Volume 15 , Issue 2 , PP: 35-42, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Raya Sattar Shahadha 1 , Belal Al-Khateeb 2 *
Doi: https://doi.org/10.54216/JCIM.150204
Skin cancer detection through deep learning is an evolving field, where convolutional neural networks (CNNs) have proven to be very effective in feature extraction. However, this approach still faces some limitations due to the use of data augmentation, It is the generation of artificial images. Which significantly increase the computational load without generate new clinically meaningful data and may introduce shadowed features. Therefore, this study aims to propose a new approach that use CNNs to extract important features from skin cancer medical images using the HAM 10000 dataset. The proposed approach involves training two different CNN architectures, extracting features from convolutional layers, and then use PCA to make the retrieved features less dimensional. In order to categorize skin cancer into seven different categories of skin lesions, the remaining features are then merged and fed into a classifier that uses neural networks. In comparison to earlier studies that employed CNN architectures on the same dataset, the results demonstrated that this method preserves significant information while improving computational efficiency and achieving superior classification performance. The suggested approach achieved 95.66% accuracy for multi-class classification.
Skin Cancer , Convolutional Neural Network (CNN) , Feature Extraction , Dual CNN , HAM 10000 , Principal Component Analysis (PCA) , Fully Connected Classifier
[1] A. Naeem, M. S. Farooq, A. Khelifi, and A. Abid, “Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities,” IEEE Access, vol. 8, pp. 110575–110597, 2020, doi: 10.1109/ACCESS.2020.3001507.
[2] L. Talavera-Martínez, P. Bibiloni, A. Giacaman, R. Taberner, L. J. D. P. Hernando, and M. González-Hidalgo, “A novel approach for skin lesion symmetry classification with a deep learning model,” Comput. Biol. Med., vol. 145, no. March, 2022, doi: 10.1016/j.compbiomed.2022.105450.
[3] A. A. Mukhlif, B. Al-Khateeb, and M. A. Mohammed, “An extensive review of state-of-the-art transfer learning techniques used in medical imaging: Open issues and challenges,” J. Intell. Syst., vol. 31, no. 1, pp. 1085–1111, 2022, doi: 10.1515/jisys-2022-0198.
[4] L. Alzubaidi et al., Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, vol. 8, no. 1. Springer International Publishing, 2021. doi: 10.1186/s40537-021-00444-8.
[5] S. Malaiarasan, R. Ravi, D. R. Maheswari, C. Yesubai Rubavathi, M. Ramnath, and V. Hemamalini, “Towards Enhanced Deep CNN for Early and Precise Skin Cancer Diagnosis,” Proc. 1st IEEE Int. Conf. Netw. Commun. 2023, ICNWC 2023, pp. 1–7, 2023, doi: 10.1109/ICNWC57852.2023.10127521.
[6] A. Lembhe, P. Motarwar, R. Patil, and S. Elias, “Enhancement in Skin Cancer Detection using Image Super Resolution and Convolutional Neural Network,” Procedia Comput. Sci., vol. 218, pp. 164–173, 2022, doi: 10.1016/j.procs.2022.12.412.
[7] D. Raval and J. N. Undavia, “A Comprehensive assessment of Convolutional Neural Networks for skin and oral cancer detection using medical images,” Healthc. Anal., vol. 3, no. May, p. 100199, 2023, doi: 10.1016/j.health.2023.100199.
[8] M. M. Taye, “Theoretical Understanding of Convolutional Neural Network :,” Mdpi Ag, vol. 11, no. 3, p. 52, 2023.
[9] W. Chen, X. Tan, J. Zhang, G. Du, Q. Fu, and H. Jiang, “A robust approach for multi-type classification of brain tumor using deep feature fusion,” Front. Neurosci., vol. 18, no. February, pp. 1–14, 2024, doi: 10.3389/fnins.2024.1288274.
[10]P.-N. Tan, M. Steinbach, and V. Kumar, Introduction to Data Mining (New International Editon), Pearson Education Limited, England, Essex CM20 2JE, September. 2014.
[11]A. Mankawade, A. Bodhankar, A. Mahajan, D. Prasad, S. Mahajan, and R. Dhakalkar, “Skin Cancer Detection and Intensity Calculator using Deep Learning,” 2023 Int. Conf. Adv. Technol. ICONAT 2023, pp. 1–4, 2023, doi: 10.1109/ICONAT57137.2023.10080001.
[12]K. Mridha, M. M. Uddin, J. Shin, S. Khadka, and M. F. Mridha, “An Interpretable Skin Cancer Classification Using Optimized Convolutional Neural Network for a Smart Healthcare System,” IEEE Access, vol. 11, no. April, pp. 41003–41018, 2023, doi: 10.1109/ACCESS.2023.3269694.
[13]I. N. Nawrin, T. T. Trina, R. Rahman, and A. A. Rasel, “A Comparative Analysis of Deep Learning and Hybrid Models to Diagnose Multi-Class Skin Cancer,” 2023 Int. Conf. Next-Generation Comput. IoT Mach. Learn. NCIM 2023, no. June, pp. 1–6, 2023, doi: 10.1109/NCIM59001.2023.10212670.
[14]M. R. Uddin and T. I. Mahmud, “Dense-par-AttNet: An Attention Based Deep Learning Model for Skin Lesion Classification by Transfer Learning Approach,” 4th IEEE Int. Conf. Artif. Intell. Eng. Technol. IICAIET 2022, pp. 1–5, 2022, doi: 10.1109/IICAIET55139.2022.9936758.
[15]P. Singh, M. Kumar, and A. Bhatia, “A Comparative Analysis of Deep Learning Algorithms for Skin Cancer Detection,” Proc. - 2022 6th Int. Conf. Intell. Comput. Control Syst. ICICCS 2022, no. Iciccs, pp. 1160–1166, 2022, doi: 10.1109/ICICCS53718.2022.9788197.
[16]T. K. Kumar and I. Naga Himanshu, “Artificial Intelligence Based Real-Time Skin Cancer Detection,” 2023 15th Int. Conf. Comput. Autom. Eng. ICCAE 2023, pp. 215–219, 2023, doi: 10.1109/ICCAE56788.2023.10111099.
[17]O. Sevli, “A deep convolutional neural network-based pigmented skin lesion classification application and experts evaluation,” Neural Comput. Appl., vol. 33, no. 18, pp. 12039–12050, 2021, doi: 10.1007/s00521-021-05929-4.
[18]K. Ali, Z. A. Shaikh, A. A. Khan, and A. A. Laghari, “Multiclass skin cancer classification using EfficientNets – a first step towards preventing skin cancer,” Neurosci. Informatics, vol. 2, no. 4, p. 100034, 2022, doi: 10.1016/j.neuri.2021.100034.
