Uncovering ethical biases in publicly available fetal ultrasound datasets.

Journal: NPJ digital medicine
Published Date: Jun 13, 2025

Abstract

We explore biases present in publicly available fetal ultrasound (US) imaging datasets, currently at the disposal of researchers to train deep learning (DL) algorithms for prenatal diagnostics. As DL increasingly permeates the field of medical imaging, the urgency to critically evaluate the fairness of benchmark public datasets used to train them grows. Our thorough investigation reveals a multifaceted bias problem, encompassing issues such as lack of demographic representativeness, limited diversity in clinical conditions depicted, and variability in US technology used across datasets. We argue that these biases may significantly influence DL model performance, which may lead to inequities in healthcare outcomes. To address these challenges, we recommend a multilayered approach. This includes promoting practices that ensure data inclusivity, such as diversifying data sources and populations, and refining model strategies to better account for population variances. These steps will enhance the trustworthiness of DL algorithms in fetal US analysis.

Authors

  • Maria Chiara Fiorentino
    Department of Information Engineering, Università Politecnica delle Marche, Italy. Electronic address: m.c.fiorentino@pm.univpm.it.
  • Sara Moccia
    Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Milan, Italy; Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy. Electronic address: sara.moccia@iit.it.
  • Mariachiara Di Cosmo
    Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy.
  • Emanuele Frontoni
  • Benedetta Giovanola
    Department of Political Sciences, Communication, and International Relations, Università di Macerata, Macerata, Italy.
  • Simona Tiribelli
    Simona Tiribelli is with the Department of Political Sciences, Communication, and International Relations, University of Macerata, Macerata, Italy, and the Institute for Technology and Global Health, Cambridge, MA. Annabelle Monnot is with Polygeia, Global Health Think Tank, Cambridge, UK. Syed F. H. Shah and Anmol Arora are with the School of Clinical Medicine, University of Cambridge, Cambridge. Ping J. Toong is with the Department of Pathology, University of Cambridge. Sokanha Kong is with the Department of Medical Genetics, University of Cambridge.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals