I'm organizing the #Endovis sub challenge #FedSurg this year, take your chance to participate and gain experience to create a classifier in a #federatedlearning environment from data from different hospitals to classify the degree of inflammation of the #appendix.

Looking forward to presenting at the AI in Pathology workshop for the 3rd year already! See you there 🤩

Finally out in Nature Reviews Cancer! Our "guide to artificial intelligence for cancer researchers", with Raquel Perez-Lopez Narmin Ghaffari Laleh Faisal Mahmood 🤩 article: nature.com/articles/s4156… full text: rdcu.be/dH7Z6 Hochschulmedizin_TUD Universitätsklinikum Heidelberg Nationales Centrum für Tumorerkrankungen Dresden NCT Heidelberg

Finally out in NEJM AI 🤖 "GPT-4 for Information Retrieval and Comparison of Medical Oncology Guidelines". We've developed a RAG pipeline using the GPT-4 API to answer medical oncology questions based on guidelines. Previous studies have claimed that "large language models

Out today in nature - a broad overview of AI in oncology, happy to have contributed to this along with many colleagues and friends arsela prelaj Anant Madabhushi & others

So proud of Isabella Wiest from TU Dresden and Universitätsmedizin Mannheim who is presenting about the “skill of prompt engineering” at our AI session at EASL Education #EASLcongress

What a fun session at EASL Education EASLnews #EASLcongress 2024 about "Research in the age of AI" in Milan 🇮🇹🇪🇺. Any biomedical researcher should be aware of current AI tools and develop a basic literacy. TU Dresden Nationales Centrum für Tumorerkrankungen Dresden NCT Heidelberg Hochschulmedizin_TUD Universitätsklinikum Heidelberg

New preprint from katherlab, led by Isabella Wiest - large language models can solve one of the hardest problems in medical informatics - robustly anonymizing unstructured medical documents. This unlocks a large source of clinical data for downstream AI applications. Available

Weekend read: We are discussing the future of AI in cancer research in Cancer Cell sciencedirect.com/science/articl… ... with Moritz Gerstung James Zou Marzyeh Diego Chowell Jonas Teuwen Faisal Mahmood 🤩 Nationales Centrum für Tumorerkrankungen Dresden @nct_hd DKFZ Universitätsklinikum Heidelberg TU Dresden

New preprint from katherlab: large language models for end-to-end clincial trial matching. Our system parses study protocols and patient records, and matches them. We evaluate thoroughly against human experts and find >90% correspondence. Led by Dyke Ferber 🤩

New research led by Chiara Loeffler 🤩

Just out from katherlab 👇

New research from katherlab, led by Jan Clusmann : "Prompt Injection Attacks on Large Language Models in Oncology" arxiv.org/abs/2407.18981 We show that vision-language models in oncology can be attacked easily, creating malicious output which could harm patients. TU Dresden

Exciting new research by Omar S.M. El Nahhas from katherlab 🤩

This week was about research. It is inspiring to see how people come together, clinicians with computational scientists, all with a common goal, to help cancer patients on their journey. Together, we are better! Thanks, Jakob Nikolas Kather, for organizing a great AI in medicine week.

New article from katherlab in Nature Medicine: large language models for interoperability in healthcare 👇

New research from katherlab led by Isabella Wiest 🤩

New paper from katherlab led by Omar S.M. El Nahhas et al. 😊👇

Today, we hosted the first conference on LLMs in medicine at katherlab / TU Dresden, chaired by Isabella Wiest 🤩 We are not just riding the hype train🚆 - we are working hard to provide scientific & clinical evidence for benefits and limitations of LLMs in healthcare

We had a fun session on artificial intelligence at the DGHO e. V. German/Swiss/Austrian conference of #hematology and #oncology in Basel 🇨🇭Both the main room and the overflow room were overflowing ... thanks to excellent speakers Munich Leukemia Laboratory Carolin V. Schneider, MD & others