Fraunhofer Institute for Digital Medicine MEVISInstitute News
The Fraunhofer MEVIS team at SPIE Medical Imaging 2023.
Artificial intelligence and computer-aided support for diagnosis and therapy in digital medicine – these are the topics Fraunhofer MEVIS is presenting at the International Society for Optics and Photonics (SPIE) Medical Imaging conference, which is held in San Diego, California, from February 19 to 23. This year, the Fraunhofer Institute for Digital Medicine MEVIS is again on-site at the renowned conference with numerous contributions.
Institute Director Horst Hahn is co-chairing the “Live Demonstrations Workshop” together with Karen Drukker from University of Chicago Medicine and Lubomir M. Hadjiiski from Michigan Medicine on February 21. The goal of this workshop is to provide a forum for systems and algorithms developers to show off their creations. During the workshop Fraunhofer MEVIS is presenting four live demonstrations:
- “Intensity-based 2D-3D registration for determination of fragment position in pelvic fractures”, Stephanie Häger
- “Image-based Assessment of Anatomical Structures and Position Uncertainty for TAVI Planning”, Johanna Brosig
- “minimARing – AR solution for interactive heart valve surgery planning”, Anja Hennemuth
- “Efficient Tumor Follow-Up”, Stefan Heldmann:
On February 19, Fraunhofer MEVIS researchers Markus Wenzel and Hans Meine will instruct a full-day workshop on the topic “Introduction to Medical Image Analysis Using Convolutional Neural Networks”. On February 21, Markus Wenzel and Felix Thielke will conduct a half-day course on “Transformers: A powerful tool for Medical Image Analysis and Generation“. The workshops are aimed at students, scientists and engineers from academia and industry who want to gain first practical work experience on the topic of deep learning, a variant of machine learning.
In addition, scientists from Fraunhofer MEVIS will give two oral presentations at SPIE Medical Imaging 2023:
- “Unsupervised learning of healthy anatomy for anomaly detection in brain CT scans”, Sina Walluscheck, February 20, 10:50am PST, Town & Country C
- “Combining arterial and venous CT scans in a multi-encoder network for improved hepatic vessel segmentation”, Felix Thielke, February 20, 3:30pm PST, Town & Country B