Enhancing Skin Cancer Classification with Mixup Data Augmentation and Efficientnet
Abstract
Skin lesion classification and segmentation are two crucial tasks in dermatological diagnosis, here automated approaches can significantly aid in early detection and improve treatment planning. The proposed work presents a comprehensive framework that integrates K-means clustering for segmentation, Mixup augmentation for data enhancement, and the EfficientNet B7 model for classification. Initially, K-means clustering is applied as a pre-processing step to accurately segment the lesion regions from the background, ensuring that the model focuses on processing the most relevant and informative features. This segmentation enhances the model’s ability to differentiate between subtle lesion boundaries and surrounding skin textures. To address the common issue of class imbalance and to improve the overall robustness of the classification model, Mixup augmentation is employed. This technique generates synthetic samples by linearly interpolating between pairs of images and their corresponding labels, effectively enriching the training dataset and promoting better generalization. For the classification task, EfficientNet B7 is utilized due to its superior feature extraction capabilities, optimized scalability, and excellent performance across various image recognition challenges. The entire pipeline was evaluated on a dataset comprising 10,015 dermatoscopic images covering seven distinct categories of skin lesions. The proposed method achieved outstanding performance, demonstrating a precision rate of 95.3% and maintaining a low loss of 0.2 during evaluation. Compared to traditional machine learning and earlier deep learning approaches, the proposed framework showed significant improvements, particularly in handling complex patterns and imbalanced datasets, making it a promising solution for real-world clinical deployment in dermatology.
Downloads
References
Melbin, K., Raj, Y.J.V. “Integration of modified ABCD features and support vector machine for skin lesion types classification”, Multimed Tools Appl Vol. 80, pp.8909–8929, 2021, doi: 10.1007/s11042-020-10056-8
Akilandasowmya, G., Nirmaladevi, G., Suganthi, S. U., & Aishwariya, A., “Skin cancer diagnosis: Leveraging deep hidden features and ensemble classifiers for early detection and classification”, Biomedical Signal Processing and Control, Vol. 88, article no.105306, 2024, doi:10.1016/j.bspc.2023.105306
Arun, K. A., & Palmer, M., “Skin cancer detection using deep learning” In 2024 10th International Conference on Communication and Signal Processing (ICCSP), pp. 1712–1717, 2024, doi: 10.1109/ICCSPXYZ.2024.1234567.
Kurtansky, N.R., D’Alessandro, B.M., Gillis, M.C. et al., “The SLICE-3D dataset: 400,000 skin lesion image crops extracted from 3D TBP for skin cancer detection”, Sci Data 11, Vol.88, 2024. Doi: 10.1038/s41597-024-03743-w
Ghosh, H., Rahat, I. S., Mohanty, S. N., Ravindra, J. V. R., & Sobur, A., “A Study on the Application of Machine Learning and Deep Learning Techniques for Skin Cancer Detection”, International Journal of Computer and Systems Engineering, Vol.18, no.1, pp.51–59.
Kavitha, C., Priyanka, S., Kumar, M. P., & Kusuma, V., “Skin Cancer Detection and Classification using Deep Learning Techniques”, Procedia Computer Science, Vol. 235, pp.2793-2802, 2024, doi: 10.1016/j.procs.2024.04.264
Gamil, S., Zeng, F., Alrifaey, M., Asim, M., & Ahmad, N., “An efficient AdaBoost algorithm for enhancing skin cancer detection and classification”, Algorithms, Vol.17, no.8, pp.353, 2024, doi: 10.3390/a17080353.
Wu Y, Chen B, Zeng A, Pan D, Wang R, Zhao S, “Skin Cancer Classification With Deep Learning: A Systematic Review”, Front Oncol, Vol.12, no.7, 2022, doi: 10.3389/fonc.2022.893972.
Ozdemir, B., & Pacal, I., “An innovative deep learning framework for skin cancer detection employing ConvNeXtV2 and focal self-attention mechanisms”, Results in Engineering, Vol.25, article no.103692. doi: 10.1016/j.rineng.2024.103692
Sainudeen, J. P., & V, C. S., “Skin cancer detection: improved deep belief network with optimal feature selection. Multiagent and Grid Systems”, Vol.19, no.2, pp.187-210, 2023, doi: 10.3233/MGS-230040
Renith, G., & Senthilselvi, A. “An efficient skin cancer detection and classification using Improved Adaboost Aphid–Ant Mutualism model”, International Journal of Imaging Systems and Technology, Vol.33, no.6, pp.1957-1972, 2023, doi: 10.1002/ima.22932
Li, Y., Jiao, L., Shang, R., & Stolkin, R. “Dynamic-context cooperative quantum-behaved particle swarm optimization based on multilevel thresholding applied to medical image segmentation”, Information Sciences, Vol.294, pp.408-422, 2015, doi: 10.1016/j.ins.2014.10.005
Ramkumar, K., Medeiros, E. P., Dong, A., de Albuquerque, V. H. C., Hassan, M. R., & Hassan, M. M. “A novel deep learning framework based Swin transformer for dermal cancer cell classification”, Engineering Applications of Artificial Intelligence, Vol.133, article no.108097, 2024, doi: 10.1016/j.engappai.2024.108097.
Mohakud, R., & Dash, R. “Skin cancer image segmentation utilizing a novel EN-GWO based hyper-parameter optimized FCEDN”, Journal of King Saud University-Computer and Information Sciences, Vol.34, no.10, pp.9889-9904, 2021, doi: 10.1016/j.jksuci.2021.12.018
Reis, H. C., & Turk, V. “Fusion of transformer attention and CNN features for skin cancer detection”, Applied Soft Computing, Vol.164, article no. 112013, 2024, doi: 10.1016/j.asoc.2024.112013
Sarwar, N., Irshad, A., Naith, Q. H., D. Alsufiani, K., & Almalki, F. A. “Skin lesion segmentation using deep learning algorithm with ant colony optimization”, BMC Medical Informatics and Decision Making, Vol.24, no1, pp.265, 2024, doi: 10.1186/s12911-024-02686-x
I. de Vere Hunt, J. Lester, E. Linos, “Insufficient evidence for screening reinforces need for primary prevention of skin cancer”, JAMA Intern. Med., Vol.183, no.6, pp.509–511, 2023, doi:10.1001/jamainternmed.2023.0927
R. Javed, M.S.M. Rahim, T. Saba, A. Rehman, “A comparative study of features selection for skin lesion detection from dermoscopic images”, Network Modeling Analysis in Health Informatics and Bioinformatics , Vol.9, pp.1–13, 2020, doi: 10.1007/s13721-019-0209-1
H. Tabrizchi, S. Parvizpour, J. Razmara, “An improved VGG model for skin cancer detection”, Neural Process. Lett. Vol.55, no.4, pp.3715–3732, 2023, doi: 10.1007/s11063-022-10927-1
S.H. Kassani, P.H. Kassani, “A comparative study of deep learning architectures on melanoma detection”, Tissue Cell, Vol.58, pp.76–83, 2019, DOI: 10.1016/j.tice.2019.04.009
A. Adegun, S. Viriri, “Deep learning techniques for skin lesion analysis and melanoma cancer detection: a survey of state-of-the-art”, Artif. Intell. Rev. Vol.54, pp.811–841, 2021, doi: 10.1007/s10462-020-09865-y
Balasamy, K., Seethalakshmi, V. & Suganyadevi, S. “Medical Image Analysis Through Deep Learning Techniques: A Comprehensive Survey”, Wireless Pers Commun, Vol.137, pp.1685–1714, 2024, doi: 10.1007/s11277-024-11428-1
H. Bhatt, V. Shah, K. Shah, R. Shah, M. Shah, “State-of-the-art machine learning techniques for melanoma skin cancer detection and classification: a comprehensive review”, Intelligent Medicine, Vol.3, no.3,pp.180–190, 2023, doi: 10.1016/j.imed.2022.08.004
Maryam Naqvi, et al., “Skin cancer detection using deep learning—a review”, Diagnostics, Vol.13, no.11, pp.1911, 2023, doi: 10.3390/diagnostics13111911
A.M. Smak Gregoor, T.E. Sangers, L.J. Bakker, L. Hollestein, C.A. Uyl–de Groot, T. Nijsten, M. Wakkee, “An artificial intelligence based app for skin cancer detection evaluated in a population based setting”, NPJ digital medicine, Vol.6, no.1, pp.90, 2023, DOI: 10.1038/s41746-023-00831-w
J.V. Tembhurne, N. Hebbar, H.Y. Patil, T. Diwan, “Skin cancer detection using ensemble of machine learning and deep learning techniques”, Multimed. Tool. Appl. , Vol.82, pp. 27501–27524, 2023, doi: 10.1007/s11042-023-14697-3
M. Obayya, M.A. Arasi, N.S. Almalki, S.S. Alotaibi, M. Al Sadig, A. Sayed, “Internet of things-assisted smart skin cancer detection using metaheuristics with deep learning model”, Cancers, Vol.15, no.20, pp.5016, 2023, doi: 10.3390/cancers15205016
N.A. Al-Dmour, M. Salahat, H.K. Nair, N. Kanwal, M. Saleem, N. Aziz, “Intelligence skin cancer detection using IoT with a fuzzy expert system”, 2022 International Conference on Cyber Resilience (ICCR), IEEE, Dubai, United Arab Emirates, 2022, October, pp. 1–6, DOI:10.1109/ICCR56254.2022.9995733
Maryam Tahir, et al., “DSCC_Net: multi-classification deep learning models for diagnosing of skin cancer using dermoscopic images”, Cancers Vol.15, no.7, pp.2179, 2023, doi: 10.3390/cancers15072179
O.T. Jones, R.N. Matin, M. van der Schaar, K.P. Bhayankaram, C.K.I. Ranmuthu, M.S. Islam, F.M. Walter, “Artificial intelligence and machine learning algorithms for early detection of skin cancer in community and primary care settings: a systematic review”, The Lancet Digital Health, Vol.4, no.6, e466–e476, 2022, DOI: 10.1016/S2589-7500(22)00023-1.
Copyright (c) 2025 D. Shamia, R. Umapriya, M.L.M. Prasad, Rini Chowdhury, Prashant Kumar, and K. Vishnupriya
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
