An Evaluation of Image Preprocessing in Skin Lesions Detection

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

http://hdl.handle.net/10198/30386

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
An Evaluation of Image Preprocessing.pdf		1.6 MB	Adobe PDF	Download

Send Feedback

Authors

Silva, Giuliana Martins

Lazzaretti, André E.

Monteiro, Fernando C.

Abstract(s)

This study aims to evaluate the impact of image preprocessing techniques on the performance of Convolutional Neural Networks (CNNs) in the task of skin lesion classification. The study is made on the ISIC 2017 dataset, a widely used resource in skin cancer diagnosis research. Thirteen popular CNN models were trained using transfer learning. An ensemble strategy was also employed to generate a final diagnosis based on the classifications of different models. The results indicate that image preprocessing can significantly enhance the performance of CNN models in skin lesion classification tasks. Our best model obtained a balanced accuracy of 0.7879.

Keywords

Skin Lesion Classification Convolutional Neural Networks Deep Learning Image Preprocessing

URI

http://hdl.handle.net/10198/30386

Citation

Silva, Giuliana M.; Lazzaretti, André E.; Monteiro, Fernando C. (2024). An Evaluation of Image Preprocessing in Skin Lesions Detection. In 3rd International Conference on Optimization, Learning Algorithms and Applications (OL2A 2023). Cham: Springer Nature, Vol. 2, p. 35–49. ISBN 978-3-031-53035-7