Convolutional Neural Network-Based Approach For Skin Lesion Classification
DOI:
https://doi.org/10.56294/dm2023171Keywords:
Skin Cancer, Convolutional Neural Network, Deep Learning, Medical ImagesAbstract
Skin cancer represents one of the primary forms of cancer arising from various dermatological disorders. It can be further categorized based on morphological characteristics, coloration, structure, and texture. Given the rising incidence of skin cancer, its significant mortality rates, and the substantial costs associated with medical treatment, the imperative lies in early detection to promptly diagnose symptoms and initiate appropriate interventions. Traditionally, skin cancer diagnosis and detection involve manual screening and visual examination conducted by dermatologists. these techniques are complex, error-prone, and time-consuming. Machine learning algorithms, particularly deep learning approaches, have been applied to analyze images of skin lesions, detect potential cancerous growths, and provide predictions regarding the likelihood of malignancy. In this paper, we have developed an optimized deep convolutional neural network (DCNN) specifically tailored for classifying skin lesions into benign and malignant categories. Thereby, enhancing the precision of disease diagnosis. Our study encompassed the utilization of a dataset comprising 3,297 dermoscopic images. To enhance the model's performance, we applied rigorous data preprocessing techniques and softmax activation algorithms. The suggested approach employs multiple optimizers, including Adam, RMSProp, and SGD, all configured with a learning rate of 0.0001. The outcomes of our experiments reveal that the Adam optimizer outperforms the others in distinguishing benign and malignant skin lesions within the ISIC dataset, boasting an accuracy score of 84 %, a loss rate of 32 %, a recall rating of 85 %, a precision score of 85 %, a f1-score of 85 %, and a ROC-AUC of 83 %
References
1. WHO. Cancer. Available https://www.who.int/health-topics/cancer#tab=tab_1)
2. N. Chuchu, J. Dinnes, Y. Takwoingi, R.N. Matin, S.E. Bayliss, C. Davenport, J.F. Moreau, O. Bassett, K. Godfrey, C. O'Sullivan, F.M. Walter, R.Motley, J.J. Deeks, and H.C. Williams, “Teledermatology for diagnosing skin cancer in adults”. Cochrane Database of Systematic Reviews, Dec. 2018, doi:10.1002/14651858.cd013193.
3. Maglogiannis and C.N. Doukas, “Overview of Advanced Computer Vision Systems for Skin Lesions Characterization”, IEEE Transactions on Information Technology in Biomedicine, vol. 13, no. 5, pp. 721–733, Sept. 2009, doi:10.1109/titb.2009.2017529.
4. M.S. Ali, M.S. Miah, J. Haque, M.M. Rahman, and M.K. Islam, “An enhanced technique of skin cancer classification using deep convolutional neural network with transfer learning models”, Machine Learning with Applications, vol. 5, article no. 100036, Sept. 2021, doi: 10.1016/j.mlwa.2021.100036.
5. « ISIC | International Skin Imaging Collaboration », ISIC. Consulté le: 23 octobre 2023. [En ligne]. Disponible sur: https://www.isic-archive.com
6. K. Mandal, P. K. D. Sarma, and S. Dehuri, “Image-based Skin Disease Detection and Classification through Bioinspired Machine Learning Approaches”. International Journal on Recent and Innovation Trends in Computing and Communication, vol. 12, no. 1, Sept. 2023, pp. 85–94, doi:10.17762/ijritcc.v12i1.7914.
7. R.O. Ogundokun, A. Li, R.S. Babatunde, C. Umezuruike, P.O. Sadiku, A.T. Abdulahi, and A.N. Babatunde, “Enhancing Skin Cancer Detection and Classification in Dermoscopic Images through Concatenated MobileNetV2 and Xception Models”. Bioengineering, vol. 10, no. 8, article no. 979, Aug. 2023, doi: 10.3390/ bioengineering10080979.
8. N. Nigar, A. Wajid, S. Islam, and M.K. Shahzad, “SKIN CANCER CLASSIFICATION: A DEEP LEARNING APPROACH ”, Pak. J. Sci., vol. 75, no. 02, article no. 02, juill. 2023, doi: 10.57041/pjs.v75i02.851.
9. J. S M, M. P, C. Aravindan, and R. Appavu, “Classification of skin cancer from dermoscopic images using deep neural network architectures”, Multimedia Tools and Applications, vol. 82, no 10, pp. 15763‑15778, 2023, doi: 10.1007/s11042-022-13847-3.
10. Hameed, M. Umer, U. Hafeez, H. Mustafa, A. Sohaib, M. Abubakar Siddique and H. Ahmad Madni, “Skin lesion classification in dermoscopic images using stacked convolutional neural network,” Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 4, pp. 3551–3565, Apr. 2023, doi: 10.1007/s12652-021-03485-2.
11. F. Bozkurt, “Skin lesion classification on dermatoscopic images using effective data augmentation and pre-trained deep learning approach”, Multimedia Tools and Applications, vol. 82, pp. 8985–19003, Nov. 2022, doi: 10.1007/s11042-022-14095-1.
12. R. Saifan and F. Jubair, “Six skin diseases classification using deep convolutional neural network”, Int. J. Electr. Comput. Eng. IJECE, vol. 12, no 3, article no. 3, juin 2022, pp. 3072-3082, doi: 10.11591/ijece.v12i3.pp3072-3082.
13. G. N, M. S, R. R, S. V, S. R. K. V, and S. K. B, “Enhancing Skin Cancer Diagnosis with Deep Learning-Based Classification”, Int. J. Recent Innov. Trends Comput. Commun, vol. 11, no 5s, pp. 105-111, Mai. 2023, doi: 10.17762/ijritcc.v11i5s.6634.
14. S. Albawi, M. H. Arif, and J. Waleed, “Skin cancer classification dermatologist-level based on deep learning model”, Acta Scientiarum. Technology, vol. 45, pp. e61531‑e61531, 2023, doi: 10.4025/actascitechnol.v45i1.61531.
15. Kahia, A. Echtioui, F. Kallel, and A. Ben Hamida, “Skin Cancer Classification using Deep Learning Models”, Proc. The 14th International Conference on Agents and Artificial Intelligence, Vienna, Austria: SCITEPRESS - Science and Technology Publications, 2022, pp. 554‑559. doi: 10.5220/0010976400003116.
16. X. Lu et F. Abolhasani Zadeh, “Deep Learning-Based Classification for Melanoma Detection Using XceptionNet”, J. Healthc. Eng., vol. 2022, article no .2196096, Mars 2022, doi: 10.1155/2022/2196096.
17. Auza-Santiváñez JC, Díaz JAC, Cruz OAV, Robles-Nina SM, Escalante CS, Huanca BA. Bibliometric Analysis of the Worldwide Scholarly Output on Artificial Intelligence in Scopus. Gamification and Augmented Reality 2023;1:11–11. https://doi.org/10.56294/gr202311.
18. Castillo JIR. Aumented reality im surgery: improving precision and reducing ridk. Gamification and Augmented Reality 2023;1:15–15. https://doi.org/10.56294/gr202315.
19. Castillo-Gonzalez W, Lepez CO, Bonardi MC. Augmented reality and environmental education: strategy for greater awareness. Gamification and Augmented Reality 2023;1:10–10. https://doi.org/10.56294/gr202310.
20. Aveiro-Róbalo TR, Pérez-Del-Vallín V. Gamification for well-being: applications for health and fitness. Gamification and Augmented Reality 2023;1:16–16. https://doi.org/10.56294/gr202316.
21. X. Wang, “Deep Learning-based and Machine Learning-based Application in Skin Cancer Image Classification”, J. Phys. Conf. Ser., vol. 2405, article no. 012024, Déc. 2022, doi: 10.1088/1742-6596/2405/1/012024.
22. Convolutional Neural Networks (CNN): Step 1- Convolution Operation - Blogs - SuperDataScience | Machine Learning | AI | Data Science Career | Analytics | Success ». Disponible sur: https://www.superdatascience.com/blogs/convolutional-neural-networks-cnn-step-1-convolution-operation
23. Joel, « When is max pooling exactly applied in convolutional neural networks? », Artificial Intelligence Stack Exchange. Disponible sur: https://ai.stackexchange.com/q/17857.
24. Convolutional Neural Network Tutorial [Update] », Simplilearn.com. Disponible sur: https://www.simplilearn.com/tutorials/deep-learning-tutorial/convolutional-neural-network.
25. Keras, « Keras ». Disponible sur: https://keras.io/.
26. Adam, « Adam ». Disponible sur: https://keras.io/api/optimizers/adam.
27. K. Team, « Keras documentation: RMSprop ». Disponible sur: https://keras.io/api/optimizers/rmsprop/
28. K. Team, « Keras documentation: SGD ». Disponible sur: https://keras.io/api/optimizers/sgd/.
29. « Softmax Activation Function: Everything You Need to Know | Pinecone ». Disponible sur: https://www.pinecone.io/learn/softmax-activation/
30. K. Team, « Keras documentation: ReduceLROnPlateau ». Disponible sur: https://keras.io/api/callbacks/reduce_lr_on_plateau/.
Published
Issue
Section
License
Copyright (c) 2023 Mariame Oumoulylte, Ali Omari Alaoui , Yousef Farhaoui, Ahmad El Allaoui, Abdelkhalak Bahri (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
