Deep learning techniques applied to skin lesion classification: a review

Silva, Giuliana Martins; Lazzaretti, Andre E.; Monteiro, Fernando C.

http://hdl.handle.net/10198/27583

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Deep_Learning_Techniques_Applied_to_Skin_Lesion_Classification_A_Review.pdf		155.4 KB	Adobe PDF	Download

Send Feedback

Authors

Silva, Giuliana Martins

Lazzaretti, Andre E.

Monteiro, Fernando C.

Abstract(s)

Skin cancer is one of the most common cancers in the world. The most dangerous type of skin cancer is melanoma, which can be lethal if not treated early. However, diagnosing skin lesions can be a difficult task. Therefore, deep learning techniques applied to the diagnosis of skin lesions have been explored by researchers, given their effectiveness in extracting features and classifying input data. In this work, we present a review of latest approaches that apply deep learning techniques to skin lesion classification task. In addition, some datasets used for training and validating the models are introduced, informing their characteristics and specificities, as well as popular pre-processing steps and skin lesion segmentation approaches. Finally, we comment the effectiveness of the proposed models.

Keywords

Deep learning Melanoma Skin diseases Skin lesion classification Skin lesion segmentation

URI

http://hdl.handle.net/10198/27583

Citation

Silva, Giuliana M.; Lazzaretti, Andre E.; Monteiro, Fernando C. (2022). Deep learning techniques applied to skin lesion classification: a review. In International Conference on Machine Learning, Control, and Robotics, MLCR 2022. Suzhou - China. p. 106 - 111