A Probabilistic U-Net for Segmentation of Ambiguous Images

S. Kohl, B. Romera-Paredes, C. Meyer, J. De Fauw, J. Ledsam, K. Maier-Hein, S. Eslami, D. Jimenez Rezende, Olaf Ronneberger
32nd Conference on Neural Information Processing Systems (NeurIPS), Dec 2018
Abstract: Many real-world vision problems suffer from inherent ambiguities. In clinical applications for example, it might not be clear from a CT scan alone which particular region is cancer tissue. Therefore a group of graders typically produces a set of diverse but plausible segmentations. We consider the task of learning a distribution over segmentations given an input. To this end we propose a generative segmentation model based on a combination of a U-Net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible hypotheses. We show on a lung abnormalities segmentation task and on a Cityscapes segmentation task that our model reproduces the possible segmentation variants as well as the frequencies with which they occur, doing so significantly better than published approaches. These models could have a high impact in real-world applications, such as being used as clinical decision-making algorithms accounting for multiple plausible semantic segmentation hypotheses to provide possible diagnoses and recommend further actions to resolve the present ambiguities.

Other associated files : 7928-a-probabilistic-u-net-for-segmentation-of-ambiguous-images.pdf [1.5MB]  

Images and movies


BibTex reference

  author       = "SAA. Kohl and B. Romera-Paredes and C. Meyer and J. De Fauw and JR. Ledsam and KH. Maier-Hein and SMA. Eslami and D. Jimenez Rezende and O. Ronneberger",
  title        = "A Probabilistic U-Net for Segmentation of Ambiguous Images",
  booktitle    = "32nd Conference on Neural Information Processing Systems (NeurIPS)",
  month        = "Dec",
  year         = "2018",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2018/Ron18b"

Other publications in the database