Graham, Mark S;
Tudosiu, Petru-Daniel;
Wright, Paul;
Lopez Pinaya, Walter Hugo;
U-King-Im, Jean-Marie;
Mah, Yee H;
Teo, James T;
... Cardoso, M Jorge; + view all
(2022)
Transformer-based out-of-distribution detection for clinically
safe segmentation.
In: Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi, (eds.)
Proceedings of Medical Imaging with Deep Learning.
(pp. pp. 457-476).
PMLR: Zurich, Switzerland.
Preview |
Text
Nachev_Transformer-based out-of-distribution detection for clinically safe. segmentation.pdf Download (2MB) | Preview |
Abstract
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.
| Type: | Proceedings paper |
|---|---|
| Title: | Transformer-based out-of-distribution detection for clinically safe segmentation |
| Event: | 5th International Conference on Medical Imaging with Deep Learning |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.mlr.press/v172/ |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Transformers, out-of-distribution detection, segmentation, uncertainty. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > UCL Queen Square Institute of Neurology UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > UCL Queen Square Institute of Neurology > Brain Repair and Rehabilitation |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10181115 |
Archive Staff Only
 |
View Item |
