Dear Spiral user, We’re pleased to introduce Helix, https://helix.imperial.ac.uk/ Imperial’s new repository for research datasets. Please use Helix for all future dataset deposits. There is no change to Spiral - continue depositing as usual. For queries, contact the Research Data Management team at rdm-enquiries@imperial.ac.uk. Kind regards, the Spiral Team. The Spiral team
Detecting outliers with foreign patch interpolation
File(s)
2022_013.pdf (7.92 MB)
Published version
OA Location
Author(s)
Tan, Jeremy
Hou, Benjamin
Batten, James
Qiu, Huaqi
Kainz, Bernhard
Type
Journal Article
Abstract
In medical imaging, outliers can contain hypo/hyper-intensities, minor deformations, or completely altered anatomy. To detect these irregularities it is helpful to learn the features present in both normal and abnormal images. However this is difficult because of the wide range of possible abnormalities and also the number of ways that normal anatomy can vary naturally. As such, we leverage the natural variations in normal anatomy to create a range of synthetic abnormalities. Specifically, the same patch region is extracted from two independent samples and replaced with an interpolation between both patches. The interpolation factor, patch size, and patch location are randomly sampled from uniform distributions. A wide residual encoder decoder is trained to give a pixel-wise prediction of the patch and its interpolation factor. This encourages the network to learn what features to expect normally and to identify where foreign patterns have been introduced. The estimate of the interpolation factor lends itself nicely to the derivation of an outlier score. Meanwhile the pixel-wise output allows for pixel- and subject- level predictions using the same model.
Our code is available at https://github.com/jemtan/FPI
Date Issued
2022-04-01
Date Acceptance
2022-04-01
Citation
Journal of Machine Learning for Biomedical Imaging, 2022, 2022 (013), pp.1-27
URI
URL
ISSN
2766-905X
Publisher
Melba
Start Page
1
End Page
27
Journal / Book Title
Journal of Machine Learning for Biomedical Imaging
Volume
2022
Issue
013
Copyright Statement
©2020 Tan, Hou, Batten, Qiu, and Kainz. This paper is open access under license: CC-BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
License URL
Sponsor
Engineering & Physical Science Research Council (E
Wellcome Trust
Wellcome Trust/EPSRC
Wellcome Trust
Engineering & Physical Science Research Council (E
Engineering and Physical Sciences Research Council (EPSRC)
Engineering & Physical Science Research Council (EPSRC)
Identifier
https://www.melba-journal.org/papers/2022:013.html
Grant Number
RTJ5557761-1
PO :RTJ5557761-1
NS/A000025/1
RTJ5557761
RTJ5557761-1
EP/S013687/1
EP/S013687/1
Publication Status
Published
Date Publish Online
2022-04-14