Deep Learning for Early Detection of Skin Cancer: Towards AI-Assisted Dermatology

Affaf Khaouane; Hadjer Barki; Samira Ferhat; salah Hanini

Affaf Khaouane yahia fares university of medea
Hadjer Barki university of medea algeria
Samira Ferhat university of medea algeria
salah Hanini university of medea algeria

Keywords: Skin Cancer, Deep Learning, Transfer Learning, Feature Extraction, Neural Networks, Image Classification, Dermatology, Medical Imaging.

Abstract

Skin cancer remains one of the most common and potentially fatal diseases, necessitating early and precise diagnosis for effective intervention. This study introduces a deep learning-based framework for skin cancer classification, employing transfer learning with AlexNet and convolutional neural network (CNN)-based feature extraction coupled with a neural network classifier. A dataset of 160 dermoscopic images (80 cancerous and 80 non-cancerous) was curated from publicly available sources and preprocessed to eliminate duplicates. Two models were developed: (1) CNN_TransferLearning, which involved fine-tuning AlexNet on the dataset, and (2) CNN_Features_NN, where deep features extracted from the CNN were used to train a neural network. Model performance was assessed through internal validation on a validation set and external validation on an independent test set. The CNN_Features_NN model demonstrated superior performance in external validation, achieving an accuracy of 96%, with precision = 0.93, recall = 1, F1-score = 0.96, and specificity = 0.90. These results surpass the diagnostic accuracy of many traditional methods and approach the performance of experienced dermatologists. The robustness of the model was further validated using applicability domain analysis via the leverage method, ensuring reliable classification of unseen images. These results underscore the potential of deep learning in automating skin cancer detection, offering a valuable tool for clinical practice to reduce diagnostic errors and improve patient outcomes.

References

1. Mogensen M, Jemec GB. Diagnosis of nonmelanoma skin cancer/keratinocyte carcinoma: a review of diagnostic accuracy of nonmelanoma skin cancer diagnostic tests and technologies. Dermatologic Surgery. 2007;33(10):1158-74.
2. Lui H, Zhao J, McLean D, Zeng H. Real-time Raman spectroscopy for in vivo skin cancer diagnosis. Cancer research. 2012;72(10):2491-500.
3. Anushree U, Shetty S, Kumar R, Bharati S. Adjunctive Diagnostic Methods for Skin Cancer Detection: A Review of Electrical Impedance‐Based Techniques. Bioelectromagnetics. 2022;43(3):193-210.
4. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. nature. 2017;542(7639):115-118.
5. Tschandl P, Rosendahl C, Kittler H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data. 2018;5(1):1-9.
6. Qin Z, Liu Z, Zhu P, Xue Y. A GAN-based image synthesis method for skin lesion classification. Computer Methods and Programs in Biomedicine. 2020;195:105568.
7. Harangi B. Skin lesion classification with ensembles of deep convolutional neural networks. Journal of biomedical informatics. 2018;86:25-32.
8. Gessert N, Nielsen M, Shaikh M, Werner R, Schlaefer A. Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data. MethodsX. 2020;7:100864.
9. Mahbod A, Schaefer G, Wang C, Ecker R, Ellinge I, editors. Skin lesion classification using hybrid deep neural networks. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2019: IEEE.
10. Nasr-Esfahani E, Samavi S, Karimi N, Soroushmehr SMR, Jafari MH, Ward K, et al., editors. Melanoma detection by analysis of clinical images using convolutional neural network. 2016 38th annual international conference of the IEEE engineering in medicine and biology society (EMBC); 2016: IEEE.
11. Kawahara J, Daneshvar S, Argenziano G, Hamarneh G. Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE journal of biomedical and health informatics. 2018;23(2):538-46.
12. Brinker TJ, Hekler A, Utikal JS, Grabe N, Schadendorf D, Klode J, et al. Skin cancer classification using convolutional neural networks: systematic review. Journal of medical Internet research. 2018;20(10):e11936.
13. Wu Y, Chen B, Zeng A, Pan D, Wang R, Zhao S. Skin cancer classification with deep learning: a systematic review. Frontiers in Oncology. 2022;12:893972.
14. KABIR F. skin-cancer-dataset: kaggle Database; Available from: https://www.kaggle.com/datasets/farjanakabirsamanta/skin-cancer-dataset?select=Skin+Cancer.
15. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 2012;25.
16. Lu S, Lu Z, Zhang Y-D. Pathological brain detection based on AlexNet and transfer learning. Journal of computational science. 2019;30:41-47.
17. Huang C, Geiger E, Kupfer J. Sensitivity of landscape metrics to classification scheme. International Journal of Remote Sensing. 2006;27(14):2927-2948.
18. Mustafa B, Loh A, Freyberg J, MacWilliams P, Wilson M, McKinney SM, et al. Supervised transfer learning at scale for medical imaging. arXiv preprint arXiv:210105913. 2021.
19. Hirano H, Minagi A, Takemoto K. Universal adversarial attacks on deep neural networks for medical image classification. BMC medical imaging. 2021;21:1-13.
20. Abdar M, Samami M, Mahmoodabad SD, Doan T, Mazoure B, Hashemifesharaki R, et al. Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning. Computers in biology and medicine. 2021;135:104418.
21. Bian J, Zhang S, Wang S, Zhang J, Guo J. Skin lesion classification by multi-view filtered transfer learning. IEEE Access. 2021;9:66052-66061.
22. Alzubaidi L, Al-Amidie M, Al-Asadi A, Humaidi AJ, Al-Shamma O, Fadhel MA, et al. Novel transfer learning approach for medical imaging with limited labeled data. Cancers. 2021;13(7):1590.
23. Li H, Wang Y, Wan R, Wang S, Li T-Q, Kot A. Domain generalization for medical imaging classification with linear-dependency regularization. Advances in neural information processing systems. 2020;33:3118-3129.
24. Zunair H, Hamza AB. Melanoma detection using adversarial training and deep transfer learning. Physics in Medicine & Biology. 2020;65(13):135005.
25. Huq A, Pervin MT, editors. Analysis of adversarial attacks on skin cancer recognition. 2020 International Conference on Data Science and Its Applications (ICoDSA); 2020: IEEE.
26. Gu Y, Ge Z, Bonnington CP, Zhou J. Progressive transfer learning and adversarial domain adaptation for cross-domain skin disease classification. IEEE journal of biomedical and health informatics. 2019;24(5):1379-1393.
27. Wei Z, Song H, Chen L, Li Q, Han G. Attention-based DenseUnet network with adversarial training for skin lesion segmentation. IEEE Access. 2019;7:136616-136629.
28. Roy K, Kar S, Ambure P. On a simple approach for determining applicability domain of QSAR models. Chemometrics and Intelligent Laboratory Systems. 2015;145:22-29.
29. Hanser T, Barber C, Marchaland J, Werner S. Applicability domain: towards a more formal definition. SAR and QSAR in Environmental Research. 2016;27(11):865-881.
30. Organisation for Economic Co-operation and Development (OECD). Guidance Document on the Validation of (Quantitative) Structure-Activity Relationship [(Q)SAR] Models. Paris: OECD Publishing available from http://www.oecd.org.; 2014.