A Probabilistic U-Net for Segmentation of Ambiguous Images

TL;DR

This paper introduces a probabilistic U-Net model that generates multiple plausible segmentation hypotheses for ambiguous images, improving over previous methods in capturing segmentation variability for clinical and urban scene applications.

Contribution

It presents a novel combination of U-Net and conditional variational autoencoder to model a distribution over segmentations, enabling efficient generation of diverse plausible outputs.

Findings

Outperforms existing methods in reproducing segmentation variants and their frequencies.

Effective on lung abnormalities and Cityscapes segmentation tasks.

Potential for clinical decision support by accounting for segmentation ambiguities.

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.