English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Pathological brain lesions exhibit diverse appearance in brain images, interms of intensity, texture, shape, size, and location. Comprehensive sets ofdata and annotations are difficult to acquire. Therefore, unsupervised anomalydetection approaches have been proposed using only normal data for training,with the aim of detecting outlier anomalous voxels at test time. Denoisingmethods, for instance classical denoising autoencoders (DAEs) and more recentlyemerging diffusion models, are a promising approach, however naive applicationof pixelwise noise leads to poor anomaly detection performance. We show thatoptimization of the spatial resolution and magnitude of the noise improves theperformance of different model training regimes, with similar noise parameteradjustments giving good performance for both DAEs and diffusion models. Visualinspection of the reconstructions suggests that the training noise influencesthe trade-off between the extent of the detail that is reconstructed and theextent of erasure of anomalies, both of which contribute to better anomalydetection performance. We validate our findings on two real-world datasets(tumor detection in brain MRI and hemorrhage/ischemia/tumor detection in brainCT), showing good detection on diverse anomaly appearances. Overall, we findthat a DAE trained with coarse noise is a fast and simple method that givesstate-of-the-art accuracy. Diffusion models applied to anomaly detection are asyet in their infancy and provide a promising avenue for further research.

The role of noise in denoising models for anomaly detection in medical images