Oversight in medical images is a crucial problem, and timely reporting of medical images is desired. Therefore, an all-purpose anomaly detection method that can detect virtually all types of lesions/diseases in a given image is strongly desired. However, few commercially available and versatile anomaly detection methods for medical images have been provided so far. Recently, anomaly detection methods built upon deep learning methods have been rapidly growing in popularity, and these methods seem to provide reasonable solutions to the problem. However, the workload to label the images necessary for training in deep learning remains heavy. In this study, we present an anomaly detection method based on two trained flow-based generative models. With this method, the posterior probability can be computed as a normality metric for any given image. The training of the generative models requires two sets of images: a set containing only normal images and another set containing both normal and abnormal images without any labels. In the latter set, each sample does not have to be labeled as normal or abnormal; therefore, any mixture of images (e.g., all cases in a hospital) can be used as the dataset without cumbersome manual labeling. The method was validated with two types of medical images: chest X-ray radiographs (CXRs) and brain computed tomographies (BCTs). The areas under the receiver operating characteristic curves for logarithm posterior probabilities of CXRs (0.868 for pneumonia-like opacities) and BCTs (0.904 for infarction) were comparable to those in previous studies with other anomaly detection methods. This result showed the versatility of our method.
Download