2006–2010       B.A., Neuroscience, Wellesley College    
2010–2012       M.A., Graduate Medical Sciences, Boston University
2013–2017       M.D., Oakland University William Beaumont School of Medicine 

Post-Graduate Education and Training                                                                                   

2017–2018       Preliminary-Medicine Residency, Yale-Waterbury Hospital
2018–2022       Diagnostic Radiology Residency, Mt. Sinai West
2022–2023       Body Imaging Fellowship, Stanford University
2022–2023       Informatics fellowship, American College of Radiology (ACR)

Florence (Flo) Doo, M.D., M.A., CIIP, is an abdominal radiologist, clinical informaticist, and physician innovator.

Dr. Doo is an Assistant Professor and serves as Director of Innovation at the University of Maryland Medical Intelligent Imaging (UM²ii) Center in the Department of Diagnostic Radiology & Nuclear Medicine at the University of Maryland School of Medicine, and also is the Co-lead of the AI-enabled Medical Imaging research team in the Center for Applied AI (CA²i) at the University of Maryland Institute for Health Computing (UM-IHC).

Dr. Doo’s expertise spans clinical radiology, imaging informatics, AI-driven healthcare innovation, and entrepreneurship. She has held local and national leadership positions with prominent medical societies such as the Radiological Society of North America (RSNA), the American College of Radiology (ACR), and the Society for Advanced Body Imaging (SABI). Dr. Doo also serves as the Vice President of Artificial Intelligence in Radiology Education (AIRE) which provides free AI literacy education, and also serves on Board of Governors of the RadDiscord online educational community. She is a recipient of multiple awards, including the RSNA Roentgen Resident/Fellow Research Award, Alpha Omega Alpha (AOA) medical honor society induction, the American Board of Radiology Volunteer Service Award, Outstanding Mentor (for Transformative Impact) at the UMB 48th annual Medical Student Research Day, and recognition as a semifinalist/finalist for Most Influential Radiology Researcher by AuntMinnie.com ("Minnies," in both 2024 and 2025).

Dr. Doo has authored over 50 peer-reviewed publications*, addressing the intersection of medical imaging, climate impacts on health care delivery, and responsible implementation of AI in clinical practice. Her work is currently funded through several prestigious career development and research grants, including the Association of Academic Radiologists Clinical Effectiveness in Radiology Research Academic Fellowship (AAR CERRAF, a foundation career development award supported by GE Healthcare), the  UMMC Innovation Challenge award (for development of a large language model clinical data chatbot), the Mid-Atlantic Center for Cardiometabolic Health  (MACCH, a Johns Hopkins NIH MHHD P50 Center) project grant, and the Johns Hopkins – University of Maryland Baltimore ICTR/NIH CTSA  K12 mentored career development grant award.

Her research program focuses on translating technologies to improve clinical patient care, with a focus on safe/trustworthy and sustainable applications of AI and informatics tools.

*For more on Dr. Doo's publications, please see ResearchGate profile or ORCID link below.

translational AI, clinical AI implementation, artificial intelligence (AI), machine learning, deep learning, large language models (LLMs), generative AI, agentic AI, natural language processing, medical imaging AI, abdominal imaging, clinical informatics, imaging informatics, AI safety, trustworthy AI, human-centered AI, AI evaluation and validation, sustainability, climate and health, population health, innovation, entrepreneurship

For a full list, please refer to ORCiD: https://orcid.org/0000-0001-6519-5222

1. Savage CH, Kanhere A, Parekh V, Langlotz CP, Joshi A, Huang H, Doo FX. Open-Source Large Language Models in Radiology: A Review and Tutorial for Practical Research and Clinical Deployment. Radiology. 2025 Jan;314(1):e241073. doi: 10.1148/radiol.241073. PMID: 39873598; PMCID: PMC11783163.
2. Doo FX, Cook TS, Siegel EL, et al. Exploring the Clinical Translation of Generative Models Like ChatGPT: Promise and Pitfalls in Radiology, From Patients to Population Health. J Am Coll Radiol. 2023;20(9):877-885. doi:10.1016/j.jacr.2023.07.007. PMID: 37467871
3. Doo FX, Vosshenrich J, Cook TS, Moy L, Almeida EPRP, Woolen SA, Gichoya JW, Heye T, Hanneman K. Environmental Sustainability and AI in Radiology: A Double-Edged Sword. Radiology. 2024 Feb;310(2):e232030. doi: 10.1148/radiol.232030. PMID: 38411520; PMCID: PMC10902597.
4. Dogra S, Rifai S, Hadi M, Hanna T, Rozenshtein A, Retrouvey M, Huang H, Doo FX. From Artificial Intelligence to Robotics: How to Navigate Technological Innovation in Radiology With the Gartner Hype Cycle. Acad Radiol. 2026 Mar;33(3):662-679. doi: 10.1016/j.acra.2025.11.018. PMID: 41781096; PMCID: PMC12965137.
5. Doo FX, Lee R, Rockall A, Rula EY, Moy L. Medical Imaging Contrast Media Use. JAMA Netw Open. 2025 Dec 1;8(12):e2547304. doi: 10.1001/jamanetworkopen.2025.47304. PMID: 41348361; PMCID: PMC12681031.

Dr. Doo’s research focuses on translational artificial intelligence (AI) in medical imaging and clinical care. Her primary goal is moving machine learning, deep learning, and advanced AI tools from development into safe, effective, and sustainable real-world clinical use.

Core areas of investigation include:

• Medical imaging & clinical informatics: Advancing data applications, imaging informatics, and population health initiatives across radiology and medical imaging, building on clinical expertise in abdominal imaging and multidisciplinary care.
• Next-generation AI innovation: Exploring and developing novel AI approaches, including agentic AI systems, multimodal large language models (MLLMs), foundation and world models, and advanced reasoning frameworks, to bridge the gap between AI pattern recognition and expert clinical judgment.
• Human-AI safety & trustworthiness: Developing frameworks for AI safety, stress-testing clinical algorithms, and prioritizing human-centered design in clinician-AI interaction.
• AI implementation, evaluation & governance: Leading the clinical translation of AI, including evaluation, validation, workflow integration, and governance of large language models (LLMs) and other AI tools. This includes deploying open-source LLMs and clinical data chatbots to improve radiology workflows and clinical data retrieval.
• Sustainability in AI & medical imaging: Investigating sustainability across the AI lifecycle and imaging practice, from the environmental and climate impact of AI (e.g., model energy use and carbon footprint) and green imaging practices (e.g., contrast media) to the long-term operational sustainability of clinical AI deployment.

Clinicians, data scientists/engineers, industry partners, trainees, and community members are welcome to reach out.

Personal site:
https://flo-doo.github.io/index.html

Center for Applied AI (CA2i), University of Maryland Institute for Health Computing (UM-IHC) site:
https://ihc.umd.edu/research-centers/applied-ai/

University of Maryland Medical Intelligent Imaging Center (UM2ii) Lab site:
https://www.medschool.umaryland.edu/um2ii/