Beyond the Patterns 29 Fabian Isensee nn U Net: self configuring deep learning image segmentation

The famous author of the nnUNet Paper is giving some insights on his most recent discoveries on medical image segmentation at our lab in the next week 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 nontrivial and highly dependent on dataset properties and hardware conditions. We developed nnUNet, a deep learningbased segmentation method that automatically configures itself, including preprocessing, network architecture, training and postprocessing 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, nnUNet surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international bi