Machine Learning and Deep Learning Algorithms for Skin Cancer Classification from Dermoscopic Images

We carry out a critical assessment of machine learning and deep learning models for the classification of skin tumors. Machine learning (ML) algorithms tested in this work include logistic regression, linear discriminant analysis, k-nearest neighbors classifier, decision tree classifier and Gaussian naive Bayes, while deep learning (DL) models employed are either based on a custom Convolutional Neural Network model, or leverage transfer learning via the use of pre-trained models (VGG16, Xception and ResNet50). We find that DL models, with accuracies up to 0.88, all outperform ML models. ML models exhibit accuracies below 0.72, which can be increased to up to 0.75 with ensemble learning. To further assess the performance of DL models, we test them on a larger and more imbalanced dataset. Metrics, such as the F-score and accuracy, indicate that, after fine-tuning, pre-trained models perform extremely well for skin tumor classification. This is most notably the case for VGG16, which exhibits an F-score of 0.88 and an accuracy of 0.88 on the smaller database, and metrics of 0.70 and 0.88, respectively, on the larger database.

Automated summary

In this study, we critically assessed the performance of machine learning and deep learning models for skin tumor classification. The results showed that deep learning models consistently outperformed machine learning models, with accuracies up to 0.88. Ensemble learning improved the accuracy of machine learning models to 0.75. After fine-tuning, the pre-trained models performed exceptionally well in skin tumor classification, especially VGG16, which achieved an F-score of 0.88 and an accuracy of 0.88 on the smaller database, and metrics of 0.70 and 0.88, respectively, on the larger database.