Keywords: Unsupervised Pathology Detection, Domain Shift, Confounders
TL;DR: We show that the good image-level performance of unsupervised pathology detection methods on the Hyper-Kvasir dataset mainly relates to the domain shift between images with and without polyps and not to the actual presence of polyps
Abstract: Unsupervised Pathology Detection (UPD) has recently received considerable attention in medical image diagnosis. However, the lack of publicly available benchmark datasets for UPD makes researchers fall back on datasets that were originally created for other tasks. These datasets may exhibit domain shift that acts as a confounding variable, fooling observers into believing that the models excel at detecting pathologies, while a significant part of the model’s performance is detecting the domain shift. In this short paper, we show on the example of the Hyper-Kvasir dataset, how confounding variables can dramatically skew the actual performance of pathology detection methods.
Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: novel methodological ideas without extensive validation
Primary Subject Area: Detection and Diagnosis
Secondary Subject Area: Learning with Noisy Labels and Limited Data
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.