Open Access Open Access  Restricted Access Subscription Access

Deep Learning Algorithms for Automated Skin Cancer Detection: A Comparative Study

Ruchi Banarjee, Aman Kumar, Gopal Khorwal

Abstract


Skin cancer is one of the most common forms of cancer globally, with early detection playing a crucial role in improving patient outcomes. Traditional diagnostic methods rely heavily on dermatologists’ expertise, which can be subjective and time-consuming. Recent advancements in deep learning have shown remarkable potential in automating skin cancer detection from dermoscopic images. This study provides a comparative analysis of popular deep learning algorithms, including Convolutional Neural Networks (CNN), ResNet, DenseNet, and Vision Transformers (ViT), in terms of accuracy, sensitivity, specificity, and computational efficiency. Experimental results indicate that hybrid architectures such as CNN-Transformer combinations outperform conventional CNNs, offering a promising pathway for real-world clinical applications.

 


Full Text:

PDF

References


Esteva, A., Kuprel, B., Novoa, R. A., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118.

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 (CVPR), 770–778.

Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4700–4708.

Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations (ICLR).

Chen, L., Lu, C., Yang, Y., & Zhang, Y. (2022). Hybrid CNN-Transformer models for medical image classification. IEEE Transactions on Medical Imaging, 41(12), 3545–3556.

Siegel, R. L., Miller, K. D., & Jemal, A. (2023). Cancer statistics, 2023. CA: A Cancer Journal for Clinicians, 73(1), 17–48.

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 (CVPR), 770–778.

Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4700–4708.

Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations (ICLR).

Chen, L., Lu, C., Yang, Y., & Zhang, Y. (2022). Hybrid CNN-Transformer models for medical image classification. IEEE Transactions on Medical Imaging, 41(12), 3545–3556.


Refbacks

  • There are currently no refbacks.