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

Magnetic Resonance (MR) imaging allows the acquisition of images withdifferent contrast properties depending on the acquisition protocol and themagnetic properties of tissues. Many MR brain image processing techniques, suchas tissue segmentation, require multiple MR contrasts as inputs, and eachcontrast is treated differently. Thus it is advantageous to automate theidentification of image contrasts for various purposes, such as facilitatingimage processing pipelines, and managing and maintaining large databases viacontent-based image retrieval (CBIR). Most automated CBIR techniques focus on atwo-step process: extracting features from data and classifying the image basedon these features. We present a novel 3D deep convolutional neural network(CNN)-based method for MR image contrast classification. The proposed CNNautomatically identifies the MR contrast of an input brain image volume.Specifically, we explored three classification problems: (1) identifyT1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery(FLAIR) contrasts, (2) identify pre vs post-contrast T1, (3) identify pre vspost-contrast FLAIR. A total of 3418 image volumes acquired from multiple sitesand multiple scanners were used. To evaluate each task, the proposed model wastrained on 2137 images and tested on the remaining 1281 images. Results showedthat image volumes were correctly classified with 97.57% accuracy.

Classifying magnetic resonance image modalities with convolutional neural networks