| Title: | Unsupervised brain imaging 3D anomaly detection and segmentation with transformers |
| Journal: | Medical Image Analysis |
| Published: | 4 May 2022 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/35598520/ |
| DOI: | https://doi.org/10.1016/j.media.2022.102475 |
| Citations: | 84 (67 in last 2 years) as of 8 Aug 2024 |
Publication 7140
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Pathological brain appearances may be so heterogeneous as to be intelligible only as anomalies, defined by their deviation from normality rather than any specific set of pathological features. Amongst the hardest tasks in medical imaging, detecting such anomalies requires models of the normal brain that combine compactness with the expressivity of the complex, long-range interactions that characterise its structural organisation. These are requirements transformers have arguably greater potential to satisfy than other current candidate architectures, but their application has been inhibited by their demands on data and computational resources. Here we combine the latent representation of vector quantised variational autoencoders with an ensemble of autoregressive transformers to enable unsupervised anomaly detection and segmentation defined by deviation from healthy brain imaging data, achievable at low computational cost, within relative modest data regimes. We compare our method to current state-of-the-art approaches across a series of experiments with 2D and 3D data involving synthetic and real pathological lesions. On real lesions, we train our models on 15,000 radiologically normal participants from UK Biobank and evaluate performance on four different brain MR datasets with small vessel disease, demyelinating lesions, and tumours. We demonstrate superior anomaly detection performance both image-wise and pixel/voxel-wise, achievable without post-processing. These results draw attention to the potential of transformers in this most challenging of imaging tasks.7 Authors
- Walter H.L. Pinaya
- Petru-Daniel Tudosiu
- Robert Gray
- Geraint Rees
- Parashkev Nachev
- Sebastien Ourselin
- M. Jorge Cardoso
1 Application
| Application ID | Title |
|---|---|
| 58292 | Prediction of neurovascular incidental findings using simulation of the cardio-neuro vascular pathway |
Enabling scientific discoveries that improve human health