Ethical framework for responsible foundational models in medical imaging
Frontiers in Medicine · 19.05.2025 · 12
DOI: 10.3389/fmed.2025.1544501 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Frontiers in Medicine, online erschienen am 19.05.2025. Verfasst von Debesh Jha und 35 weiteren Autor:innen. Beteiligte Einrichtung: Machine and Hybrid Intelligence Lab, Department of Radiology, Northwestern University, Chicago, IL, United States. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institutes of Health.
Abstract (Originalsprache)
The emergence of foundational models represents a paradigm shift in medical imaging, offering extraordinary capabilities in disease detection, diagnosis, and treatment planning. These large-scale artificial intelligence systems, trained on extensive multimodal and multi-center datasets, demonstrate remarkable versatility across diverse medical applications. However, their integration into clinical practice presents complex ethical challenges that extend beyond technical performance metrics. This study examines the critical ethical considerations at the intersection of healthcare and artificial intelligence. Patient data privacy remains a fundamental concern, particularly given these models' requirement for extensive training data and their potential to inadvertently memorize sensitive information. Algorithmic bias poses a significant challenge in healthcare, as historical disparities in medical data collection may perpetuate or exacerbate existing healthcare inequities across demographic groups. The complexity of foundational models presents significant challenges regarding transparency and explainability in medical decision-making. We propose a comprehensive ethical framework that addresses these challenges while promoting responsible innovation. This framework emphasizes robust privacy safeguards, systematic bias detection and mitigation strategies, and mechanisms for maintaining meaningful human oversight. By establishing clear guidelines for development and deployment, we aim to harness the transformative potential of foundational models while preserving the fundamental principles of medical ethics and patient-centered care.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Machine and Hybrid Intelligence Lab, Department of Radiology, Northwestern University, Chicago, IL, United States.
- Sustainable Communication Technologies, SINTEF Digital, Trondheim, Norway.
- Department of Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, IL, United States.
- Department of Electrical and Computer Engineering, University of Catania, Catania, Italy.
- Department of Radiation Oncology, University of Chicago, Chicago, IL, United States.
- Department of Radiation Oncology, Northwestern University, Chicago, IL, United States.
Förderung
- National Institutes of Health
Zitieren
APA
Jha, D., Durak, G., Das, A., Sanjotra, J., Susladkar, O., Sarkar, S., Rauniyar, A., Kumar Tomar, N., Peng, L., Li, S., Biswas, K., Aktas, E., Keles, E., Antalek, M., Zhang, Z., Wang, B., Zhu, X., Pan, H., Seyithanoglu, D., …, & Bagci, U. (2025). Ethical framework for responsible foundational models in medical imaging. Frontiers in Medicine, 12. https://doi.org/10.3389/fmed.2025.1544501
Vancouver
Jha D, Durak G, Das A, Sanjotra J, Susladkar O, Sarkar S, et al. Ethical framework for responsible foundational models in medical imaging. Frontiers in Medicine. 2025;12. doi:10.3389/fmed.2025.1544501
BibTeX
@article{Jha2025,
author = {Jha, Debesh and Durak, Gorkem and Das, Abhijit and Sanjotra, Jasmer and Susladkar, Onkar and Sarkar, Suramyaa and Rauniyar, Ashish and Kumar Tomar, Nikhil and Peng, Linkai and Li, Sirui and Biswas, Koushik and Aktas, Ertugrul and Keles, Elif and Antalek, Matthew and Zhang, Zheyuan and Wang, Bin and Zhu, Xin and Pan, Hongyi and Seyithanoglu, Deniz and Medetalibeyoglu, Alpay and Sharma, Vanshali and Cicek, Vedat and Rahsepar, Amir A and Hendrix, Rutger and Cetin, A Enis and Aydogan, Bulent and Abazeed, Mohamed and Miller, Frank H and Keswani, Rajesh N and Savas, Hatice and Jambawalikar, Sachin and Ladner, Daniela P and Borhani, Amir A and Spampinato, Concetto and Wallace, Michael B and Bagci, Ulas},
title = {Ethical framework for responsible foundational models in medical imaging},
journal = {Frontiers in Medicine},
year = {2025},
volume = {12},
doi = {10.3389/fmed.2025.1544501}
}
EUVIMED