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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

CNN (Convolutional Neural Network) models have been successfully used forsegmentation of the left ventricle (LV) in cardiac MRI (Magnetic ResonanceImaging), providing clinical measurements. In practice, two questions arisewith deployment of CNNs: 1) when is it better to use a shallow model instead ofa deeper one? 2) how the size of a dataset might change the networkperformance? We propose a framework to answer them, by experimenting with deepand shallow versions of three U-Net families, trained from scratch in sixsubsets varying from 100 to 10,000 images, different network sizes, learningrates and regularization values. 1620 models were evaluated using 5-foldcross-validation by loss and DICE. The results indicate that: sample sizeaffects performance more than architecture or hyper-parameters; in smallsamples the performance is more sensitive to hyper-parameters thanarchitecture; the performance difference between shallow and deeper networks isnot the same across families.

A study of CNN capacity applied to Left Venticle Segmentation in Cardiac MRI