Invited Talk – Fabian Isensee (German Cancer Research Center): nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation, May 5th, 10h AM CET

Symbolic picture for the article. The link opens the image in a large view.

The famous author of the nnU-Net Paper is giving some insights on his most recent discoveries on medical image segmentation at our lab in the next week!

Title: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
Date: May 5th, 10h AM CET

Abstract: Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image analysis and quantification in many applications, the design of respective specialized solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We developed nnU-Net, a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task. The key design choices in this process are modeled as a set of fixed parameters, interdependent rules and empirical decisions. Without manual intervention, nnU-Net surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international biomedical segmentation competitions. We make nnU-Net publicly available as an out-of-the-box tool, rendering state-of-the-art segmentation accessible to a broad audience by requiring neither expert knowledge nor computing resources beyond standard network training.

Short Bio:

  • 2009 – 2015: Bachelor and Master of Science in Molecular Biotechnology an Uni Heidelberg
  • 2015 – 2020: Dr. rer. nat. am DKFZ bei Klaus Maier-Hein
  • 2020 – now: Head of Applied Computer Vision Lab (Helmholtz Imaging Platform (HIP) Unit DKFZ)
  • Winner of the BVM Award 2020!