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

Liver cancer has high morbidity and mortality rates in the world. Multi-phaseCT is a main medical imaging modality for detecting/identifying and diagnosingliver tumors. Automatically detecting and classifying liver lesions in CTimages have the potential to improve the clinical workflow. This task remainschallenging due to liver lesions' large variations in size, appearance, imagecontrast, and the complexities of tumor types or subtypes. In this work, wecustomize a multi-object labeling tool for multi-phase CT images, which is usedto curate a large-scale dataset containing 1,631 patients with four-phase CTimages, multi-organ masks, and multi-lesion (six major types of liver lesionsconfirmed by pathology) masks. We develop a two-stage liver lesion detectionpipeline, where the high-sensitivity detecting algorithms in the first stagediscover as many lesion proposals as possible, and the lesion-reclassificationalgorithms in the second stage remove as many false alarms as possible. Themulti-sensitivity lesion detection algorithm maximizes the informationutilization of the individual probability maps of segmentation, and thelesion-shuffle augmentation effectively explores the texture contrast betweenlesions and the liver. Independently tested on 331 patient cases, the proposedmodel achieves high sensitivity and specificity for malignancy classificationin the multi-phase contrast-enhanced CT (99.2%, 97.1%, diagnosis setting) andin the noncontrast CT (97.3%, 95.7%, screening setting).

A Cascaded Approach for ultraly High Performance Lesion Detection and False Positive Removal in Liver CT Scans