EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adversarial Training Based Domain Adaptation of Skin Cancer Images

Syed Qasim Gilani, Muhammad Umair, Maryam Naqvi, Oge Marques iD, Hee-Cheol Kim

Life · 14.08.2024 · 14 (8) · 1009

DOI: 10.3390/life14081009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Life, online erschienen am 14.08.2024. Verfasst von Syed Qasim Gilani und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USA. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin lesion datasets used in the research are highly imbalanced; Generative Adversarial Networks can generate synthetic skin lesion images to solve the class imbalance problem, but it can result in bias and domain shift. Domain shifts in skin lesion datasets can also occur if different instruments or imaging resolutions are used to capture skin lesion images. The deep learning models may not perform well in the presence of bias and domain shift in skin lesion datasets. This work presents a domain adaptation algorithm-based methodology for mitigating the effects of domain shift and bias in skin lesion datasets. Six experiments were performed using two different domain adaptation architectures. The domain adversarial neural network with two gradient reversal layers and VGG13 as a feature extractor achieved the highest accuracy and F1 score of 0.7567 and 0.75, respectively, representing an 18.47% improvement in accuracy over the baseline model.

Schlagwörter

Stichwörter der Autor:innen

classificationdeep learningsegmentationskin cancer

Autor:innen und Institutionen

  • Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USA.
  • Department of Electrical and Computer Engineering, Old Dominion University, Norfolk, VA 23529, USA.
  • Institute of Digital Anti-Aging Healthcare, Inje University, Gimhae 50834, Republic of Korea.

ORCID-Profile: Oge Marques

Zitieren

APA

Gilani, S. Q., Umair, M., Naqvi, M., Marques, O., & Kim, H. C. (2024). Adversarial Training Based Domain Adaptation of Skin Cancer Images. Life, 14(8), 1009. https://doi.org/10.3390/life14081009

Vancouver

Gilani SQ, Umair M, Naqvi M, Marques O, Kim HC. Adversarial Training Based Domain Adaptation of Skin Cancer Images. Life. 2024;14(8):1009. doi:10.3390/life14081009

BibTeX
@article{Gilani2024,
  author = {Gilani, Syed Qasim and Umair, Muhammad and Naqvi, Maryam and Marques, Oge and Kim, Hee-Cheol},
  title = {Adversarial Training Based Domain Adaptation of Skin Cancer Images},
  journal = {Life},
  year = {2024},
  volume = {14},
  number = {8},
  pages = {1009},
  doi = {10.3390/life14081009}
}
Kostenlos starten →