🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

#AI Agents in #Radiology: The Future of Intelligent Workflows pubs.rsna.org/page/ai/blog/2… Bardia Khosravi, MD Yale Department of Radiology & Biomedical Imaging Penn Radiology Residents #agent #AgenticAI #LLMs

Since dehydration during conferences is a serious thing: 😄🍎 avoid next day AKI! SIIM #siim2025

🚀 Attending #SIIM25? Don't miss the AI Playground! Test cutting-edge LLMs (o4-mini, Gemini, Claude, etc) head-to-head in our SIIM LLM Arena and experience the latest breakthroughs in medical AI firsthand. See which models truly deliver on their promises! 🤖⚡ SIIM

Radiology’s Challenge for the Next 5 Years: Figure out how to double imaging capacity while halving the time necessary for interpretation, with similar or better quality. Is AI the answer? ajnr.org/content/45/12/…

Excited to officially launch the Chameleon Dataset at #SIIM25! A 10,000-report synthetic chest CT dataset generated using GPT-4o — HIPAA-compliant, radiologist-reviewed, and ready for AI research. No patients. No PHI. Just data.

How can we tell if AI is truly fair in radiology? 🧠This study by Paul Yi et al unpacks the big challenges in evaluating algorithmic bias, from inconsistent definitions to missing demographic data. A must-read for building better, more equitable models. pubs.rsna.org/doi/10.1148/ra…

Take the stage at #SIIM #CAIMI25 & contribute to the ongoing revolution in #MedicalImaging #AI! Submit your abstract by Jul 24 and get published in #TheJIIM if accepted! Oct 20-21 | Irvine, CA siim.org/learning-event…

Congrats, Bardia Khosravi, MD! Very well-deserved! #siim25 SIIM

Honored to receive Honorable Mention at #SIIM25 for our work on de-identifying medical reports on edge devices using SLMs 🏆 Congrats to Theo Dapamede for winning Best Paper with his CV risk prediction from mammograms! 👏 Grateful to my mentors Brad Erickson and Judy Gichoya 🙏🏻

Scrolling this Saturday morning? ☕️📰 Catch up on this week’s Radiology content: AI, breast MRI, lung cancer screening, and more. Sharp insights for your weekend brain boost: pubs.rsna.org/toc/radiology/…

2025 #AI Playground Awards – League of Radiologists 1st place goes to Vidya Viswanathan, MD 2nd place goes to Maurice Zissen, MD 3rd place goes to Yujia Wei, MD, PhD #SIIM25 Awards

#SIIM 2025 Scientific Poster & Demonstration Awards 1st place goes to Aawez Mansuri, MS, Systems Software Engineer from Emory University for "LLM Showdown: Benchmarking Performance, Cost, and Speed of Granular Ground Truth Extraction in Radiology Reports for Post-Deployment

So so so cool. Llama 1B batch one inference in one single CUDA kernel, deleting synchronization boundaries imposed by breaking the computation into a series of kernels called in sequence. The *optimal* orchestration of compute and memory is only achievable in this way.

Radiology: Artificial Intelligence offers leading-edge #MachineLearning research ➡️ pubs.rsna.org/journal/ai WFUMB #WFUMP2025 #ultrasound #USRad #POCUS #ML #AI

Dr. Lauren Kim chats with Ivan Pedrosa and Robert Watson, MD about what’s new in the updated ACR MRI Safety Manual and why it matters for your practice. rsnaradiology.libsyn.com/updated-mri-sa…

Ollama can now think! 🤔🤔🤔 For thinking models, and especially useful for very thoughtful models like DeepSeek-R1-0528, Ollama can separate the thoughts and the response. Thinking can also be disabled! This is useful for getting a direct response. This works across

An attempt to explain (current) ChatGPT versions. I still run into many, many people who don't know that: - o3 is the obvious best thing for important/hard things. It is a reasoning model that is much stronger than 4o and if you are using ChatGPT professionally and not using o3

1/ Very pleased to see that the first AI-based long-term breast cancer risk prediction model (Clairity) announced FDA de novo authorization this past week. Many excellent models (Yala et al, Salim et al, NYU Langone Health Department of Radiology Chen et al) have all shown that AI-based estimation of