We are happy to share that our new work "Xplainer: From X-Ray Observations to Explainable Zero-Shot Diagnosis" was accepted at #MICCAI2023 Matthias Keicher Ege Oezsoy Nassir Navab TUM CAMP Arxiv: arxiv.org/pdf/2303.13391… Demo: huggingface.co/spaces/CAMP-Vi… Code: github.com/ChantalMP/Xpla…

Thrilled to share that our paper on automated structured radiology reporting, which introduces the Rad-ReStruct benchmark & hi-VQA method, was accepted at #MICCAI2023! Arxiv: arxiv.org/abs/2307.05766 Github: github.com/ChantalMP/Rad-… Matthias Keicher Ege Oezsoy Nassir Navab TUM CAMP

Dan Hashimoto, MD MS FACS Joël L. Lavanchy Clarunis Basel Beat Müller IHU Strasbourg CAMMA @MartinWagnerMD Stefanie Speidel@NCTDresden EAES Amin Madani MD PhD Asensus Surgical Deepak Alapatt Chinedu Nwoye NVIDIA Aditya Murali Luca Sestini Matthias Keicher introducing some great works on multimodal (images, text, etc) learning at the #SurgicalDataScience Summer School! #Edu4SDS23

Check out our new work, RaDialog, a large vision-language model for enhancing radiology report accuracy and interactive assistance! 🌐 chantalmp.github.io/RaDialog/ 📄 arxiv.org/pdf/2311.18681… 💻 github.com/ChantalMP/RaDi… Ege Oezsoy Benjamin Busam Nassir Navab Matthias Keicher TUM CAMP

How can we design adaptable and scalable methods for Holistic OR Domain Modeling? Towards this, we introduce ORacle arxiv.org/abs/2404.07031, a vision-language model, which incorporates multi-view and temporal capabilities and can leverage external knowledge during inference.

Happy to share that "ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling" has been accepted at #MICCAI24. Paper: arxiv.org/abs/2404.07031 Code: github.com/egeozsoy/ORacle #LLM #SDS #LVLM #SGG #MLLM

🚨 New publication alert: 📢 “Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder.” 🖊️ M Atad, D Schinz, H Moeller, R Graf, B Wiestler, Daniel Rueckert, Nassir Navab, J S Kirschke, Matthias Keicher. ⬇️

I am very happy to present „ORacle“ at #MICCAI2024 in the Surgical Data Science oral session on Tuesday 8th at 16:45 (Crystal Room). You can also come to the poster session to learn more scalable holistic OR modeling! Chantal Pellegrini Matthias Keicher Nassir Navab

We are extremely honered that our work“ORacle“ has received the Best Paper Runner-Up Award at MICCAI 2024! Huge thanks to our supervisors Matthias Keicher Nassir Navab #MICCAI2024 #BestPaperRunnerUp

🎉 Thrilled to share MM-OR has been accepted to #CVPR2025. MM-OR is a new, large scale multimodal operating room dataset for semantic understanding of surgeries. It captures robotic knee replacement surgeries with multi-view RGB-D video, audio, speech transcripts, robotic logs,

I am happy to share that RaDialog was accepted to MIDL 2025! We look forward to presenting the newest version of RaDialog, with an improved architecture, extended instruct dataset, more thorough evaluation and analysis and Hugging Face integration.