Deep Learning

Organizing the 2nd version of the MICCAI Workshop on aFfordable AI and healthcare

Co-Organizing the 10. DFG-#Nachwuchsakademie

We had a wonderful week (10. DFG-#Nachwuchsakademie) with many insightful talks and fruitful discussions at the Schloss Birlinghoven! 20 participants with medical and technical backgrounds, from all over Germany, came together to learn about #AI in #Medicine!

What can we learn about a generated image corrupting its latent representation?

Generative adversarial networks (GANs) offer an effective solution to the image-to-image translation problem, thereby allowing for new possibilities in medical imaging. They can translate images from one imaging modality to another at a low cost. For …

Organizing a workshop on the Next Generation of AI in Medicine

Affordable AI and Healthcare

We are also interested in developing affordable AI solutions suitable for poor-quality data generated by low infrastructure and point-of-care diagnosis.

Organizing the 1st MICCAI Workshop on aFfordable AI and healthcare

Seminar: Federated Learning in Healthcare (SoSe2021)

Organizers: Dr. Shadi Albarqouni, Helmholtz AI and TU Munich, Prof. Nassir Navab, Chair for Computer Aided Medical Procedures, and Prof. Daniel Rueckert, Chair for AI in Medicine, TU Munich Time: Fridays, 10:00 - 12:00

BigPicture Project

The 6-year EU Funded €70 million project called BIGPICTURE will herald a new era in pathology

Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study

Deep unsupervised representation learning has recently led to new approaches in the field of Unsupervised Anomaly Detection (UAD) in brain MRI. The main principle behind these works is to learn a model of normal anatomy by learning to compress and …

An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation

Organ segmentation in CT volumes is an important pre-processing step in many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of the art in this task. However, since this …