EUVIMEDEUVIMED entdecken
Crossref

Achieve fairness without demographics for dermatological disease diagnosis

Ching-Hao Chiu, Yu-Jen Chen, Yawen Wu, Yiyu Shi, Tsung-Yi Ho

Medical Image Analysis · 2024-07 · 95 · 103188

DOI: 10.1016/j.media.2024.103188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Image Analysis, 2024-07. Verfasst von Ching-Hao Chiu und 4 weiteren Autor:innen. Beteiligte Einrichtung: National Tsing Hua University, No. 101 , Section 2, Kuang-Fu Road, Hsinchu, Taiwan. Electronic address: gwjh101708@gapp.nthu.edu.tw. Hauptthemen laut MEDLINE: Skin Diseases. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In medical image diagnosis, fairness has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and potentially tear society apart. Recent research addresses prediction biases in deep learning models concerning demographic groups (e.g., gender, age, and race) by utilizing demographic (sensitive attribute) information during training. However, many sensitive attributes naturally exist in dermatological disease images. If the trained model only targets fairness for a specific attribute, it remains unfair for other attributes. Moreover, training a model that can accommodate multiple sensitive attributes is impractical due to privacy concerns. To overcome this, we propose a method enabling fair predictions for sensitive attributes during the testing phase without using such information during training. Inspired by prior work highlighting the impact of feature entanglement on fairness, we enhance the model features by capturing the features related to the sensitive and target attributes and regularizing the feature entanglement between corresponding classes. This ensures that the model can only classify based on the features related to the target attribute without relying on features associated with sensitive attributes, thereby improving fairness and accuracy. Additionally, we use disease masks from the Segment Anything Model (SAM) to enhance the quality of the learned feature. Experimental results demonstrate that the proposed method can improve fairness in classification compared to state-of-the-art methods in two dermatological disease datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Skin DiseasesHumansDeep LearningImage Interpretation, Computer-AssistedDemography

Stichwörter der Autor:innen

AI fairnessDermatological disease diagnosisFairness through unawareness

Autor:innen und Institutionen

  • National Tsing Hua University, No. 101 , Section 2, Kuang-Fu Road, Hsinchu, Taiwan. Electronic address: gwjh101708@gapp.nthu.edu.tw.
  • National Tsing Hua University, No. 101 , Section 2, Kuang-Fu Road, Hsinchu, Taiwan.
  • University of Notre Dame, Holy Cross Dr, Notre Dame, IN, USA.
  • The Chinese University of Hong Kong, Shatin, NT, Hong Kong.

Förderung

  • National Institutes of Health

Zitieren

APA

Chiu, C. H., Chen, Y. J., Wu, Y., Shi, Y., & Ho, T. Y. (2024). Achieve fairness without demographics for dermatological disease diagnosis. Medical Image Analysis, 95, 103188. https://doi.org/10.1016/j.media.2024.103188

Vancouver

Chiu CH, Chen YJ, Wu Y, Shi Y, Ho TY. Achieve fairness without demographics for dermatological disease diagnosis. Medical Image Analysis. 2024;95:103188. doi:10.1016/j.media.2024.103188

BibTeX
@article{Chiu2024,
  author = {Chiu, Ching-Hao and Chen, Yu-Jen and Wu, Yawen and Shi, Yiyu and Ho, Tsung-Yi},
  title = {Achieve fairness without demographics for dermatological disease diagnosis},
  journal = {Medical Image Analysis},
  year = {2024},
  volume = {95},
  pages = {103188},
  doi = {10.1016/j.media.2024.103188}
}
Kostenlos starten →