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

Machine learning-based segmentation in medical imaging is widely used inclinical applications from diagnostics to radiotherapy treatment planning.Segmented medical images with ground truth are useful for investigating theproperties of different segmentation performance metrics to inform metricselection. Regular geometrical shapes are often used to synthesize segmentationerrors and illustrate properties of performance metrics, but they lack thecomplexity of anatomical variations in real images. In this study, we present atool to emulate segmentations by adjusting the reference (truth) masks ofanatomical objects extracted from real medical images. Our tool is designed tomodify the defined truth contours and emulate different types of segmentationerrors with a set of user-configurable parameters. We defined the ground truthobjects from 230 patient images in the Glioma Image Segmentation forRadiotherapy (GLIS-RT) database. For each object, we used our segmentationsynthesis tool to synthesize 10 versions of segmentation (i.e., 10 simulatedsegmentors or algorithms), where each version has a pre-defined combination ofsegmentation errors. We then applied 20 performance metrics to evaluate allsynthetic segmentations. We demonstrated the properties of these metrics,including their ability to capture specific types of segmentation errors. Byanalyzing the intrinsic properties of these metrics and categorizing thesegmentation errors, we are working toward the goal of developing adecision-tree tool for assisting in the selection of segmentation performancemetrics.

Informing selection of performance metrics for medical image segmentation evaluation using configurable synthetic errors