Detecting Outliers with Foreign Patch Interpolation

Jeremy Tan1, Benjamin Hou1, James Batten1, Huaqi Qiu1, Bernhard Kainz1
1: Imperial College London
Publication date: 2022/04/14
PDF · Code · arXiv


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


self-supervised learning · medical imaging · outlier detection

Bibtex @article{melba:2022:013:tan, title = "Detecting Outliers with Foreign Patch Interpolation", author = "Tan, Jeremy and Hou, Benjamin and Batten, James and Qiu, Huaqi and Kainz, Bernhard", journal = "Machine Learning for Biomedical Imaging", volume = "1", issue = "April 2022 issue", year = "2022", pages = "1--27", issn = "2766-905X", doi = "", url = "" }
RISTY - JOUR AU - Tan, Jeremy AU - Hou, Benjamin AU - Batten, James AU - Qiu, Huaqi AU - Kainz, Bernhard PY - 2022 TI - Detecting Outliers with Foreign Patch Interpolation T2 - Machine Learning for Biomedical Imaging VL - 1 IS - April 2022 issue SP - 1 EP - 27 SN - 2766-905X DO - UR - ER -

2022:013 cover