One-Class SVM on siamese neural network latent space for Unsupervised Anomaly Detection on brain MRI White Matter Hyperintensities
This addresses the problem of detecting subtle brain lesions in neuroimaging with limited supervision, though it is incremental as it builds on existing patch-based and outlier detection approaches.
The paper tackled unsupervised anomaly detection for brain MRI white matter hyperintensities by proposing a method using a siamese patch-based auto-encoder latent space with a One-Class SVM, achieving performance on par with the best state-of-the-art methods on a public challenge dataset.
Anomaly detection remains a challenging task in neuroimaging when little to no supervision is available and when lesions can be very small or with subtle contrast. Patch-based representation learning has shown powerful representation capacities when applied to industrial or medical imaging and outlier detection methods have been applied successfully to these images. In this work, we propose an unsupervised anomaly detection (UAD) method based on a latent space constructed by a siamese patch-based auto-encoder and perform the outlier detection with a One-Class SVM training paradigm tailored to the lesion detection task in multi-modality neuroimaging. We evaluate performances of this model on a public database, the White Matter Hyperintensities (WMH) challenge and show in par performance with the two best performing state-of-the-art methods reported so far.