Deep Learning-based algorithms showed great performance in many fields of image procession and pattern recognition and compete with technologies such as compressive sensing and iterative optimization. The basis for the success of these algorithms is the availability of large amounts of data (big data) for training and of high computing power (typically GPUs). In this seminar we try to answer the question how typical problems in medical imaging might profit from deep learning concepts. The discussed fields are computer aided detection (CAD), image reconstruction, image denoising, and image registration. The seminar will give an insight into the newest results in literature. Additionally the participants will have the opportunity to implement example code and learn the usage of typical open source deep learning libraries.

Dates & Rooms:
Monday, 8:15 - 9:45; Room: KH 1.021

Hornegger, Joachim
Maier, Andreas
Ritschl, Ludwig