That’s a wrap on the 2021 Radiological Society of North America (RSNA) Annual Meeting, known in shorter form as RSNA21. This year’s event was a hybrid event with the opportunity to connect with others interested in artificial intelligence (AI) in medicine. The UCSF Center for Intelligent Imaging (ci2) was proud of our members who presented on a variety of topics, and we were equally delighted to see the extensive AI programming. Here are a few highlights we wanted to share!
1. Discovering the importance of inclusivity and diversity in healthcare AI.
“When it comes to developing radiology AI, how can we help ensure generalizability?” This topic was discussed at a Lunch and Learn hosted by Kheiron Medical, one of the ci2’s key collaborators. Bonnie Joe, MD, PhD, UCSF ci2 member and chief of Breast Imaging at UCSF Radiology, was part of this panel of experts on inclusivity and diversity in healthcare AI. Overall, AI has the ability and potential to enhance workflows and implement interventions to improve access to care.
2. The Imaging Artificial Intelligence in Practice (IAIP) demonstration.
A much talked about highlight from this year's was the large artificial intelligence (AI) showcase, including an AI in Practice demonstration to highlight how AI is already impacting patient care, to show how AI will change the way radiologists will work and explore what is needed to deploy and maintain AI effectively. "This is the most important work in radiology AI right now - addressing how we move beyond papers and proofs of concept to production deployment of useful AI in imaging centers, hospitals and reading rooms," said John Mongan, MD, PhD, director of translational informatics at the UCSF ci2.
3. The Brain Tumor AI Challenge winner recognition event
This competition focused on brain tumor detection and classification, utilizing multi-parametric magnetic resonance imaging (mpMRI) scans. It represents the culmination of a decade of Brain Tumor Segmentation (BraTS) challenges, offering a large and diverse dataset with detailed annotations and an important associated biomarker. It was organized in a partnership between RSNA and the American Society of Neuroradiology (ASNR) and the Medical Image Computing and Computer Assisted Interventions (MICCAI) Society. Dr. Mongan was a host of the event.
4. A full schedule of lectures, courses, panels, posters and presentations on AI, imaging informatics, machine learning, natural language processing and more.
During RSNA21, UCSF ci2 members were part of a full schedule of expert panels, fireside chats presentations, poster discussions, educational courses and learning labs. Great job by Sharmila Majumdar, PhD, John Mongan, MD, PhD, Spencer Behr, MD, Maggie Chung, MD, Bonnie Joe, MD, PhD, Kimberly Kallianos, MD, Marc Kohli, MD, Jae Ho Sohn, MD, MS, Javier Villanueva-Meyer, MD and Zhen Wang, MD. All of these events provided opportunities to network and learn from fellow AI in healthcare colleagues.
Overall, it was a great annual meeting, and we're looking forward to RSNA22!
