Timezone: »

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
Miguel Monteiro · Loic Le Folgoc · Daniel Coelho de Castro · Nick Pawlowski · Bernardo Marques · Konstantinos Kamnitsas · Mark van der Wilk · Ben Glocker

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #319

In image segmentation, there is often more than one plausible solution for a given input. In medical imaging, for example, experts will often disagree about the exact location of object boundaries. Estimating this inherent uncertainty and predicting multiple plausible hypotheses is of great interest in many applications, yet this ability is lacking in most current deep learning methods. In this paper, we introduce stochastic segmentation networks (SSNs), an efficient probabilistic method for modelling aleatoric uncertainty with any image segmentation network architecture. In contrast to approaches that produce pixel-wise estimates, SSNs model joint distributions over entire label maps and thus can generate multiple spatially coherent hypotheses for a single image. By using a low-rank multivariate normal distribution over the logit space to model the probability of the label map given the image, we obtain a spatially consistent probability distribution that can be efficiently computed by a neural network without any changes to the underlying architecture. We tested our method on the segmentation of real-world medical data, including lung nodules in 2D CT and brain tumours in 3D multimodal MRI scans. SSNs outperform state-of-the-art for modelling correlated uncertainty in ambiguous images while being much simpler, more flexible, and more efficient.

Author Information

Miguel Monteiro (Imperial College London)
Loic Le Folgoc (Imperial College London)
Daniel Coelho de Castro (Microsoft Research / Imperial College London)
Nick Pawlowski (Imperial College London)
Bernardo Marques (Imperial College London)
Konstantinos Kamnitsas (Imperial College London)
Mark van der Wilk (Imperial College)
Ben Glocker (Imperial College London)

More from the Same Authors