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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Imaging phantoms are test patterns used to measure image quality in computertomography (CT) systems. A new phantom platform (Mercury Phantom, Gammex)provides test patterns for estimating the task transfer function (TTF) or noisepower spectrum (NPF) and simulates different patient sizes. Determining whichimage slices are suitable for analysis currently requires manual annotation ofthese patterns by an expert, as subtle defects may make an image unsuitable formeasurement. We propose a method of automatically classifying these testpatterns in a series of phantom images using deep learning techniques. Byadapting a convolutional neural network based on the VGG19 architecture withweights trained on ImageNet, we use transfer learning to produce a classifierfor this domain. The classifier is trained and evaluated with over 3,500phantom images acquired at a university medical center. Input channels forcolor images are successfully adapted to convey contextual information forphantom images. A series of ablation studies are employed to verify designaspects of the classifier and evaluate its performance under varying trainingconditions. Our solution makes extensive use of image augmentation to produce aclassifier that accurately classifies typical phantom images with 98% accuracy,while maintaining as much as 86% accuracy when the phantom is improperlyimaged.

Automatic phantom test pattern classification through transfer learning with deep neural networks