"Comparative Validation of AI Algorithms"
On April 21-22, HIDA will participate in the Big-DATA.AI Summit of the digital association bitkom as part of a partnership. Presentation by Prof. Lena Maier-Hein, DKFZ
Lena Maier-Hain, Head of the Department Computer Assisted Medical Interventions at the German Cancer Research Center in Heidelberg (DKFZ) will represent the Helmholtz Association in the thematic area "Digital Health, Medical Research, Diagnostics and Therapy" with a contribution on the virtual stage. Topic of her presentation:
Comparative validation of AI algorithms: common pitfalls and new concepts
Abstract: Every year hundreds of new algorithms are published in the field of biomedical image analysis. For a long time, the validation and evaluation of new methods was based on the authors' personal datasets, which made a fair and direct comparison of the solutions impossible. Now, common research practice has changed to include the organization of international challenges that allow benchmarking of algorithms on publicly released datasets.
After more than 15 years of biomedical challenges, we have carefully analyzed and critiqued the common practice regarding the design and organization of biomedical image analysis challenges. This talk will provide statistics and new insights on various topics related to biomedical image analysis challenges, from the choice of metrics and ranking schemes to the pitfalls that can arise when organizing or participating in a challenge.
About Lena Maier-Hein
Lena Maier-Hein received her diploma (2005) and PhD (2009) with honors from the Karlsruhe Institute of Technology and completed her postdoctoral period at the German Cancer Research Center (DKFZ) and the Hamlyn Centre for Robotic Surgery at Imperial College London. During her time as a junior research group leader at DKFZ (2011-2016), she habilitated (2013) at the University of Heidelberg.
As DKFZ department head, she now works in the field of biomedical image analysis with a focus on surgical data science, computational biophotonics and validation of machine learning algorithms. Lena Maier-Hein is a Fellow of the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society and the European Laboratory for Learning and Intelligent Systems (ELLIS). She has been awarded several science prizes, including the Heinz Maier-Leibnitz Prize 2013 of the German Research Foundation (DFG) and the Berlin-Brandenburg Academy Prize 2017/18. Lea Maier-Hein has received a Starting Grant (2015-2020) and a Consolidator Grant (2021-2026) from the European Research Council (ERC).
The full program of the Big Data.AI Summit can be found here.
You want to see Lena Maier-Hein's lecture?
