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

We explore a solution for learning disease signatures from weakly, yet easilyobtainable, annotated volumetric medical imaging data by analyzing 3D volumesas a sequence of 2D images. We demonstrate the performance of our solution inthe detection of emphysema in lung cancer screening low-dose CT images. Ourapproach utilizes convolutional long short-term memory (LSTM) to "scan"sequentially through an imaging volume for the presence of disease in a portionof scanned region. This framework allowed effective learning given onlyvolumetric images and binary disease labels, thus enabling training from alarge dataset of 6,631 un-annotated image volumes from 4,486 patients. Whenevaluated in a testing set of 2,163 volumes from 2,163 patients, our modeldistinguished emphysema with area under the receiver operating characteristiccurve (AUC) of .83. This approach was found to outperform 2D convolutionalneural networks (CNN) implemented with various multiple-instance learningschemes (AUC=0.69-0.76) and a 3D CNN (AUC=.77).

Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network