q-Space Novelty Detection with Variational Autoencoders
This work addresses the problem of detecting abnormalities like multiple sclerosis lesions in medical images without labeled lesion data, which is incremental as it builds on existing VAE-based novelty detection approaches.
The authors tackled novelty detection in medical imaging by proposing a family of methods based on variational autoencoders (VAEs) trained only on normal data, achieving performance that outperforms previous methods for detecting multiple sclerosis lesions in diffusion MRI scans and state-of-the-art results on the MNIST dataset.
In machine learning, novelty detection is the task of identifying novel unseen data. During training, only samples from the normal class are available. Test samples are classified as normal or abnormal by assignment of a novelty score. Here we propose novelty detection methods based on training variational autoencoders (VAEs) on normal data. Since abnormal samples are not used during training, we define novelty metrics based on the (partially complementary) assumptions that the VAE is less capable of reconstructing abnormal samples well; that abnormal samples more strongly violate the VAE regularizer; and that abnormal samples differ from normal samples not only in input-feature space, but also in the VAE latent space and VAE output. These approaches, combined with various possibilities of using (e.g. sampling) the probabilistic VAE to obtain scalar novelty scores, yield a large family of methods. We apply these methods to magnetic resonance imaging, namely to the detection of diffusion-space (q-space) abnormalities in diffusion MRI scans of multiple sclerosis patients, i.e. to detect multiple sclerosis lesions without using any lesion labels for training. Many of our methods outperform previously proposed q-space novelty detection methods. We also evaluate the proposed methods on the MNIST handwritten digits dataset and show that many of them are able to outperform the state of the art.