UHN AI Hub
@UHNAIHUB
A Collaborative Centre at the University Health Network in Toronto designed to augment human intelligence through healthcare innovation.
A new artificial intelligence-driven tool detects the causes of liver graft injury without the need for invasive biopsies. Developed at UHN, GraftIQ is a hybrid model blending clinician expertise with machine learning. Read more: bit.ly/40iODZ3
We're hiring an MLOps Engineer! Join us in transforming healthcare with AI. Tackle complex health system challenges, make a real-world impact, and drive innovation. 🔗Apply now: jobs.smartrecruiters.com/UniversityHeal…
Inspired by tools like ChatGPT, @UHN researchers are creating powerful AI models that can read and understand DNA, RNA and proteins — all at the same time — to better predict how cells behave and how diseases develop ➜ bit.ly/44uZIZB @UHN_Research @BoWang87
Missed our latest AI Rounds? 🎥 Watch the recording of @JunMa_11's insightful talk on foundation models for biomedical image analysis here: youtube.com/watch?v=H1WH7t… Stay tuned for details on our next AI Rounds!
📢 Join in on the AI Hub's upcoming AI Rounds! 🎙️ @JunMa_11, ML Lead at the AI Hub, will share insights on how foundation models are transforming biomedical image analysis. 🗓️ Wednesday, July 9th ⏰ 5pm-6pm Register now!🔗 events.teams.microsoft.com/event/df9f8b81…
Great insights from @BoWang87 in this piece, looking at the road ahead for AI in digital pathology - opportunities, challenges, and what it'll take to get it right.
Just had the pleasure of being interviewed by @Nature on the rise of AI in digital pathology. With growing workloads and global shortages of pathologists, the field is turning to AI not as a luxury—but as a necessity. Full article: nature.com/articles/d4158… In the article, I…
A new commentary examines the shortcomings of Canada’s proposed Artificial Intelligence and Data Act and argues for a more targeted, sector-specific approach to ensure patient safety, transparency, and responsible innovation in future AI legislation. nejm.ai/4ekfI3Q
🎉 Huge milestone: MedSAM has officially surpassed 2,000 citations! 🏆 MedSAM was the first foundation model for medical imaging! When we open-sourced MedSAM, our goal was to empower the entire medical imaging community—and seeing it become a global standard is beyond…
I usually don't talk about preprints, but I will make an exception here: Introducing #MedSAM (Segment Anything in Medical Images arxiv.org/abs/2304.12306) for universal medical image segmentation! 📷 1st attempt adapting SAM to medical domains 📷 Large-scale supervised training…
We're two weeks out from @JunMa_11's presentation at the AI Rounds on how foundation models are transforming biomedical image analysis! Be sure to register if you haven’t already.
📢 Join in on the AI Hub's upcoming AI Rounds! 🎙️ @JunMa_11, ML Lead at the AI Hub, will share insights on how foundation models are transforming biomedical image analysis. 🗓️ Wednesday, July 9th ⏰ 5pm-6pm Register now!🔗 events.teams.microsoft.com/event/df9f8b81…
Learn how @TIER_UHN is revolutionizing cancer care with AI! A newly developed chatbot offers personalized support for metastatic breast cancer patients, enhancing understanding of treatment options and providing timely, reliable information. Read more: bit.ly/4lpSwna
🚨 Excited to share my first-author publication in the prestigious Journal of Hepatology- one of the top avenues for liver research🙏 journal-of-hepatology.eu/article/S0168-… @MamathaBhat3 @CmcintoshAi @bjhasjim @HepHepHourray @TGHRI_UHN @UHNTransplant @UHNAIHUB @UHN_Research @UofT_TCAIREM
🚨 A new study from @TGHRI_UHN’s @MamathaBhat3 & @CmcintoshAi introduces a #MachineLearning tool—Decision Path Similarity Matching (DPSM)—that simulates clinical trial conditions to predict survival, enabling improved clinical decision-making. 🔗doi.org/10.1016/j.jhep…
📢 Join in on the AI Hub's upcoming AI Rounds! 🎙️ @JunMa_11, ML Lead at the AI Hub, will share insights on how foundation models are transforming biomedical image analysis. 🗓️ Wednesday, July 9th ⏰ 5pm-6pm Register now!🔗 events.teams.microsoft.com/event/df9f8b81…
Learn about how multimodal datasets are driving the future of precision oncology in this insightful interview with @bhaibeka. In particular, AI-enabled virtual biopsies have the potential to transform cancer care.
🚨 From the @AACR Annual Meeting: CDI’s @bhaibeka on the frontier of #AIinOncology-- virtual biopsies have the power to transform #cancercare 🧬By integrating imaging & clinical data, multimodal AI models can enable earlier, less invasive diagnostics 🔗technologynetworks.com/cancer-researc…
Biopsies may no longer be the first stop. @UHN’s new #AI tool—GraftIQ—helps diagnose liver graft injuries non-invasively, faster, and more accurately. Read more about this study co-led by Dr. @MamathaBhat3 with global collaborators. ➡️ uhnresearch.ca/news/precision…
How can we make genomic foundation models actually useful to biology?! Teach them to REASON!! 🧬 Excited to share BioReason - the first model to successfully integrate DNA foundation models (eg, Evo 2) with LLMs (eg, Qwen3) for biological reasoning! 🔬 What we built: • Novel…