Medical Imaging

Course: Introduction to Machine Learning

Machine Learning has gained a lot of momentum within development organizations that are actively looking for innovative solutions to leverage their data to identify new levels of understanding their operations and processes. Machine learning is a subfield of Artificial Intelligence where the machine learns from data rather than from explicit programming.

Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering

Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, especially for 3D volume data. Recent breakthroughs in self-supervised learning (SSL) offer the ability to overcome the …

Federated disentangled representation learning for unsupervised brain anomaly detection

With the advent of deep learning and increasing use of brain MRIs, a great amount of interest has arisen in automated anomaly segmentation to improve clinical workflows; however, it is time-consuming and expensive to curate medical imaging. Moreover, …

Development of a Deep Learning Toolkit for MRI-Guided Online Adaptive Radiotherapy

The 3-year DFG Funded project with LMU and TU Munich (2022-2025)

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 …

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.

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 …

Multi-task multi-domain learning for digital staining and classification of leukocytes

oking stained images preserving the inter-cellular structures, crucial for the medical experts to perform classification. We achieve better structure preservation by adding auxiliary tasks of segmentation and direct reconstruction. Segmentation …