EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Bias Analysis and Data Augmentation Strategies in Skin Lesion Classification

Thiago Meneses Lopes, Martin Heckmann, Marcelo Ponciano da Silva, Pedro Henrique Bugatti, Priscila Tiemi Maeda Saito

Revista de Informática Teórica e Aplicada · 16.03.2026 · 33 (2) · 348-355

DOI: 10.22456/2175-2745.150974 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Revista de Informática Teórica e Aplicada, online erschienen am 16.03.2026. Verfasst von Thiago Meneses Lopes und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early detection of skin cancer is vital for effective treatment and improving patient recovery. In recent years, a growing number of computer vision studies have been developed to aid in diagnosis, drawing significant attention from researchers. However, challenges still persist, such as data imbalance and the lack of comprehensive datasets. Additionally, limited research has focused on how variations in skin tone across different populations affect the performance of models in skin lesion classification. This study seeks to create a more effective approach to address data biases in lesion classification across diverse skin tones. We initially explored several data augmentation techniques, employing traditional feature extractors for image analysis. For classification, models such as k-Nearest Neighbor, Random Forest, and Support Vector Machine were used. This study focused on two well-known and publicly available skin lesion datasets: HAM10000 and PAD-UFES-20, both of which have significant class imbalances. Further experiments were conducted to assess potential biases, with the Individual Typology Angle (ITA) metric applied to evaluate the skin tone distribution within the datasets.

Zitieren

APA

Lopes, T. M., Heckmann, M., Silva, M. P. D., Bugatti, P. H., & Saito, P. T. M. (2026). Bias Analysis and Data Augmentation Strategies in Skin Lesion Classification. Revista de Informática Teórica e Aplicada, 33(2), 348-355. https://doi.org/10.22456/2175-2745.150974

Vancouver

Lopes TM, Heckmann M, Silva MPD, Bugatti PH, Saito PTM. Bias Analysis and Data Augmentation Strategies in Skin Lesion Classification. Revista de Informática Teórica e Aplicada. 2026;33(2):348-355. doi:10.22456/2175-2745.150974

BibTeX
@article{Lopes2026,
  author = {Lopes, Thiago Meneses and Heckmann, Martin and Silva, Marcelo Ponciano da and Bugatti, Pedro Henrique and Saito, Priscila Tiemi Maeda},
  title = {Bias Analysis and Data Augmentation Strategies in Skin Lesion Classification},
  journal = {Revista de Informática Teórica e Aplicada},
  year = {2026},
  volume = {33},
  number = {2},
  pages = {348--355},
  doi = {10.22456/2175-2745.150974}
}
Kostenlos starten →