Typicality Excels Likelihood for Unsupervised Out-of-Distribution Detection in Medical Imaging

Detecting pathological abnormalities in medical images in an unsupervised manner holds potential for advancing modern medical diagnostics. However, supervised methods encounter challenges with exceedingly unbalanced training distributions due to limited clinical incidence rates. Likelihood-based unsupervised Out-of-Distribution (OOD) detection with generative models, especially Normalizing Flows, in which pathological abnormalities are considered OOD, could offer a promising solution. However, research in this direction has shown limited success as prior work has revealed that the likelihood does not accurately reflect the degree of anomaly for OOD samples, where in many instances higher likelihoods are assigned to anomalous samples compared to training samples. In this study, we present the first exploration of typicality (i.e. determining if samples belong to the typical set) for OOD detection in medical imaging, where test samples are juxtaposed against the probability mass rather than the density. The obtained findings demonstrate the superiority of evaluating typicality against likelihood for finding pathological abnormalities. We achieve state-of-the-art performance on the ISIC, COVID-19, and RSNA Pneumonia datasets, while being robust against significant data imbalances.