Classification of Malignant and Benign Skin Lesions Using CNN Models
DOI:
https://doi.org/10.36602/ijeit.v14i1.572Keywords:
accuracy, cancer detection, deep learning, performance, skin lesions.Abstract
Dermatology has been transformed through the use of machine learning in health research. By leveraging large data sets and training deep learning models on diverse skin lesion images, researchers have opened the door to improving and modernizing traditional diagnostic methods. This paper aimed to develop a highly effective model for accurately classifying skin cancer images as benign or malignant, thus contributing to early detection. The methodology involved utilizing three custom Convolutional Neural Networks (CNNs) to extract essential features from dermatoscopic images, focusing on characteristics such as the borders of melanoma. Non-cancerous tumors are typically smooth and regular in their edges, while malignant ones have an uneven and rough border. The CNN models were trained on a melanoma dataset comprising images from both benign and malignant cases. Pre- processing steps such as data augmentation were also employed to further improve the performance of the model. The performance of the models was evaluated thoroughly using metrics such as precision, recall, F1 score, and accuracy. By training the models on Melanoma skin cancer, the models provided relatively high accuracies on the validations: 91%, 88%, and 94% for the first, second, and third model, respectively. Additionally, the accuracy for Benign skin cancer is 92%, 89% and 95% for the first, second, and third model, respectively. The third CNN model achieved the best precision and recall with 93% and 95% for Benign skin cancer, and 92% and 94% for Melanoma skin cancer. The third CNN model consistently outperformed the others, offering balanced and superior accuracy in distinguishing between benign and malignant skin cancer cases
Downloads
References
[1] Y. Alsahafi, M. Kassem, and K. Hosny, “Skin-Net: a novel deep residual network for skin lesions classification using multilevel feature extraction and cross-channel correlation with detection of outlier,”Journal of Big Data, vol. 10, no. 1, 2023. doi.org/10.1186/s40537-023- 00769-6.
[2] M. Dildar, et al., “Skin Cancer Detection: A Review Using Deep Learning Techniques,” Int. J. Environ. Res. Public Health, vol. 18, no. 10, 2021.doi.org/10.3390/ijerph18105479.
[3] M. Hossin, et al., “Melanoma skin cancer detection using deep learning and advanced regularizer,” 2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020. doi.org/10.1109/ICACSIS51025.2020.9263118.
[4] R. Ashraf, et al., “an efficient technique for skin cancer classification using deep learning,” Proceedings - 23rd IEEE International Multi-Topic Conference, INMIC 2020, 2020. doi.org/10.1109/INMIC50486.2020.9318164.
[5] M. Javaid, et al., “Significance of machine learning in healthcare: Features, pillars and applications,” international journal of intelligent networks, 2022. doi.org/10.1016/j.ijin.2022.05.002.
[6] R. Gangurde, et al., “Developing an Efficient Cancer Detection and Prediction Tool Using Convolution Neural Network Integrated with Neural Pattern Recognition,” BioMed Research International, 2023. https://doi.org/10.1155/2023/6970256.
[7] A. Abougarair, et al., “Breast Cancer Histopathology Images Detection,” International Conference on Artificial Intelligence and its Applications in the Age of Digital Transformation, Springer conference, Nouakchott, Mauritania, 23-25April, 2024.
[8] A. Oun, et al., “Deep Learning-Based Automated Approach for Classifying Bacterial Images,” International Journal of Robotics and Control Systems, vol.4, no. 2, 2024. doi: 10.31763/ijrcs. v4i2.1423
[9] A. Abdullah, K. Siddique, and T. Shaukat, “An intelligent mechanism to detect multi-factor skin cancer,” Diagnostics, vol. 14, no. 13, p. 1359, 2024. doi: 10.3390/diagnostics14131359.
[10] R. Islam, et al., “SkinNet: A CNN model for improved benign and malignant skin lesion detection,” Proc. IEEE Conf., 2024, pp. 231–236. doi: 10.1109/peeiacon63629.2024.10800037.
[11] S. lsuhibany, et al., “Classification of skin cancer lesions using explainable deep learning,” Sensors, vol. 22, no. 18, p. 6915, 2022. doi: 10.3390/s22186915.
[12] W. Salma and A. Eltrass, “Automated deep learning approach for classification of malignant melanoma and benign skin lesions,” Multimedia Tools Appl., vol. 81, no. 22, pp. 32643–32660, 2022. doi: 10.1007/s11042- 022-13081-x.
[13] N. Lankadasu, D. Pesarlanka, A. Sharma, S. Sharma, and S. Gochhait, “Skin cancer classification using a convolutional neural network: An exploration into deep learning,” Proc. IEEE Conf., 2024, pp. 1047–1052. doi: 0.1109/icetsis61505.2024.10459368.
[14] M. Oumoulylte, A. Alaoui, Y. Farhaoui, A. El Allaoui, and A. Bahri, “Convolutional neural network-based approach for skin lesion classification,” Diagnostics, 2023. doi: 10.56294/dm2023171.
[15] M. Oumoulylte, A. O. Alaoui, Y. Farhaoui, A. El Allaoui, and A. Bahri, “Convolutional neural network-based skin cancer classification with transfer learning models,” Radìoelektronnì ì Komp’ûternì Sistemi, 2023. doi: 10.32620/reks.2023.4.07.
[16] S. Patil and H. Patil, “Modified CNNs for automated binary classification of skin lesions: Benign vs. malignant,” Proc. IEEE Conf., 2023, pp. 958–964. doi: 10.1109/aece59614.2023.10428444.
[17] E. Aslan and Y. Özüpak, “Advanced skin cancer detection using convolutional neural networks and transfer learning,” Middle East J. Sci., 2024. doi: 10.51477/mejs.1592302.
[18] A. John-Otumu, R. Ekemonye, T. Ewunonu, V. O. Aniugo, and O. Okonkwo, “Optimizing CNN kernel sizes for enhanced melanoma lesion classification in dermoscopy images,” Mach. Learn. Res., vol. 9, no. 2, pp. 26– 38, 2024. doi: 10.11648/j.mlr.20240902.11.
[19] N. Lankadasu, D. Pesarlanka, “A. Sharma, S. Sharma, and S. Gochhait, “Skin cancer classification using a convolutional neural network: An exploration into deep learning,” Proc. IEEE Conf., 2024, pp. 1047–1052. doi: 10.1109/icetsis61505.2024.10459368.
[20] J. Seetha, et al., “Computer-aided detection of skin cancer detection from lesion images via deep-learning techniques,” Int. J. Recent Innov. Trends Comput. Commun., vol. 11, no. 2s, pp. 293–302, 2023. doi: 10.17762/ijritcc.v11i2s.6158.
[21] S. Al-Sultan, “Deep learning-based automated diagnosis of skin cancer from thermoscopic images,” J. Univ. Babylon, vol. 32, no. 4, pp. 199–212, 2024. doi: 10.29196/jubpas. v32i4.5533.
[22] M. Singla, K. Gill, M. Kumar, and R. Rawat, “Cutting-edge dermatological advances using deep learning for precise skin cancer classification,” Proc. IEEE Conf., 2024. doi: 10.1109/icsses62373.2024.10561393.
[23] E. Hamed, M. Salem, N. Badr, and M. Tolba, “A deep learning-based classification framework for annotated histopathology lung cancer images,” Proc. Int. Conf., 2023, pp. 86–94. doi: 10.1007/978-3-031- 43247-7_8.
[24] H. Nair, et al., “Melanoma skin cancer prediction using machine learning algorithm,” Deleted J., vol. 2, no. 12, pp. 3703–3709, 2024. doi: 10.47392/irjaem.2024.0550.
[25] T. Mahmood, J. Li, Y. Pei, F. Akhtar, M. Rehman, and S. Wasti, “Breast lesions classifications of mammographic images using a deep convolutional neural network-based approach,” PLOS ONE, vol. 17, no. 1, p. e0263126, 2022. doi: 10.1371/journal.pone.0263126.
[26] A. Ajel, A. Al-Dujaili, Z. G. Hadi, and A. J. Humaidi, “Skin cancer classifier based on convolution residual neural network,” Int. J. Electr. Comput. Eng., vol. 13, no. 6, pp. 6240–6248, 2023. doi: 10.11591/ijece. v13i6.pp6240-6248.
[27] T. Nivyashree and P. V. Pramila, “Detection of malignant and benign skin lesions using the influence of activation function and accuracy analysis in densely connected convolutional network compared over convolutional neural network,” Proc. IEEE Conf., 2023, pp. 1–6. doi: 10.1109/iccebs58601.2023.10448550.
[28] R. Sahu and A. Dash, “Identification of malignant cells using convolutional neural network,” in Proc. IEEE Conf., 2023, pp. 01–06. doi: 10.1109/ccpis59145.2023.10291907.
[29] R. Mhedbi, H. Chan, P. Credico, R. Joshi, J. Wong, and C. Hong, “A convolutional neural network-based system for classifying malignant and benign skin lesions using mobile-device images,” medRxiv, 2023. doi: 10.1101/2023.12.06.23299413.
[30] M. Abugarir, et al., CNNs for Automatic Skin Cancer Classification,” Journal of Advances in Artificial Intelligence, Vol. 2, Num. 2, 2024.doi: 10.18178/JAAI.2024.2.2.218-234
[31] F. Thabit, et al., “Blood Cells Cancer Detection Based on Deep Learning,” Journal of Advances in Artificial Intelligence, Volume 2, Number 1, 2024. DOI: 10.18178/JAAI.2024.2.1.108-121.
[32] C. Fanconi, S“kin cancer: malignant vs. Benign, processed skin cancer pictures of the ISIC archive Kaggle dataset, https://www.kaggle.com/fanconic/skin-cancer-malignant-vs benign.
[33] M. Dildar, S. Akram, M. Irfan et al., “Skin cancer detection: a review using deep learning techniques,” International Journal of Environmental Research and Public Health, vol. 18, no. 10, pp. 1–22, 2021.
[34] M. Hasan, et al., “Skin cancer detection using convolutional neural network,” Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence-ICCAI 19, pp. 254–258, Association for Computing Machinery, New York, NY, USA, 2019.
[35] T. Yue, et al., “An experimental study on breast lesion detection and classification from ultrasound images using deep learning architectures,” BMC Medical Imaging, vol. 19, no. 1, 2019.
[36] O. Salih, et al., “FFT-Assisted U-Net Architecture for Improved Skin Lesion Segmentation,” IEEE 3rd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA2023), 21-23 May,2023, Benghazi, Libya.
[37] O. Salih, et al., “An Overview of Skin Lesion Segmentation Methods: Techniques, Challenges, and Future Directions,” IEEE 3rd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA2023), 21-23 May,2023, Benghazi, Libya.
[38] S. Elghany, et al., “Diagnosis of various skin cancer lesions based on fine-tuned Resnet50 deep network, Computers,” Materials & Continua, vol. 68, no. 1, pp. 117–135, 2021.
[39] D. Renza, et al., “Fake banknote recognition using deep learning,” Applied Sciences, vol. 11, no. 3, p. 1281, 2021.
[40] A. Abougarair, “Optimal Control Synthesis of Epidemic Model,” IJEIT International Journal on Engineering and Information Technology, vol.8, no. 2, Misrata, June 2022, Special Issue for the International Engineering Conference IEC2022 MU.
[41] W. Elside, “Traffic Sign Recognition Using CNN,” Journal of Advances in Artificial Intelligences, Vol.3, Number 1, 2025.
[42] M. Bakouri, et al. “Optimizing cancer treatment using optimal control theory,” AIMS Mathematics, 2024, Volume 9, Issue 11: 31740-31769. doi: 10.3934/math.20241526
[43] S. Sawan, et al., “Cancer Treatment Precision Strategies Through Optimal Control Theory,” Journal of Robotics and Control (JRC), Vol. 5, Issue 5, pp. 1261-1290, 2024.
[44] I. Alkaber, et al., “Comparative Evaluation of PID Controller Tuning through Conventional and Genetic Algorithm,” IEEE 4th International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA), Tripoli, Libya, 19-21 May 2024.
[45] S. Elwefati, et al., “Identification and Control of Epidemic Disease Based Neural Networks and Optimization Technique,” International Journal of Robotics and Control Systems, 3(4),780-803, 2023.
[46] A. Ma’arif, et al., “Model Predictive Control for Optimizes Battery Charging Process,”IEEE 4th International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA), Tripoli, Libya, 19-21 May 2024.
[47] A. Abougarair, “Adaptive Neural Networks Based Optimal Control for Stabilizing Nonlinear System,” IEEE 3rd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA2023), 21-23 May,2023, Benghazi, Libya.
[48] I. Buzkhar, “Modeling and Control of a Two Wheeled Robot Machine with a Handling Mechanism,” IEEE 3rd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA2023), 21-23 May,2023, Benghazi, Libya.
[49] A. Abougarair, “Real Time Classification for Robotic Arm Control Based Electromyographic Signal, 2022 IEEE 2st International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA2022), 23-25 may,2022, Sabrata, Libya.
[50] M. Aburakhis, et al., “Adaptive Neural Networks Based Robust Output Feedback Controllers for Nonlinear Systems,” International Journal of Robotics and Control Systems, Vol. 2, No. 1, 2022, pp. 37-56, ISSN: 2775-2658, http://pubs2.ascee.org/index.php/ijrcs
[51] M. Bakush, et al., “Control of Epidemic Disease Based Optimization Technique,” IEEE 1st International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA2021),25-27 may,2021, Tripoli, Libya.
[52] H. Gnan, et al., “Implementation of a Brain-Computer Interface for Robotic Arm Control,” IEEE 1st International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA2021),25-27 may,2021, Tripoli, Libya.
[53] A. Abougarair, “Position and Orientation Control of a Mobile Robot Using Intelligent Algorithms Based Hybrid Control Strategies,” Journal of Engineering Research, Issue (34), pp 67-86, September 2022.
[54] A. Abougarair, “Model Reference Adaptive Control And Fuzzy Optimal Controller For Mobile Robot,” Journal of Multidisciplinary Engineering Science and Technology, pp 9722-9728,Vol. 6, Issue 3, 2019, Germany.
[55] M. Edardar et al., “Tracking control with hysteresis compensation using neural networks,” 2021 IEEE 1st International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering MI-STA, pp. 36-40, 25-27 May 2021.
[56] M. Edardar et al., “Lyapunov Redesign of Piezo-Actuator for Positioning Control,” 9th International Conference on Systems and Control (ICSC), Caen, France, pp. 499-503, 2021.
[57] W. Arebi et. al., “Smart glove for sign language translation,” International Robotics & Automation Journal, vol. 8, issue 3, pp. 109-117, 2022.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2025 The International Journal of Engineering & Information Technology (IJEIT)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
