Ethical framework for responsible foundational models in medical imaging
Этическая основа ответственного использования базовых моделей в медицинской визуализации
2025-05-19
SCID: 54.1/3dwx322z
Discuss with AI
algorithmic biasfoundation modelshuman oversightmedical imagingpatient data privacy
Figures from the paper
Abstract (AI)
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.
Key Findings
1
Clear development and deployment guidelines are presented as necessary for responsible innovation while preserving medical ethics and patient-centered care.
2
Foundational models offer versatile capabilities for disease detection, diagnosis, and treatment planning across diverse medical imaging applications.
3
Historical disparities in medical datasets may cause foundational models to perpetuate or worsen healthcare inequities among demographic groups.
4
The proposed ethical framework emphasizes privacy safeguards, systematic bias detection and mitigation, and meaningful human oversight.
5
Their clinical integration creates ethical risks involving patient-data privacy, memorization of sensitive information, algorithmic bias, and limited transparency.
Research Object
foundational models for medical imaging in clinical practice
Research Subject
ethical challenges and responsible development and deployment, including privacy, algorithmic bias, transparency, explainability, and human oversight
Publication Details
Publication Date
2025-05-19
Journal
Publisher
ISSN
Cited by
21
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai9
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
A Unified Approach to Interpreting Model Predictions2017
"Why Should I Trust You?": Explaining the Predictions of Any Classifier2016
Advances and Open Problems in Federated Learning2020
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation2021
On the Opportunities and Risks of Foundation Models2021
A multilevel review of artificial intelligence in organizations: Implications for organizational behavior research and practice2023
Ethics and governance of trustworthy medical artificial intelligence2023
Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations (Short Paper)2023