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

Creating a dataset for training supervised machine learning algorithms can bea demanding task. This is especially true for medical image segmentation sinceone or more specialists are usually required for image annotation, and creatingground truth labels for just a single image can take up to several hours. Inaddition, it is paramount that the annotated samples represent well thedifferent conditions that might affect the imaged tissues as well as possiblechanges in the image acquisition process. This can only be achieved byconsidering samples that are typical in the dataset as well as atypical, oreven outlier, samples. We introduce a new sampling methodology for selectingrelevant images from a large dataset in a way that evenly considers bothprototypical as well as atypical samples. The methodology involves thegeneration of a uniform grid from a feature space representing the samples,which is then used for randomly drawing relevant images. The selected imagesprovide a uniform covering of the original dataset, and thus define aheterogeneous set of images that can be annotated and used for trainingsupervised segmentation algorithms. We provide a case example by creating adataset containing a representative set of blood vessel microscopy imagesselected from a larger dataset containing thousands of images. The dataset,which we call VessMAP, is being made available online to aid the development ofnew blood vessel segmentation algorithms.

A new sampling methodology for defining heterogeneous subsets of samples for training image segmentation algorithms