Meetings By Mail Decoding Radiology AI A SABI Primer 2025

• Target Audience: radiologists, imaging scientists, technologists
• Sample video: contact me for sample video
• Information:

Release date: October 21, 2025

A source of innovation for nearly fifty years, the Society for Advanced Body Imaging (SABI) presents this exploration into AI fundamentals, practical uses and opportunities for Radiologists at all experience levels.  Decoding Radiology AI: A SABI Primer provides the requisite foundational skills and perspectives to flourish in this constantly evolving technological landscape.

Topics include: Fundamentals, radiomics, large language model integration, reporting, applications for body, cardiothoracic, MSK, neuro, pediatric, breast and nuclear imaging, ethics and bias, generative AI and much more!

The Meetings By Mail: Decoding Radiology AI – A SABI Primer 2025 is best for radiologists, imaging scientists, technologists, and healthcare leaders who want training on how artificial intelligence is reshaping radiology practice. It is designed as a flexible, on‑demand program that introduces AI concepts from fundamentals to clinical applications, with a focus on practical integration into imaging workflows.

Who Should Enroll

Radiologists & imaging specialists seeking to understand and apply AI in diagnostic imaging.

Medical physicists & imaging scientists exploring algorithm development and validation.

Radiology technologists interested in how AI tools affect workflow and image acquisition.

Healthcare administrators & leaders evaluating AI adoption in radiology departments.

Residents, fellows, and trainees in radiology who need structured exposure to AI concepts.

Industry professionals (AI developers, vendors) wanting to align solutions with clinical needs.

What You’ll Learn

AI fundamentals in radiology: machine learning, deep learning, and neural networks explained.

Clinical applications: AI in image interpretation, workflow optimization, and decision support.

Validation & regulation: FDA approval pathways, bias reduction, and ethical considerations.

Case‑based examples: real‑world demonstrations of AI tools in radiology practice.

Future directions: generative AI, multimodal imaging integration, and precision medicine.

• Topics:

Session 1: AI Fundamentals

Introduction to AI Terms and Methods

Jordan Perchik, MD

AI and the User Interface

Dr. Clare Rainey

Q&A: Artificial Intelligence You Need to Know

Multiple Faculty

Radiomics in Pancreatic Tumor Imaging

Richard Do, MD, PhD

Large Language Models Integration Into Radiology Workflow: Potential Applications, Efficacy and Limitations

Soheil Kooraki, MD

Improving Radiology Report Conciseness & Structure Via Large Language Models

Les Folio, DO, MPH

Session 2: Body Imaging Applications

Intelligent Scanning: Using Automated Tools to Improve and Personalize MRI Scans

Angela Tong, MD

AI in Pulmonary Imaging

Steven Rothenberg, MD

Application of AI in Cardiac Imaging

Huma Samar, MBBS

Deep Learning Advances in Cardiopulmonary Imaging– Flow, Structure and Function

Albert Hsiao, MD, PhD

Abdominal Organ Segmentations: The Power of Deep Learning

Martin Prince, MD, PhD

My Favorite App For That

Jordan Perchik, MD

Hot Topics in AI: Updates in Pancreatic Imaging

Linda Chu, MD

Hot Topics in AI: Enhancing Endometriosis Detection: A Deep Learning Approach Using MRI Imaging

Mana Moassefi, MD

Session 3:  Imaging Applications for MSK, Neuro, Breast & More

AI in MSK Imaging

Jake Mandell, MD

AI Applications in Neuroradiology

Marwa Ismail, PhD

AI in Pediatric Imaging

Andrew Smith, MD, PhD

Introduction to AI Applications in Breast Imaging

Mark Traill, MD

AI in Nuclear Imaging

Tyler Bradshaw, PhD

Session 4: Ethics and Bias

Intelligent Imaging: Exploring the Sustainability of Radiology and Radiology AI

Florence Doo, MD

Navigating Bias in Artificial Intelligence for Clinical Radiology: Key Considerations and Challenges

Melina Hosseiny, MD and Rita Maria Lahoud, MD

Ethical Considerations in Imaging AI

Muhammad Umair, MD

Bias in AI: Case Study in Comparing Performance Between US and African Hospitals

Jordan Perchik, MD

Panel Discussion: Should We Let Computers Write Our Reports for Us?

Multiple Faculty

Session 5: Looking Forward . . .

Preparing Radiologists for an AI Enhanced Future: Practical Tips for Trainees

Melina Hosseiny, MD

AI and Its Changing Role in Healthcare

Omer Awan, University of Maryland

Update on AI and Academic Publishing

Eric Tamm, MD, Ali Shah Tejani, MD and Samuel Galgano, MD

ChatGPT & Generative AI: A New Frontier For Healthcare

Florence Doo, MD

Panel Discussion: Generative AI

Multiple Faculty