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

The detection of lesions in magnetic resonance imaging (MRI)-scans of humanbrains remains challenging, time-consuming and error-prone. Recently,unsupervised anomaly detection (UAD) methods have shown promising results forthis task. These methods rely on training data sets that solely contain healthysamples. Compared to supervised approaches, this significantly reduces the needfor an extensive amount of labeled training data. However, data labellingremains error-prone. We study how unhealthy samples within the training dataaffect anomaly detection performance for brain MRI-scans. For our evaluations,we consider three publicly available data sets and use autoencoders (AE) as awell-established baseline method for UAD. We systematically evaluate the effectof impured training data by injecting different quantities of unhealthy samplesto our training set of healthy samples from T1-weighted MRI-scans. We evaluatea method to identify falsely labeled samples directly during training based onthe reconstruction error of the AE. Our results show that training with impureddata decreases the UAD performance notably even with few falsely labeledsamples. By performing outlier removal directly during training based on thereconstruction-loss, we demonstrate that falsely labeled data can be detectedand removed to mitigate the effect of falsely labeled data. Overall, wehighlight the importance of clean data sets for UAD in brain MRI anddemonstrate an approach for detecting falsely labeled data directly duringtraining.

Unsupervised Anomaly Detection in 3D Brain MRI using Deep Learning with impured training data