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

Non-invasive radiological-based lesion characterization and identification,e.g., to differentiate cancer subtypes, has long been a major aim to enhanceoncological diagnosis and treatment procedures. Here we study a specificpopulation of human subjects, with the hope of reducing the need for invasivesurgical biopsies of liver cancer patients, which can cause many harmfulside-effects. To this end, we propose a fully-automated and multi-stage livertumor characterization framework designed for dynamic contrast computedtomography (CT). Our system comprises four sequential processes of tumorproposal detection, tumor harvesting, primary tumor site selection, and deeptexture-based tumor characterization. Our main contributions are that, (1) wepropose a 3D non-isotropic anchor-free detection method for liver lesions; (2)we present and validate spatially adaptivedeep texture (SaDT) learning, whichallows for more precise characterization of liver lesions; (3) using asemi-automatic process, we bootstrap off of 200 gold standard annotations tocurate another 1001 patients. Experimental evaluations demonstrate that our newdata curation strategy, combined with the SaDT deep dynamic texture analysis,can effectively improve the mean F1 scores by >8.6% compared with baselines, indifferentiating four major liver lesion types. Our F1 score of (hepatocellularcarcinoma versus remaining subclasses) is 0.763, which is higher than reportedhuman observer performance using dynamic CT and comparable to an advancedmagnetic resonance imagery protocol. Apart from demonstrating the benefits ofour data curation approach and physician-inspired workflow, these results alsoindicate that analyzing texture features, instead of standard object-basedanalysis, is a promising strategy for lesion differentiation.

Harvesting, Detecting, and Characterizing Liver Lesions from Large-scale Multi-phase CT Data via Deep Dynamic Texture Learning