Excited to share two advances that bring us closer to real-world impact in healthcare AI: SDBench introduces a new benchmark that transforms 304 NEJM cases into interactive diagnostic simulations. AI must ask questions, order tests, and weigh costs, mirroring the complexity of

🔍 Pulmonary cysts on CT as a marker for Birt-Hogg-Dubé syndrome in renal neoplasm patients In 127 patients with renal tumors and pulmonary cysts, certain CT features - perilymphatic distribution, irregular/elliptical cyst shape, and interlobular septal location - showed high

@InsightsImaging @ESTI_Society @EsurOffice @myESR @ESUR_JN @ESOR_myESR @BSTImaging @juniorBSTI

📢NEW @InsightsImaging👉 https://t.co/PnzuCO47ov ⭐️BHDS should be considered in patients with renal neoplasm &🫁cysts ⭐️Radiologists can identify specific CT features of 🫁cysts & improve recognition of BHDS @Radiology_UOC @BHD_Foundation #radres #Radtwitter #FOAMrad #FOAMmed 👇👇

📢📢Now published in #ACMTOCHI, our research on: “Challenges for Responsible AI Design and Workflow Integration in Healthcare: A Case Study of Automatic Feeding Tube Qualification in Radiology” https://t.co/FvYQmGQeTg Details in 🧵below

Datasets, Benchmarks, and Protocols by D.C. de Castro (@dccastr0) et al.: PadChest-GR: A Bilingual Chest X-Ray Dataset for Grounded Radiology Report Generation https://t.co/8iX01f740o #AIinMedicine

NEJM-AI: Introducing PadChest-GR, the world's first bilingual, grounded radiology reporting benchmark for chest X-rays! https://t.co/7PMiIf1Uts

Important advance in AI medical imaging by pretraining solely on unimodal biomedical imaging data. This achieves similar or greater performance than state-of-the-art biomedical-language-supervised models on a diverse range of benchmarks.

RAD-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision, published today in Nature Machine Intelligence. 👉 Link https://t.co/aDI2KxqvLk #microsoft #healthcare #ai #ResearchPapers

Wondering how #DigitalTwins differ from #causality and #SyntheticData - and why it matters? Watch my latest talk to explore these distinctions and the game-changing potential of Digital Twins for bespoke medicine, improve decision-making, and other areas:

Our MAIRA-2 model for (grounded) radiology report generation from CXRs is out now!

RadEdit stress-tests biomedical vision models by simulating dataset shifts through precise image editing. It uses diffusion models to create realistic, synthetic datasets, helping to identify model weaknesses and evaluate robustness: https://t.co/s4g0zLP6q6

THIS X-RAY DOESN'T EXIST @eccvconf #ECCV2024 🧵1/9

RadFact is game changing to evaluate report generation. Check it out https://t.co/mzCigpv52I and in our MAIRA-2 pre-print:

my team's radiology report generation metric is now open source: microsoft/RadFact: A metric suite leveraging the logical inference capabilities of LLMs, for radiology report generation both with and without grounding (https://t.co/HfvVKhXuEp)#MoreMetrics https://t.co/O8BUiFKuGN

@BHD_Foundation @myrovlytis

We're pleased to announce the publishing of ERN's first definitive European clinical guidelines for the diagnosis and management of BHD. We are proud to be a part of this milestone project. Read our new article to learn more: https://t.co/UFiKeQwBTt

We're pleased to announce the publishing of ERN's first definitive European clinical guidelines for the diagnosis and management of BHD. We are proud to be a part of this milestone project. Read our new article to learn more: https://t.co/sseE2vebuq

📢NEW Birt-Hogg-Dubé syndrome GUIDELINES 👉 https://t.co/djFsOrUG3l Learn when to consider ⭐️a diagnosis of BHD syndrome ⭐️genetic testing of FLCN &more @Radiology_UOC @Prof_Marciniak @BHD_Foundation @myrovlytis @Cambridge_Uni @CUH_NHS #MedTwitter #FOAMed

🎉Proud to be part of this collaborative effort to develop #AI diagnostic tools for #BHDsyndrome & other rare genetic disorders causing pneumothorax👉 https://t.co/qDJbkEegiE @myrovlytis @AsherOrionGroup @Prof_Marciniak @BrighamWomens @MassGenBrigham @Cambridge_Uni @radiology_UOC