A Robust Skin Cancer Detection and Classification Model Based on Improved Convolutional Neural Networks

Skin cancer (SC) is a major health problem that demands early detection and classification for the best chances of survival. Existing computer vision techniques lack the capacity to address the fine-grained variability exhibited by skin lesion features across surfaces. It is important to identify the SC signs early as the incidence and death rates of this disease are rising rapidly, along with the cost of care. Techniques for diagnosing SC often rely on visual analysis or techniques that do not have accurate results; this can be dangerous for the patient. Hence, deep learning (DL) methods have proved helpful for researchers to construct different methods for the early detection of SC. To distinguish SC from melanoma, these techniques used the lesion's color, size, form, symmetry, and other features. Using the HAM10000 dataset, a sizable and varied dataset, this work suggests a novel DL-based SC detection and diagnosis scheme (DL-SCDCM) that employs DL techniques, particularly CNN, to guarantee an accurate but efficient diagnosis. The proposed CNN model was trained before testing, and it demonstrated impressive performance, correctly diagnosing seven distinct skin lesion types with an accuracy of 96.9 %. Furthermore, the results were compared to those of other research that proposed a slightly different approach, and the proposed model outperformed the others in these comparisons.

Skin cancer Classification, Medical Image Modification, Deep learning, CNN, Normalization, Augmentation

Swapno, S. M. R., Nobel, S. N., Meena, P. K., Meena, V. P., Bahadur, J., & Appaji, A. (2025). Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy. Results in Engineering, 25, 104168.‏

Bappi, M. B. R., Swapno, S. M. R., & Rabbi, M. F. (2024, May). Skin cancer disease detection using MCD-GRU: A deep learning approach. In 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT) (pp. 445-450). IEEE.‏

Jojoa Acosta, M. F., Caballero Tovar, L. Y., Garcia-Zapirain, M. B., & Percybrooks, W. S. (2021). Melanoma diagnosis using deep learning techniques on dermatoscopic images. BMC Medical Imaging, 21(1), 6.‏

Khodadadi, H., Sedigh, A. K., Ataei, M., Motlagh, M. R. J., & Hekmatnia, A. (2017). Nonlinear analysis of the contour boundary irregularity of skin lesion using Lyapunov exponent and KS entropy. Journal of Medical and Biological Engineering, 37(3), 409-419.‏

Khazaei, Z., Ghorat, F., Jarrahi, A. M., Adineh, H. A., Sohrabivafa, M., & Goodarzi, E. J. W. C. R. J. (2019). Global incidence and mortality of skin cancer by histological subtype and its relationship with the human development index (HDI); an ecology study in 2018. World Cancer Res J, 6(2), e13.‏

Ibrahim, O., Gastman, B., & Zhang, A. (2014). Advances in diagnosis and treatment of nonmelanoma skin cancer. Annals of plastic surgery, 73(5), 615-619.‏

Melarkode, N., Srinivasan, K., Qaisar, S. M., & Plawiak, P. (2023). AI-powered diagnosis of skin cancer: a contemporary review, open challenges and future research directions. Cancers, 15(4), 1183.‏

Chaurasia, B. K., Raj, H., Rathour, S. S., & Singh, P. B. (2023). Transfer learning–driven ensemble model for detection of diabetic retinopathy disease. Medical & Biological Engineering & Computing, 61(8), 2033-2049.‏

Tripathi, A., Misra, A., Kumar, K., & Chaurasia, B. K. (2023). Optimized machine learning for classifying colorectal tissues. SN Computer Science, 4(5), 461.‏

Singh, P. B., Singh, P., Dev, H., & Chaurasia, B. K. (2023). Glaucoma classification using enhanced deep transfer learning models with hybrid ROI cropped optic disc technique. SN Computer Science, 4(6), 722.‏

Alam, T. M., Shaukat, K., Khelifi, A., Aljuaid, H., Shafqat, M., Ahmed, U., ... & Luo, S. (2023). A fuzzy inference-based decision support system for disease diagnosis. The Computer Journal, 66(9), 2169-2180.‏

Hasan, M. R., Fatemi, M. I., Monirujjaman Khan, M., Kaur, M., & Zaguia, A. (2021). Comparative analysis of skin cancer (benign vs. malignant) detection using convolutional neural networks. Journal of Healthcare Engineering, 2021(1), 5895156.‏

Kumar, A., & Chaurasia, B. K. (2024). Detection of SARS-CoV-2 virus using lightweight convolutional neural networks. Wireless Personal Communications, 135(2), 941-965.‏

asan, M., Barman, S. D., Islam, S., & Reza, A. W. (2019, April). Skin cancer detection using convolutional neural network. In Proceedings of the 2019 5th international conference on computing and artificial intelligence (pp. 254-258).‏

Afza, F., Sharif, M., Khan, M. A., Tariq, U., Yong, H. S., & Cha, J. (2022). Multiclass skin lesion classification using hybrid deep features selection and extreme learning machine. Sensors, 22(3), 799.‏

Akram, T., Alsuhaibani, A., Khan, M. A., Khan, S. U., Naqvi, S. R., & Bilal, M. (2024). Dermo‐Optimizer: Skin Lesion Classification Using Information‐Theoretic Deep Feature Fusion and Entropy‐Controlled Binary Bat Optimization. International Journal of Imaging Systems and Technology, 34(5), e23172.‏

Bibi, S., Khan, M. A., Shah, J. H., Damaševičius, R., Alasiry, A., Marzougui, M., ... & Masood, A. (2023). MSRNet: multiclass skin lesion recognition using additional residual block based fine-tuned deep model’s information fusion and best feature selection. Diagnostics, 13(19), 3063.‏

Ozdemir, B., & Pacal, I. (2025). An innovative deep learning framework for skin cancer detection employing ConvNeXtV2 and focal self-attention mechanisms. Results in Engineering, 25, 103692.‏

Dillshad, V., Khan, M. A., Nazir, M., Saidani, O., Alturki, N., & Kadry, S. (2025). D2LFS2Net: Multi‐class skin lesion diagnosis using deep learning and variance‐controlled Marine Predator optimisation: An application for precision medicine. CAAI Transactions on Intelligence Technology, 10(1), 207-222.‏

Chopade, A. (2019, April). Seven class classification of skin lesions by using incremental convolutional neural network in Python. In Proceedings of the International Conference on Advances in Electronics, Electrical & Computational Intelligence (ICAEEC).‏

UdriȘtoiu, A. L., Stanca, A. E., Ghenea, A. E., Vasile, C. M., Popescu, M., UdriȘtoiu, Ș. C., ... & Gruionu, G. (2020). Skin diseases classification using deep leaning methods. Current Health Sciences Journal, 46(2), 136.‏

Chanda, D. et al. A new deep convolutional ensemble network for skin cancer classification. Biomed. Signal. Process. Control. 89, 105757 (2024).

Brancaccio, G., Balato, A., Malvehy, J., Puig, S., Argenziano, G., & Kittler, H. (2024). Artificial intelligence in skin cancer diagnosis: a reality check. Journal of Investigative Dermatology, 144(3), 492-499.‏

Obaid, A. L., Haddad, N. M., & Taha, M. S. (2024, November). DL-SCDDS: Accurate Skin Cancer Detection and Diagnosis Scheme Based on an Improved Convolutional Neural Networks Model. In International Human-Centered Technology Conference (pp. 201-214). Cham: Springer Nature Switzerland.‏

abbar, N. K., Naderan, M., & Taha, M. S. (2025). HybridIoMT: A Dual-Phase Machine Learning Framework for Robust Cybersecurity in Internet of Medical Things. International Journal of Intelligent Engineering & Systems, 18(4).