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

arXiv: https://arxiv.org/abs/2507.16207 · HTML: https://mlsanity.com/paper/2507.16207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 55 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 17 of 17)

- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation](https://mlsanity.com/paper/2312.14867/) (2023)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [CT2Rep: Automated Radiology Report Generation for 3D Medical Imaging](https://mlsanity.com/paper/2403.06801/) (2024)
- [GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes](https://mlsanity.com/paper/2305.16037/) (2023)
- [Design Principles for Generative AI Applications](https://mlsanity.com/paper/2401.14484/) (2024)
- [Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for Radiology](https://mlsanity.com/paper/2402.14252/) (2024)
- [RadEdit: stress-testing biomedical vision models via diffusion image editing](https://mlsanity.com/paper/2312.12865/) (2023)
- [Supporting Sensemaking of Large Language Model Outputs at Scale](https://mlsanity.com/paper/2401.13726/) (2024)
- [WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI](https://mlsanity.com/paper/2501.01397/) (2025)
- [On the Horizon: Interactive and Compositional Deepfakes](https://mlsanity.com/paper/2209.01714/) (2022)
- [Next Steps for Human-Centered Generative AI: A Technical Perspective](https://mlsanity.com/paper/2306.15774/) (2023)
- [Medical Image Synthesis via Fine-Grained Image-Text Alignment and Anatomy-Pathology Prompting](https://mlsanity.com/paper/2403.06835/) (2024)
- [A Survey on Responsible Generative AI: What to Generate and What Not](https://mlsanity.com/paper/2404.05783/) (2024)
- [When Two Wrongs Don't Make a Right" -- Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology](https://mlsanity.com/paper/2411.01007/) (2024)

## Abstract (arXiv)

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.