Influence
August 14, 2025

Exploring the potential of generative artificial intelligence in medical image synthesis: opportunities, challenges, and future directions

Published in The Lancet Digital Health. Here is a link to the article.

Regenstrief Institute authors: Saptarshi Purkayastha, PhD

This viewpoint explores how generative artificial intelligence (AI) is transforming medical imaging through the creation of realistic synthetic datasets. It discusses key AI image generation methods—such as physics-informed and statistical models—and their potential to expand and diversify medical research. The paper highlights the benefits of synthetic data, including enhanced diversity, data privacy, and utility for modeling complex biological processes. Applications include improving medical education, supplementing rare disease data, streamlining radiology workflows, and supporting secure multicenter collaborations. The authors also address ethical and practical challenges, such as patient privacy, data replication, and bias, and call for the development of strong evaluation standards and responsible AI use in medical imaging.

Authors:

Bardia Khosravi 1Saptarshi Purkayastha 2Bradley J Erickson 3Hari M Trivedi 4Judy W Gichoya 5
Affiliations1Department of Radiology, Mayo Clinic, Rochester, MN, USA; Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN, USA.

2Luddy School of Informatics and Computing, Indiana University, Indianapolis, IN, USA.

3Department of Radiology, Mayo Clinic, Rochester, MN, USA.

4Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA, USA.

5Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA, USA.

Related News

Chris Harle, PhD

Supporting electronic health record data usage in research for teams with varying data science and clinical knowledge: a food service analogy approach

Published in the Journal of the American Medical Informatics Association: JAMIA. Here is a link to the article. Regenstrief

Predictive model, comprehensive data identify risk factors for amputation and death among patients with chronic wounds

Predictive model, comprehensive data identify risk factors for amputation and death among patients with chronic wounds

Findings from Regenstrief Institute’s Chronic Wound Registry may help clinicians and patients make informed decisions and improve outcomes  Chronic wounds affect

Brian Dixon, PhD, MPA (left) and Kathleen Unroe, M.D., MHA (right)

Regenstrief researchers give national presentations on public health informatics and aging

Two Regenstrief Institute research scientists were invited to present their work at nationally recognized grand rounds events, highlighting the

Adaptive ethics roadmap guides responsible AI integration in intensive care

Transdisciplinary team develops framework to ensure ethical, transparent AI use in critical care environments Delirium is a common but