Computer Assisted Medical Interventions

Seminar Deep Learning in Medical Image Analysis


(12.10.) Currently, we are planning the seminar as an on-site event; in case of a switch to virtual teaching we will inform you on this page. We will also publish the complete seminar program here as soon as the topics have been assigned.


Seminar Logo


This seminar will discuss current research in the field of machine learning-based biomedical image processing. In contrast to general image analysis applications the medical domain provides special challenges that we want to focus on within the seminar:

  • Data scarcity: It is rather common that research on complex medical applications faces the problem of only small amounts of available data. This is rarely due to intrinsic rareness of certain medical cases, but rather to difficulties related to the use of highly sensitive personal information, which is well-protected by law. Current research hence deals with approaches that get by with little or no annotated data at all.
  • Robustness: Often decisive between life and death, algorithms in the medical domain necessarily need to ensure robustness as another criterion. Outliers have to be discovered automatically and treated separately during processing. In a more general sense, the processing systems should themselves be aware about the uncertainty in their computations and provide the user with related quantitative information.
  • Generalizability: Medical applications are highly subjected to variability. This includes, for example, different versions and settings of recording devices as well as different modes of handling by physicians. With the intention of broad applicability beyond a specific setting, solid generalizability of the method is required.

 A detailed list of topics will be released around the briefing date.

General information

There will be a briefing on November 4th including a presentation and the distribution of the topics as well as an introduction of grading criteria and other requirements for students. This will also provide an opportunity to ask any questions regarding seminar organization.

We will meet regularly every two weeks on Wednesdays from 14:00 till 15:30, starting from November 4th until February 10th. There will be no meeting during Christmas holidays (last meeting before: 16.12. & first meeting afterwards: 13.1.). The room will be announced here.

Either register directly during the briefing or send an e-mail to Patrick Scholz (for contact details see below).

The seminar ideally suits students of Computer Science. We offer both "Proseminar" and "Seminar" topics, hence also welcome Bachelor students, but the main focus lies on advanced techniques and prior knowledge on Machine Learning, especially Neural Networks, is a precondition.


Prof. Dr. Lena Maier-Hein
INF 223 (REZ), F.01.086

Tim Adler
INF 223 (REZ), F.02.022

Patrick Scholz
INF 223 (REZ), F.01.088

to top
powered by webEdition CMS