BMIC Group ETH Zurich

Check out the paper and try out the code here: Paper: arxiv.org/pdf/2509.19997 Github: github.com/NicoSchulthess…

How does one detect anomalies and reach scores close to state of the art methods, while reducing runtime use by more than half? By fitting a Dirichlet process mixture model to DINOv2 patch embeddings of images from healthy patients!

In this paper published in Nature Communications, Erdil et al. proposed a method for predicting active brown adipose tissue from CT scans. Read more here: nature.com/articles/s4146…

That's a wrap on #MICCAI2025! It was great to present our work and connect with everyone around the world! 감사합니다 :)

We have two papers accepted to #MICCAI2025! "Anomaly Detection by Clustering DINO Embeddings using a Dirichlet Process Mixture” by Nico Schulthess and "Conformal forecasting for surgical instrument trajectory” by Sara Sangalli & Gary Sarwin. Excited to see you in Daejeon!

We are happy to announce that the article  "Learning to segment anatomy and lesions from disparately labeled sources in brain MRI” from Meva Himmetoglu et al. is accepted to Medical Image Analysis journal! arxiv.org/abs/2503.18840

We have 2 papers accepted to #ICLR2025! 🎉 "Uncertainty modeling for fine-tuned implicit functions" by Anna Susmelj et al. and "Multimodality Helps Few-Shot 3D Point Cloud Semantic Segmentation" by Zhaochong An et al. ! arxiv.org/abs/2406.12082 arxiv.org/abs/2410.22489 Congrats!

Thanks again @d_zimmerer for the chance to address the MOOD community at #MICCAI2024! Our call for papers and accompanying dataset with @FrontMedTech are in the works. forms.gle/7gjF6R5YJ1rjNa… Until then, we’d love everyone’s input on how best to advance anomaly detection.

Paper link: proceedings.neurips.cc/paper_files/pa… Paper code: github.com/salusanga/auco…

Check out the video where she explains the method more in detail: youtu.be/v0NONmH5M1Y

When the model confidence on predictions is low, we rely on experts for inspection. But the time experts have is limited and very expensive! In her paper, @salusanga proposes to maximize the "area under confidence operating characteristic curve" to address this trade-off.

On the final day of #MICCAI2024, Yolanne Lee and Kyriakos Flouris are presenting their work on Energy-Based Prior Latent Space Diffusion Model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI, at the Deep Generative Models for MICCAI Workshop!

Happy to be here and exchange with peers at the end of fourth day of #MICCAI2024!

Spotlight presentation is over! You can find the poster in the Conference Center now to discuss more in detail.

Dr. Jeremy Tan gave a keynote talk at Medical Out of Distribution Analysis Challenge.

Our PhD student Qi Ma presented his work on "Video Foundation Model for Medical 3D Segmentation" at ToothFairy2 Challenge.

First day of satellite events at #MICCAI2024 was very welcoming!

We are excited to share the new paper by Ertunc Erdil et al. "Predicting standardized uptake value of brown adipose tissue from CT scans using convolutional neural networks" published at Nature Communications: doi.org/10.1038/s41467…

Gary will present his paper at "Spotlight Session 15" at #MICCAI2024 on Wednesday, October 9, 2024 at the Main Hall!

We are happy to share that the paper titled "Predicting mortality after transcatheter aortic valve replacement using preprocedural CT" from David Brüggemann et al. has been accepted to Scientific Reports! Check it out here: nature.com/articles/s4159…