07.07.2025
How Neural Networks Are Changing Medical Imaging – With Reinhard Heckel
Research Film
Clear imaging is essential for accurate diagnosis — but when it comes to the heart, motion makes it one of the most difficult organs to capture in high resolution. Traditional reconstruction methods often struggle to deliver the detail clinicians need.
«Deep neural networks can improve the clarity and diagnostic value by giving much sharper and higher resolution images from measurements where classical methods just don’t do as well.»
Reinhard Heckel
MCML PI
Reinhard Heckel, Professor of Machine Learning at TUM and MCML PI, is using deep neural networks to change that. His team is developing methods that reconstruct sharper, more detailed images from limited or noisy measurements — even when the subject is moving.
«The data is really what makes the difference between a well-performing method that is robust and reliable, and a method that is just going to work on a handful of patients.»
Reinhard Heckel
MCML PI
A key focus of his research is data: how to source it, how to ensure it’s diverse, and how to train robust models that generalize across patient populations.
This work is paving the way for more accurate imaging tools that can help detect pathologies that might otherwise go unnoticed.
This video is part of our MCML spotlight series on researchers driving real-world impact with AI.
©MCML
The film was produced and edited by Nicole Huminski and Nikolai Huber.
Related
09.07.2026
MCML Junior Member Bolei Ma Earns Best Paper and SAC Highlight Awards at ACL 2026
Bolei Ma receives a Best Paper Award and an SAC Highlight Award at ACL 2026 for outstanding contributions to NLP research.
08.07.2026
How Autonomous Systems Learn to Understand Their Environment
The team at the startup SE3 Labs has developed a spatial AI technology that uses images, videos, and map data to create realistic 3D models.
08.07.2026
MCML Junior Member Sarah Ball Receives Outstanding Position Paper Award at ICML 2026
MCML Junior Member Sarah Ball and her co-author Phil Hackemann received the Outstanding Position Paper Award at ICML 2026 this week in Seoul.
