An Optimized Classification Framework for Skin Lesion Detection Using Machine Learning
Received: 28 June 2025 | Revised: 9 July 2025, 13 July 2025, 17 July 2025, 20 July 2025, 28 July 2025, and 4 August 2025 | Accepted: 14 August 2025 | Online: 21 October 2025
Corresponding author: Shaik Razia
Abstract
This study presented a Machine Learning (ML) evaluation for automated skin lesion classification, utilizing three available datasets: DermNet, PH2, and ISIC. The methodology involved preprocessing steps, including image normalization, Gaussian noise filtering, data augmentation through Random Oversampling and SMOTE, and dimensionality reduction using Principal Component Analysis (PCA). Four classical ML classifiers, including Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbors (k-NN), and Logistic Regression, were trained and examined. Metrics, such as accuracy, precision, recall, and F1-score, highlighted the variations in classifier effectiveness across datasets. The results demonstrated that the RF model achieved the highest accuracy of 99.3% on the ISIC dataset, while SVM yielded great performance on the DermNet and PH2 datasets, with accuracies of 93.1% and 94.2%, respectively. Future work should focus on incorporating Convolutional Neural Networks (CNNs) and non-visual data.
Keywords:
skin lesion detection, machine learning, principal component analysis, class imbalance, classifier performanceDownloads
References
G. G. De Angelo, A. G. C. Pacheco, and R. A. Krohling, "Skin lesion segmentation using deep learning for images acquired from smartphones," in 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, July 2019. DOI: https://doi.org/10.1109/IJCNN.2019.8851803
P. Kaler, S. Kodli, and S. Anakal, "Diagnosis of Skin Cancer Using Machine Learning and Image Processing Techniques," International Journal of Education and Management Engineering, vol. 12, no. 5, pp. 38–45, 2022. DOI: https://doi.org/10.5815/ijeme.2022.05.05
N. Mittal, S. Tanwar, and S. K. Khatri, "Identification & enhancement of different skin lesion images by segmentation techniques," in 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Noida, India, Sept. 2017. DOI: https://doi.org/10.1109/ICRITO.2017.8342500
S. N. Hasan, "Accurate Deep Learning Algorithms for Skin Lesion Classification," International Information and Engineering Technology Association, vol. 29, no. 4, pp. 1529–1539, Aug. 2024. DOI: https://doi.org/10.18280/isi.290426
S. A. Hanum, A. Dey, and M. A. Kabir, "An Attention-Guided Deep Learning Approach for Classifying 39 Skin Lesion Types." arXiv, Jan. 10, 2025.
V. A. Rajendran and S. Shanmugam, "Automated Skin Cancer Detection and Classification using Cat Swarm Optimization with a Deep Learning Model," Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12734–12739, Feb. 2024. DOI: https://doi.org/10.48084/etasr.6681
I. Rahman, M. K. Islam, A. N. Chy, and M. A. Azim, "Fusion of Shallow and Deep Features for Classifying Skin Lesions," in 25th International Conference on Computer and Information Technology (ICCIT), Cox’s Bazar, Bangladesh, Dec. 2022. DOI: https://doi.org/10.1109/ICCIT57492.2022.10055219
S. Gomathi and N. Arunachalam, "Skin Lesion Prediction and Classification Using Innovative Modified Long Short-Term Memory-Based Hybrid Optimization Algorithm," International Journal of Computational Intelligence Systems, vol. 17, no. 1, July 2024, Art. no. 186. DOI: https://doi.org/10.1007/s44196-024-00599-1
D. Kourav and A. Kathal, "Skin Lesion Image Segmentation Based on C-Means Clustering Algorithm," International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 12, pp. 987–990, Oct. 2019. DOI: https://doi.org/10.35940/ijitee.K1306.1081219
A. Upadhyay, A. Chauhan, and D. Kudtarkar, "Skin Lesion Melanoma Detection Using Digital Image Processing," International Journal of Research and Analytical Reviews (IJRAR), vol. 6, no. 1, pp. 44–49, Mar. 2019.
V. Chakkarapani, S. Poornapushpakala, and S. Suresh, "Enhancing Skin Cancer Detection with Multimodal Data Integration: A Combined Approach Using Images and Clinical Notes," SN Computer Science, vol. 6, no. 1, Jan. 2025, Art. no. 72. DOI: https://doi.org/10.1007/s42979-024-03601-x
K. Behara, E. Bhero, and J. T. Agee, "An Improved Skin Lesion Classification Using a Hybrid Approach with Active Contour Snake Model and Lightweight Attention-Guided Capsule Networks," Diagnostics, vol. 14, no. 6, Mar. 2024, Art. no. 636. DOI: https://doi.org/10.3390/diagnostics14060636
Dermnet, Kaggle.
PH2 Dataset, Dataset Ninja.
ISIC Challenge Datasets, ISIC Challenge.
S. Sreena and A. Lijiya, "Skin Lesion Analysis Towards Melanoma Detection," in 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), Kannur, India, July 2019. DOI: https://doi.org/10.1109/ICICICT46008.2019.8993219
P. E. Freer, "Skin Lesions," in Breast Imaging, Onford, UK: Oxford University Press, 2018. DOI: https://doi.org/10.1093/med/9780190270261.003.0050
W. A. Mahdi, S. S. Imam, A. Alotaibi, S. Alhallaf, R. F. Alzhrani, and S. Alshehri, "Formulation and Evaluation of a Silymarin Inclusion Complex-Based Gel for Skin Cancer," ACS Omega, vol. 10, no. 3, pp. 3006–3017, Jan. 2025. DOI: https://doi.org/10.1021/acsomega.4c09614
M. Mansilla-Polo, "Should patients undergoing hematopoietic stem cell transplantation undergo screening and monitoring for skin cancer?," Anais Brasileiros de Dermatologia, vol. 100, no. 2, pp. 372–373, 2025. DOI: https://doi.org/10.1016/j.abd.2024.06.007
R. Zou, J. Zhang, and Y. Wu, "Skin Lesion Segmentation through Generative Adversarial Networks with Global and Local Semantic Feature Awareness.," Electronics, vol. 13, no. 19, Oct. 2024, Art. no. 3853. DOI: https://doi.org/10.3390/electronics13193853
P. Entezari, A. Alaini, H. Mirfazaelian, and Y. Daneshbod, "A cutaneous lesion," Internal and Emergency Medicine, vol. 10, no. 7, pp. 879–880, Oct. 2015. DOI: https://doi.org/10.1007/s11739-015-1234-4
D. Zakria et al., "The Role of Image-Guided Superficial Radiation Therapy in the Treatment of Nonmelanoma Skin Cancer," SKIN The Journal of Cutaneous Medicine, vol. 9, no. 1, pp. 2042–2054, Jan. 2025. DOI: https://doi.org/10.25251/skin.9.1.1
P. Sahu, S. K. Mohapatra, P. K. Sarangi, J. Mohanty, and P. K. Sarangi, "Detection of non-melanoma skin cancer by deep convolutional neural network and stochastic gradient descent optimization algorithm," Journal of Mechanics of Continua amd Mathematical Sciences, vol. 20, no. 1, pp. 59–72, Jan. 2025. DOI: https://doi.org/10.26782/jmcms.2025.01.00005
Downloads
How to Cite
License
Copyright (c) 2025 Shaik Razia, Sivaneasan Balakrishnan, Mohammed Ali Hussain, Prasun Chakrabarti
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
