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 quality of patient care associated with diagnostic radiology isproportionate to a physician workload. Segmentation is a fundamental limitingprecursor to both diagnostic and therapeutic procedures. Advances in machinelearning (ML) aim to increase diagnostic efficiency by replacing a singleapplication with generalized algorithms. The goal of unsupervised anomalydetection (UAD) is to identify potential anomalous regions unseen duringtraining, where convolutional neural network (CNN) based autoencoders (AEs) andvariational autoencoders (VAEs) are considered a de facto approach forreconstruction based-anomaly segmentation. The restricted receptive field inCNNs limits the CNN to model the global context. Hence, if the anomalousregions cover large parts of the image, the CNN-based AEs are not capable ofbringing a semantic understanding of the image. Meanwhile, vision transformers(ViTs) have emerged as a competitive alternative to CNNs. It relies on theself-attention mechanism that can relate image patches to each other. Weinvestigate in this paper Transformer capabilities in building AEs for thereconstruction-based UAD task to reconstruct a coherent and more realisticimage. We focus on anomaly segmentation for brain magnetic resonance imaging(MRI) and present five Transformer-based models while enabling segmentationperformance comparable to or superior to state-of-the-art (SOTA) models. Thesource code is made publicly available on GitHub:https://github.com/ahmedgh970/Transformers_Unsupervised_Anomaly_Segmentation.git.

Transformer based Models for Unsupervised Anomaly Segmentation in Brain MR Images