Ethical Framework for Responsible Foundational Models in Medical Imaging

Debesh Jha¹Gorkem Durak¹Abhijit Das¹Jasmer Sanjotra¹Onkar Susladkar¹Suramyaa Sarkar¹Ashish Rauniyar¹Nikhil Kumar Tomar¹Linkai Peng¹Sirui Li¹Koushik Biswas¹Ertugrul Aktas¹Elif KELES¹Matthew Antalek¹Zheyuan Zhang¹Bin Wang¹Xin Zhu^1,2Hongyi Pan¹Deniz Seyithanoglu^1,3Alpay Medetalibeyoglu³Vanshali Sharma¹Vedat Çiçek¹Amir Ali Rahsapar¹Rutger Hendrix^1,4A. Enis Cetin²Bulent Aydogan⁵Mohamed Abazeed¹Frank H Miller¹Rajesh N Keswani¹Hatice Savas¹Sachin Jambawalikar⁶Daniela P Ladner¹Amir Ali Borhani¹Concetto Spampinato⁴Michael B Wallace⁷Ulas Bagci^1*

• ¹Northwestern Medicine, Chicago, Illinois, United States
• ²University of Illinois Chicago, Chicago, Illinois, United States
• ³Faculty of Medicine, Istanbul University, Istanbul, Istanbul, Türkiye
• ⁴University of Catania, Catania, Sicily, Italy
• ⁵The University of Chicago, Chicago, Illinois, United States
• ⁶Columbia University, New York City, New York, United States
• ⁷Mayo Clinic Florida, Jacksonville, Florida, United States

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 1 Debesh Jha et al.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 decisionmaking. 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.