prasad, N. H., Nagaraj, H. C. (Eds.) Advances in Communication and Applications. ERCICA 2023. Lecture Notes in Electrical Engineering, vol. 1105. Singapore: Springer.
4. Haney, J. M., & Liang, C. J. (2024). A literature review on safety perception and trust during human–robot interaction with autonomous mobile robots that apply to industrial environments. IISE Transactions on Occupational Ergonomics and Human Factors, *12*(1–2), 6–27.
5. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778.
6. Helaly, H. A., Badawy, M., & Haikal, A. Y. (2024). A review of deep learning approaches in clinical and healthcare systems based on medical image analysis. Multimedia Tools and Applications, *83*(12), 36039–36080.
7. Hussain, I., & Nazir, M. B. (2024). Mind matters: exploring AI, machine learning, and deep learning in neurological health. International Journal of Advanced Engineering Technology and Innovation, *1*(4), 1–43.
8. Kumari, J., Kumar, E., & Kumar, D. (2023). A structured analysis to study the role of machine learning and deep learning in the healthcare sector with big data analytics. Archives of Computational Methods in Engineering, *30*(6), 3673–3701.
9. Luo, L., Wang, X., Lin, Y., Ma, X., Tan, A., Chan, R., ... & Chen, H. (2024). Deep learning in breast cancer imaging: A decade of progress and future directions. IEEE Reviews in Biomedical Engineering.
10. Maduranga, M. W. P., & Nandasena, D. (2022). Mobile-based skin disease diagnosis system using convolutional neural networks (CNN). International Journal of Image, Graphics and Signal Processing.
11. Mehta, R., Shui, C., & Arbel, T. (2024). Evaluating the fairness of deep learning uncertainty estimates in medical image analysis. Proceedings of Medical Imaging with Deep Learning, 1453–1492. PMLR.
12. Mondol, R. K., Millar, E. K., Graham, P. H., Browne, L., Sowmya, A., & Meijering, E. (2023). hist2rna: an efficient deep learning architecture to predict gene expression from breast cancer histopathology images. Cancers, *15*(9), 2569.
13. Reyad, M., Sarhan, A. M., & Arafa, M. (2024). Architecture optimization for hybrid deep residual networks in liver tumor segmentation using a GA. International Journal of Computational Intelligence Systems, *17*(1), 1–22.
14. Sarhan, A. M., Gobara, M., Yasser, S., Elsayed, Z., Sherif, G., Moataz, N., ... & Ali, H. A. (2024). Knee osteoporosis diagnosis based on deep learning. International Journal of Computational Intelligence Systems, *17*(1), 241.
15. Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations.
16. Singh, U., Abhishek, K., & Azad, H. K. (2024). A survey of cutting-edge multimodal sentiment analysis. ACM Computing Surveys, *56*(9), 1–38.
17. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818–2826.
18. Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, 6105–6114.
19. Tschandl, P., Rosendahl, C., & Kittler, H. (2018). The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data, *5*, 180161.
20. World Cancer Research Fund. (n.d.). Skin cancer statistics. Retrieved from https://www.wcrf.org/cancer-trends/skin-cancer-statistics/
21. Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Sebastian Thrun (2017). Dermatologist-Level Classification Of Skin Cancer With Deep Neural Networks. Nature, 542(7639), 115–118.
22. Haenssle, H. A., Fink, C., Schneiderbauer, R., Toberer, F., Buhl, T., & Claus Garbe (2018), “Man Against Machine: Diagnostic Performance Of A Deep Learning Convolutional Neural Network For Dermoscopic Melanoma Recognition” Annals of Oncology, 29(8), 1836–1842.
23. Codella, N. C. F., Nguyen, Q. B., Pankanti, S., Gutman, D. A., Helba, B., Halpern, A. C., & John R. Smith (2017), “Deep Learning Ensembles For Melanoma Recognition In Dermoscopy Images” IBM Journal of Research and Development, 61(4/5),
24. Tschandl, P., Rosendahl, C., & Harald Kittler (2018), “The HAM10000 dataset: A Large Collection Of Multi-Source Dermatoscopic Images Of Common Pigmented Skin Lesions,” Scientific Data, 5, 180161
25. Brinker, T. J., Hekler, A., Enk, A. H., Berking, C., Haferkamp, S., & Jochen S. Utikal (2019), Deep Neural Networks Are Superior To Dermatologists In Melanoma Image Classification, European Journal of Cancer, 119, 11–17.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
