We are delighted to announce that MLMIA lab members Nikolas Morshuis and Paul Fischer won the MICCAI 2022 K2S Challenge in Singapore! The objective of this challenge was to segment knee structures directly from 8x undersampled 3D MR images.
MLMIA group leader Christian Baumgartner has co-organised the MICCAI UNSURE 2022 workshop on uncertainty and safety of machine learning based medical image analysis systems. The workshop was held as satellite event of the main MICCAI conference in Singapore.
Stefano Woerner’s paper on “Strategies for Meta-Learning with Diverse Tasks” got accepted to the MIDL 2022 short paper track. Meta-learning research is typically evaluated on very homogenous toy tasks and it is unclear how directly this technology is applicable to much more diverse medical imaging tasks.
Our paper on “Adversarial Robustness of MR Image Reconstruction Under Realistic Perturbations” first-authored by Nikolas Morshuis got accepted to the MICCAI workshop on Machine Learning for Medical Image Reconstruction (MLMIR) 2022 as an oral presentation.
Our research on using class-specific counterfactuals to create an inherently interpretable multi-label classifier led by MLMIA lab member Susu Sun has been accepted to the Medical Imaging with Deep Learning (MIDL) conference, which will be held in Nashville, Tennessee this year.