EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Challenges in Reducing Bias Using Post-Processing Fairness for Breast Cancer Stage Classification with Deep Learning

Armin Soltan, Peter Washington

Algorithms · 28.03.2024 · 17 (4) · 141

DOI: 10.3390/a17040141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 28.03.2024. Verfasst von Armin Soltan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Hawaii Health Digital Lab, Information and Computer Science, University of Hawaii at Manoa, Honolulu, HI 96822, USA. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NIMHD NIH HHS, National Institute on Minority Health and Health Disparities of the National Institutes of Health 10.13039/100006545.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast cancer is the most common cancer affecting women globally. Despite the significant impact of deep learning models on breast cancer diagnosis and treatment, achieving fairness or equitable outcomes across diverse populations remains a challenge when some demographic groups are underrepresented in the training data. We quantified the bias of models trained to predict breast cancer stage from a dataset consisting of 1000 biopsies from 842 patients provided by AIM-Ahead (Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity). Notably, the majority of data (over 70%) were from White patients. We found that prior to post-processing adjustments, all deep learning models we trained consistently performed better for White patients than for non-White patients. After model calibration, we observed mixed results, with only some models demonstrating improved performance. This work provides a case study of bias in breast cancer medical imaging models and highlights the challenges in using post-processing to attempt to achieve fairness.

Schlagwörter

Stichwörter der Autor:innen

algorithmic fairnessbreast cancerdeep learningequalized oddsequalized opportunitypost-processing method

Autor:innen und Institutionen

  • Hawaii Health Digital Lab, Information and Computer Science, University of Hawaii at Manoa, Honolulu, HI 96822, USA.

Förderung

  • NIGMS NIH HHS
  • NIMHD NIH HHS
  • National Institute on Minority Health and Health Disparities of the National Institutes of Health 10.13039/100006545

Zitieren

APA

Soltan, A., & Washington, P. (2024). Challenges in Reducing Bias Using Post-Processing Fairness for Breast Cancer Stage Classification with Deep Learning. Algorithms, 17(4), 141. https://doi.org/10.3390/a17040141

Vancouver

Soltan A, Washington P. Challenges in Reducing Bias Using Post-Processing Fairness for Breast Cancer Stage Classification with Deep Learning. Algorithms. 2024;17(4):141. doi:10.3390/a17040141

BibTeX
@article{Soltan2024,
  author = {Soltan, Armin and Washington, Peter},
  title = {Challenges in Reducing Bias Using Post-Processing Fairness for Breast Cancer Stage Classification with Deep Learning},
  journal = {Algorithms},
  year = {2024},
  volume = {17},
  number = {4},
  pages = {141},
  doi = {10.3390/a17040141}
}
Kostenlos starten →