In this @RSNA #RadAdv review, @FelipeLopezMD et al. provide an overview of the deep learning-based models that have the potential to enhance CT detection of pancreatic tumors. @Hopkins_Rad @OxfordJournals @SusannaLeeRad https://t.co/6d9BwBGGfI

Excited to share our editorial on the potential of vision-language models to enhance scientific communication through automated visual abstracts in @radiology_rsna with my mentor @LindaChuMD.

ICYMI: Vision-language models can now draft visual abstracts for radiology papers, but human oversight remains vital to ensure accuracy and scientific integrity. @LindaChuMD and Dr. @emiramaro of @Hopkins_Rad discuss further in this targeted editorial. https://t.co/sDfMbyiXzj

And huge congratulations to @FelipeLopezMD for winning the Magna Cum Laude award! 🎉⭐️

Feeling incredibly honored and grateful to receive the Young Investigator Award at the SABI Conference 2025! 🏆@SABImaging I’m deeply thankful to my mentors and lab members for their constant guidance. @TheFelixLab @ctisus @LindaChuMD @Hopkins_Rad #SABI2025

Honored to share that our work earned a Magna Cum Laude Award at #SABI2025! 🏆 Thanks to Drs. Elliot Fishman – @ctisus , and @LindaChuMD for their mentorship! @Hopkins_Rad @HopkinsMedicine @lustgartenfdn @SABImaging @TheFelixLab #AI #Radiology #PancreaticCancer #SABI2025

The largest medical #AI randomized controlled trial yet performed, enrolling >100,000 women undergoing mammography screening, was published today @LancetDigitalH The use of A.I. led to 29% higher detection of cancer, no increase of false positives, and reduced workload compared

today we are announcing reinforcement finetuning, which makes it really easy to create expert models in specific domains with very little training data. livestream going now: https://t.co/ABHFV8NiKc alpha program starting now, launching publicly in q1

I mentored a brilliant student Anya Chauhan at the SRI program by @Harvard's @openbio_lab. Check out her project "Digital Patients🤖" 👇 We show that a model trained on a fully synthetic dataset can perform remarkably well on real medical imaging data! 1/n

1/n We are excited to announce EchoPrime – the first echocardiography AI model capable of evaluating a full transthoracic echocardiogram study, identify the most relevant videos, and produce a comprehensive interpretation! Great work lead by @milos_ai, EchoPrime is the largest

arXiv -> alphaXiv Students at Stanford have built alphaXiv, an open discussion forum for arXiv papers. @askalphaxiv You can post questions and comments directly on top of any arXiv paper by changing arXiv to alphaXiv in any URL!

Learn more about the exciting research presented at last month’s Mix & Mingle event, including the winner of and runners-up for the Audience Choice Award:

Vector Database by Hand ✍️ Vector databases are revolutionizing how we search and analyze complex data. They have become the backbone of Retrieval Augmented Generation (#RAG). How do vector databases work? [1] Given ↳ A dataset of three sentences, each has 3 words (or tokens)

SORA by Hand ✍️ OpenAI’s #SORA took over the Internet when it was announced earlier this year. The technology behind Sora is the Diffusion Transformer (DiT) developed by William Peebles and Shining Xie. How does DiT work? 𝗚𝗼𝗮𝗹: Generate a video conditioned by a text prompt

The @UCSDHealth sepsis AI study is the first to show improvement in clinical outcomes with a deep-learning AI model Credit to the team for focusing on workflow, since healthcare AI is about more than algorithms – as the editorial highlights! (5/5) 👉 https://t.co/MXw1ZZ6rnP

I think AI agentic workflows will drive massive AI progress this year — perhaps even more than the next generation of foundation models. This is an important trend, and I urge everyone who works in AI to pay attention to it. Today, we mostly use LLMs in zero-shot mode, prompting

1/n What in the world is Sora's "diffusion transformer model"? A diffusion transformer model is a type of generative model for images, video, and other data that combines transformer architectures with diffusion probabilistic models. Here are some key details: - Diffusion

Use of #AI synthetic notes >300,000 clinic conversations, >3,400 @PermanenteDocs https://t.co/jSXwHjHUs2 —81% Physicians-less screen time during visits and less "pajama time" work on EHR —71% Patients-more time spent speaking w/ physicians —Audit of random 35 notes-high quality

Corrective RAG Proposes Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation in a RAG system. The core idea of this paper is to implement a self-correct component for the retriever and improve the utilization of retrieved documents for

You have a model, that is perfect, but after a while, it starts to perform badly? Model performance decay is a real issue. But what causes it? I will explain in this thread. 🧵