Transformer-based out-of-distribution detection for clinically safe segmentation

Research output: Contribution to journalConference paperpeer-review

4 Citations (Scopus)
41 Downloads (Pure)


In a clinical setting it is essential that deployed image processing systems are robust to the full range of inputs they might encounter and, in particular, do not make confidently wrong predictions. The most popular approach to safe processing is to train networks that can provide a measure of their uncertainty, but these tend to fail for inputs that are far outside the training data distribution. Recently, generative modelling approaches have been proposed as an alternative; these can quantify the likelihood of a data sample explicitly, filtering out any out-of-distribution (OOD) samples before further processing is performed. In this work, we focus on image segmentation and evaluate several approaches to network uncertainty in the far-OOD and near-OOD cases for the task of segmenting haemorrhages in head CTs. We find all of these approaches are unsuitable for safe segmentation as they provide confidently wrong predictions when operating OOD. We propose performing full 3D OOD detection using a VQ-GAN to provide a compressed latent representation of the image and a transformer to estimate the data likelihood. Our approach successfully identifies images in both the far- and near-OOD cases. We find a strong relationship between image likelihood and the quality of a model’s segmentation, making this approach viable for filtering images unsuitable for segmentation. To our knowledge, this is the first time transformers have been applied to perform OOD detection on 3D image data.

Original languageEnglish
Pages (from-to)457-476
Number of pages20
JournalProceedings of Machine Learning Research
Publication statusPublished - 21 May 2022
Event5th International Conference on Medical Imaging with Deep Learning, MIDL 2022 - Zurich, Switzerland
Duration: 6 Jul 20228 Jul 2022


  • out-of-distribution detection
  • segmentation
  • Transformers
  • uncertainty


Dive into the research topics of 'Transformer-based out-of-distribution detection for clinically safe segmentation'. Together they form a unique fingerprint.

Cite this