Detecting Out-of-Distribution via an Unsupervised Uncertainty Estimation for Prostate Cancer Diagnosis

Jingya Liu, Bin Lou, Mamadou Diallo, Tongbai Meng, Heinrich von Busch, Robert Grimm, Yingli Tian, Dorin Comaniciu, Ali Kamen, David Winkel, henkjan huisman, Angela Tong, Tobias Penzkofer, Ivan Shabunin, Moon Hyung Choi, Pengyi Xing, Dieter Szolar, Steven Shea, Fergus Coakley, Mukesh Harisinghani

Keywords: Out-of-distribution Detection, Uncertainty Estimation, AutoEncoder, Prostate Cancer Diagnosis

TL;DR: This paper proposed an end-to-end unsupervised framework to identify OOD cases that are likely to generate degraded PCa detection performance due to the data distribution shifts.

Abstract: Artificial intelligence-based prostate cancer (PCa) detection models have been widely explored to assist clinical diagnosis. However, these trained models may generate erroneous results specifically on datasets that are not within training distribution. In this paper, we propose an approach to tackle this so-called out-of-distribution (OOD) data problem. Specifically, we devise an end-to-end unsupervised framework to estimate uncertainty values for cases analyzed by a previously trained PCa detection model. Our PCa detection model takes the inputs of bpMRI scans and through our proposed approach we identify OOD cases that are likely to generate degraded performance due to the data distribution shifts. The proposed OOD framework consists of two parts. First, an autoencoder-based reconstruction network is proposed, which learns discrete latent representations of in-distribution data. Second, the uncertainty is computed using perceptual loss that measures the distance between original and reconstructed images in the feature space of a pre-trained PCa detection network. The effectiveness of the proposed framework is evaluated on seven independent data collections with a total of 1,432 cases. The performance of pre-trained PCa detection model is significantly improved by excluding cases with high uncertainty.

Registration: I acknowledge that publication of this at MIDL and in the proceedings 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: both

Primary Subject Area: Uncertainty Estimation

Secondary Subject Area: Unsupervised Learning and Representation Learning

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.