University of Wisconsin–Madison

Dr. McMillan Presents on Foundation Models in AI for Medical Imaging

Alan B. McMillan, PhD, Principal Investigator of the Molecular Imaging Technology Research Program (MITRP), recently delivered two talks emphasizing the growing impact of foundation models in medical imaging. On April 9, 2025, Dr. McMillan presented at the “Clinical Practice Enhanced by Artificial Intelligence Grand Rounds 2025-2026: Artificial Intelligence Applications in Radiology.” His talk, “Artificial Intelligence …

Professor McMillan Named Co-Chair of the Healthcare AI Challenge

We are excited to share that Professor Alan McMillan, Professor of Clinical Health Sciences and Director of the Molecular Imaging/Magnetic Resonance Technology Laboratory (MIMRTL), has been named Co-Chair of the Healthcare AI Challenge alongside Dr. Bernardo Bizzo, Assistant Professor and Senior Director of the Data Science Office at Mass General Brigham (MGB). Shaping the Future …

Professor McMillan Named Co-Director of ICTR Pilot Awards Program

We are pleased to announce that Dr. Alan McMillan, Professor of Clinical Health Sciences in the Department of Radiology and Director of the Molecular Imaging Technology Research Program (MITRP), has been appointed Co-Director of the ICTR Pilot Awards Program. Dr. McMillan will serve alongside Dr. Meghan Brennan and Dr. Chris Sorkness, providing strategic leadership to …

New Study Alert: Embedding-Based AI for Medical Image Classification, A More Efficient Future?

A new arXiv preprint by collaborator Raj Hansini Khoiwal and Molecular Imaging Technology Research Program (MITRP) PI Alan B. McMillan challenges conventional AI training paradigms by demonstrating that pre-trained image embeddings alone can achieve high-performance medical image classification—without traditional model training. Read the full paper: Embeddings are all you need! Achieving High Performance Medical Image …

Evaluating Large Language Models for Technical MRI Expertise: A New Study from MIMRTL

A new arXiv preprint by Alan B. McMillan, PI of MIMRTL, investigates the performance of large language models (LLMs) in answering technical MRI questions, assessing their potential to provide expert-level guidance in real-world clinical settings. The Challenge: Variability in MRI Expertise Magnetic resonance imaging (MRI) is a powerful but technically complex imaging modality. Operator skill …

New paper published: Neural Network Architectures for Self-Supervised Body Part Regression Models with Automated Localized Segmentation Application

Dr. McMillan, Principal Investigator of the MIMRTL group, in collaboration with Michael Fei, currently a medical student at Creighton University, have published a new paper in the Journal of Imaging Informatics in Medicine (JIIM) titled “Technical Note: Neural Network Architectures for Self-Supervised Body Part Regression Models with Automated Localized Segmentation Application.” This work presents advancements …

New arXiv preprint – Enhancing Interpretability in Medical Imaging with Scalable Ensembles

MIMRTL team members, graduate student Weijie Chen and Principal Investigator Alan McMillan, have published a new preprint on arXiv titled “SASWISE-UE: Segmentation and Synthesis with Interpretable Scalable Ensembles for Uncertainty Estimation”. This work introduces a framework aimed at improving the interpretability and reliability of deep learning models in medical imaging. The Challenge of Interpretability in …

New arXiv Paper Published on Bridging the Semantic Gap in Retrieval-Augmented Generation.

A new arXiv preprint, authored by Arihan Yadav, an undergraduate researcher in the Molecular Imaging/Magnetic Resonance Technology Laboratory (MIMRTL), and Alan B. McMillan, the PI of MIMRTL, introduces a novel projection-based method for aligning embeddings across different text modalities. This work presents a significant advancement in Retrieval-Augmented Generation (RAG) systems by improving the ability to …