A Human-Centered Approach to Identifying Promises, Risks, & Challenges of Text-to-Image Generative AI in Radiology

TL;DR

This paper explores the potential benefits and risks of using text-to-CT Scan generative AI in radiology through a human-centered approach involving medical professionals, highlighting technical challenges and ethical considerations.

Contribution

It introduces a human-centered evaluation framework for medical text-to-image GenAI, emphasizing stakeholder involvement in assessing its promises, risks, and practical utility.

Findings

Medical professionals see potential in GenAI for education and training.

Technical challenges include image fidelity and accuracy issues.

Stakeholder feedback reveals ethical and safety concerns.

Abstract

As text-to-image generative models rapidly improve, AI researchers are making significant advances in developing domain-specific models capable of generating complex medical imagery from text prompts. Despite this, these technical advancements have overlooked whether and how medical professionals would benefit from and use text-to-image generative AI (GenAI) in practice. By developing domain-specific GenAI without involving stakeholders, we risk the potential of building models that are either not useful or even more harmful than helpful. In this paper, we adopt a human-centered approach to responsible model development by involving stakeholders in evaluating and reflecting on the promises, risks, and challenges of a novel text-to-CT Scan GenAI model. Through exploratory model prompting activities, we uncover the perspectives of medical students, radiology trainees, and radiologists on the role that text-to-CT Scan GenAI can play across medical education, training, and practice. This human-centered approach additionally enabled us to surface technical challenges and domain-specific risks of generating synthetic medical images. We conclude by reflecting on the implications of medical text-to-image GenAI.