❓Curious if open-source LLMs can generate/validate large clinical datasets? ❓Which LLM is good enough? ❓Fine-tuning🆚prompt optimization? ✅Good news: We tested it on Echocardiography reports &shared our findings!📊 doi.org/10.1101/2024.1… Check it out & share your thoughts!💡

I’m excited to share our recent paper published in AJNR on glioblastoma and tumefactive demyelinating lesions of the brain, with multiple validation steps. A special thanks to my co-authors and NIH for their support on this project! ajnr.org/content/early/…

📚 Systematic reviews are tedious, often requiring days if not weeks of literature digging by experts. ☕️Today, I'm thrilled to introduce LatteReview, a low-code Python framework for automating SRs with multi-agent AI!🤖 💾pip install lattereview 📑arxiv.org/abs/2501.05468 1/🧵

📢 New research from MayoAILab! Dr. Erickson & team have developed a deep learning model that detects early-stage perihilar cholangiocarcinoma (pCCA), a type of bile-duct cancer. Published in Hepatology—congrats! 🔬🧠 Read more: bit.ly/441z4HH #AI #CancerDetection

🌟I’ll be presenting 3 of our works MayoAILab at #ACC25 over the next two days! LLMs, segmentation and ML CVD risk prediction! Excited to share our work and connect with fellow researchers + clinicians passionate about AI🤖and cardiology❤️. Come say hi!👋 American College of Cardiology Brad Erickson

🥳Congratulations to our💫research fellow ManaMoassefi on her outstanding achievement of matching to Mayo Clinic Radiology. Mayo Clinic Radiology Residency Rochester Mayo Clinic Radiology

Excited to share our new review on #GenerativeAI in Medicine! This thorough (20-page) guide is written for all medical professionals, demystifying AI from core concepts (like neural networks) to recent Gen-AI hot topics like RAG & agents. No prior AI background needed. The

Meet the faces behind the code! 🎊 From research discussions to model debugging and breakthrough moments, here’s the Mayo AI-Lab team that working at the intersection of medicine 🩻 and AI 🦾

📄 Our new study published in Journal of Imaging Informatics in Medicine: A cross-institutional evaluation of #LLMs for #radiology diagnosis extraction using a standardized, human-optimized prompt. link.springer.com/article/10.100…

🚀Our latest paper is now published in the Journal of the American Medical Informatics Association (#JAMIA)! 🧠We shared complete prompts and detailed optimization samples! 🔍 Don't miss the supplementary materials for this! academic.oup.com/jamia/article-…

SIIM25 Annual Meeting kicked off with a fantastic keynote by @RohiniKos ! Mayo AI Lab is here and ready to connect! 🤘 Find us at posters, booths, sessions, and all around the venue. Let’s meet and talk the future of imaging AI! ✨🦾 #SIIM25 SIIM

My first SIIM recap: Presented, connected, and had deep talks with inspiring minds working toward the same mission. To all the amazing people I met at #SIIM25 - thank you for being so welcoming, brilliant, and kind. You made my first SIIM truly special! 💫🤘 MayoAILab

Heading back from #SIIM25 with two scientific awards in hand! Huge congrats to David and Bardia - you made us proud! Big thanks to the SIIM family for such an inspiring and unforgettable meeting! 🏆✨

Check out our collection of articles on "Mitigating Bias" from MayoAILab Brad Erickson pubs.rsna.org/page/ai/mitiga… #DeepLearning #Radiomics #ArtificialIntelligence

Recent advances in compact, portable MRI and high-performance gradient inserts promise to increase accessibility to MRI. Mayo Clinic Radiology UTSW Radiology MayoAILab Kevin Zhang Ali Ganjizadeh, M.D., pM.B.A Sanaz(Shanli)Vahdati, MD Brad Erickson bit.ly/43NBrxD

Big thanks to our lab alum Kenneth Phillbrick for hosting us at Google Rochester!🌟We got a behind-the-scenes look at Google Research’s AI for Health efforts. Grateful for the insights, stories, generous exchange of ideas and delicious pizza🧠🍕

Check out our collection of articles on "Mitigating Bias" from MayoAILab Brad Erickson pubs.rsna.org/page/ai/mitiga… #ML #MachineLearning #ArtificialIntelligence

Honored to announce our latest publication: Object-oriented aortic root localization in pre-TAVR CT scan. Thanks to my mentors, Dr Bradley Erickson Brad Erickson , Dr Vinayak Nagaraja and Dr Paul Friedman for their invaluable insights and supervision.