Conference on Machine Intelligence in Medical Imaging

Benchmarking Quantization: A Comprehensive Comparison of Open-Source Large Language Models

• Blake T. Passe, Mayo Clinic
• Sanaz Vahdati, MD; Bradley J. Erickson, MD, PhD, CIIP, FSIIM

ConTEXTual Net 3D: Visual Grounding in PET/CT for Enhanced Interactive Reporting

• Zachary Huemann, MS, MA, University of Wisconsin – Madison
• Samuel Church, MS; Joshua D. Warner, MD; Daniel Tran; Xin Tie, MS; Junjie Hu, PhD; Steve Y. Cho, MD; Meghan G. Lubner, MD; Tyler J. Bradshaw, PhD

Does Size Really Matter? Comparing llama 3 vs 3.1

• Suyash Khubchandani, MD, MHA, CARPL.ai, Inc
• Amit Kumar; Vasantha K. Venugopal, MD

Large Language Models Create Useful, Accurate, Clear Summaries of Virtual Radiology Workgroup Meetings

• Benjamin Mervak, MD, Michigan Medicine
• Muhammad Bhalli, MBA; Tricia Niedbala, MBA; Kenneth Buckwalter, MD

Synthesizing Diagnostic Insights from Radiology Reports: A RAG-Based LLM Method for Reducing Hallucinations and Preventing Catastrophic Forgetting

• Briana Malik, University of Pittsburgh

Transforming Plain Text Radiology Reports into Structured Data Using Common Data Elements and FHIR Standards

• Michael Hood, MD, Massachusetts General Hospital
• Roshan Fahimi, MD; Heather Chase; Tarik Alkasab, MD, PhD