About us


The Institute for Computational Imaging and AI in Medicine (CompAI) at TUM and the Institute of Machine Learning in Biomedical Imaging (IML) at Helmholtz Center Munich focus on research to leverage machine learning for the grand challenges in biomedical imaging in areas of unmet clinical need. Novel and affordable solutions should empower clinics to make more accurate, fast and reliable decisions for early detection, treatment planning and improved patient outcome. We are looking for team members, please contact us.

About us

Meet the Team

Chair

Avatar

Julia A. Schnabel

Technical University Munich

Helmholtz Center Munich

King's College London

Professor for Computational Imaging and AI in Medicine, Director of the Institute of Machine Learning in Biomedical Imaging

Biomedical Imaging, Artificial Intelligence in Medicine

Team Support

Avatar

Sandra Mayer

Helmholtz Center Munich

Administrative Assistant

Project Management and Administration, Team Management and Support, Communication and Relations

Avatar

Sabine Franke

Technical University Munich

Administrative Assistant

Project Management and Administration, Team Management and Support, Communication and Relations

Principal Investigators

Avatar

Georgios Kaissis

Helmholtz Center Munich

Principal Investigator

Reliable artificial intelligence, Medical image computing, Probabilistic methods

Avatar

Veronika Zimmer

Technical University Munich

Principal Investigator

Medical Image Computing, Ultrasound Image Analysis, Fetal Image Analysis

Senior Researchers

Avatar

Maxime Di Folco

Helmholtz Center Munich

Research Scientist

Representation learning, Cardiac imaging

Avatar

Daniel M. Lang

Helmholtz Center Munich

Research Scientist

Self-supervised Learning, Transfer Learning, Survival Analysis

Researchers

Avatar

Cosmin I. Bercea

Technical University of Munich

Helmholtz Center Munich

PhD Student

Interpretable Machine Learning, Anomaly Detection

Avatar

Anna Reithmeir

Technical University of Munich

Munich Center for Machine Learning (MCML)

PhD Student

Medical Image Registration, Robustness and Numerics of Machine Learning Algorithms, Manifold Learning

Avatar

Hannah Eichhorn

Technical University Munich

Helmholtz Center Munich

PhD student

Magnetic Resonance Imaging, Deep learning, Image reconstruction

Avatar

Veronika Spieker

Technical University Munich

Helmholtz Center Munich

PhD Student

Machine Learning, Magnetic Resonance Imaging, Motion Detection & Correction

Alumni

Avatar

Simona Bottani

Helmholtz Center Munich

Research Scientist

Deep learning, Big data sets, Brain imaging

News

New publication at Nature Machine Intelligence

Federated disentangled representation learning for unsupervised brain anomaly detection by Cosmin I. Bercea et al. has been published at Nature Machine Intelligence.
Aug 2, 2022 1 min read
New publication at Nature Machine Intelligence
Veronika Spieker wins the 1st place MedtecLIVE Talent Award 2022

The MedtecLIVE Talent Award 2022 is given to bachelor’s and master’s theses that relate to an innovation, improvement, or new application in medical technology along with its entire value chain.
May 30, 2022 1 min read
Veronika Spieker wins the 1st place MedtecLIVE Talent Award 2022

Publications

Recent

What do we learn? Debunking the Myth of Unsupervised Outlier Detection
Even though auto-encoders (AEs) have the desirable property of learning compact representations without labels and have been widely …
PDF Cite Project
What do we learn? Debunking the Myth of Unsupervised Outlier Detection
A Deep Learning-based Integrated Framework for Quality-aware Undersampled Cine Cardiac MRI Reconstruction and Analysis
Cite
AtrialJSQnet: A New framework for joint segmentation and quantification of left atrium and scars incorporating spatial and shape information
Cite
See all publications

Publications

Featured

Deep Learning-Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentation
Segmenting anatomical structures in medical images has been successfully addressed with deep learning methods for a range of …
Dec 1, 2020
PDF Cite DOI
Model-Based and Data-Driven Strategies in Medical Image Computing
Jan 1, 2020
Cite DOI
A topological loss function for deep-learning based image segmentation using persistent homology
Jan 1, 2019
Cite
See all

Teaching

*
All Summer Winter
Deep Medical Anomaly Segmentation

Deep Medical Anomaly Segmentation

Winter semester 2022. TUM Informatics. Master Seminar.

Medical Image Registation I (IN2107)

Medical Image Registation I (IN2107)

Summer semester 2022. TUM Informatics. Master Seminar. Details

Artificial Intelligence in Medicine (IN2403)

Artificial Intelligence in Medicine (IN2403)

Winter 2021. TUM Informatics. Lecture. Details.

Artificial Intelligence in Medicine II (IN2408)

Artificial Intelligence in Medicine II (IN2408)

Summer 2022. TUM Informatics. Lecture. Details.

Open Positions

If you are interested in one of these projects please contact us and attach a motivation letter, transcript of academic records and CV.

*
All Bachelor Thesis Master Thesis PhD Post-doc Other
Segmentation and morphological comparison of distal radial articular surfaces (f/m/x)

Segmentation and morphological comparison of distal radial articular surfaces (f/m/x)

Master Thesis. I’m interested

Deep Learning for Smooth Surface and Normal Fields Reconstruction (f/m/x)

Deep Learning for Smooth Surface and Normal Fields Reconstruction (f/m/x)

Master Thesis. I’m interested

Unsupervised Anomaly Detection for Medical Imaging (f/m/x)

Unsupervised Anomaly Detection for Medical Imaging (f/m/x)

Master Thesis. I’m interested

Multi-object and multi-modal image segmentation in dental MRI and CT using limited data (f/m/x)

Multi-object and multi-modal image segmentation in dental MRI and CT using limited data (f/m/x)

Master Thesis. I’m interested

PhD AI-enabled medical imaging (f/m/x)

PhD AI-enabled medical imaging (f/m/x)

PhD position starting July 2022. Position related to MCML Munich. I’m interested

Segmentation of sparse annotated data: application to cardiac imaging (f/m/x)

Segmentation of sparse annotated data: application to cardiac imaging (f/m/x)

Master Thesis. I’m interested

Helmholtz Center Munich

Institute of Machine Learning in Biomedical Imaging

Technical University Munich

Faculty of Informatics and Institute for Advanced Study