A Deep Learning-Based Skin Cancer Detection with ResNet50V2
DOI:
https://doi.org/10.64074/dedfpe19Keywords:
ResNet50V2, Graphics processing unit, Tensor processing unit, Deep Convolutional Neural Network, Convolutional neural network, Rectified linear unitAbstract
Skin cancer is a prevalent global health concern, with melanoma being particularly dangerous due to its potential to metastasise. Researchers have harnessed deep learning techniques, specifically transfer learning, to create an automated classification system for skin lesions. This system can be especially valuable in areas with limited medical resources. The study leverages pre-trained convolutional neural networks (CNNs) and transfer learning. Using Google Collab and a dataset attached via Google Drive, skin lesion images were analysed. The dataset from the International Skin Imaging Collaboration (ISIC) was divided into eight classes, with “Melanocytic Nevus” being the most common (51% of data). Augmentation was applied to address overfitting. Comparing the sequential CNN and pre-trained ResNet50V2 models, both achieved over 60% accuracy. While ResNet50V2 had slightly better accuracy, the sequential model exhibited greater stability in validation results. Notably, segmentation techniques were not employed due to image-specific challenges. This research contributes to improving skin cancer diagnosis and underscores the potential of AI in healthcare. Doctors can benefit from this system, enhancing patient care and treatment decisions.
References
Arneesh A and Akhilesh KS (2019) Predictive approach for Melanoma Skin Cancer Detection Using CNN. In: International Conference of Sustainable Computing in Science, Technology and Management (SUSCOM-2019). http://dx.doi.org/10.2139/ssrn.3352407
Du-Harpur X, Watt FM, Luscombe NM, Lynch MD (2020) What is AI? Applications of artificial intelligence to dermatology. DOI: https://doi.org/10.1111/bjd.18880
Haenssle1 HA, Fink C, Schneiderbauer R, Toberer F, Buhl T, Blum A, Kalloo A, Ben Hadj Hassen L, Thomas A, Enk & L. Uhlmann (2018). Man against machine: diagnostic performance of a 54 deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. doi: https://doi.org/10.1093/annonc/mdy166. PMID: 29846502
Hassani H & Silva E, Unger S & Tajmazinani M, MacFeely S (2020). Artificial Intelligence (AI) or Intelligence Augmentation (IA): What Is the Future? AI. https://doi.org/10.3390/ai1020008
Noel CFC, David G, Emre C, Brian H, Michael AM, Stephen WD, Aadi K, Konstantinos L, Nabin M, Harald K, Allan H (2018). Skin Lesion Analysis Toward Melanoma Detection: https://doi.org/10.48550/arXiv.1710.05006
Park, Y. J., Kwon, G. H., Kim, J. O., Kim, N. K., Ryu, W. S., & Lee, K. S. (2020). A retrospective study of changes in skin cancer characteristics over 11 years. Archives of craniofacial surgery, 21(2), 87–91. https://doi.org/10.7181/acfs.2020.00024
Alavi, M. (1994). Computer-Mediated Collaborative Learning: An Empirical Evaluation. MIS Quarterly, 18(2), 159–174. https://doi.org/10.2307/249763
He, K., Zhang, X., Ren, S., and Sun, J. (2016) Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778. https://doi.org/10.1109/CVPR.2016.90
Introna L (1997). Management, Information, and Power: A narrative of the manager involved. London: MacMillan (PDF) The History of Information: Lessons for Information Management
Marriam N, Zahid M, Tahira N, Rizwan AN, Amjad R, Munwar I, Tanzila S (2025) Skin cancer detection from dermoscopic images using deep learning and fuzzy k-means clustering. DOI: https://doi.org/10.1002/jemt.23908
Poonkuzhali S, Barathi BUA, & Vinodhkumar S (2022) Transfer learning approach for diagnosing skin cancer with a deep convolutional neural network. Information and Communication Technology for Competitive Strategies. DOI: https://doi.org/10.21786/bbrc/13.11/13
Roshan VJ (2022) Optimal Ratio for Data Splitting In: H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA. DOI: https://doi.org/10.1002/sam.11583
Irsa Faryal. (2020). Skin Cancer Disease Detection Using Image Processing Techniques. https://doi.org/10.5281/ZENODO.5148277
