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

Finding and identifying scatteredly-distributed, small, and criticallyimportant objects in 3D oncology images is very challenging. We focus on thedetection and segmentation of oncology-significant (or suspicious cancermetastasized) lymph nodes (OSLNs), which has not been studied before as acomputational task. Determining and delineating the spread of OSLNs isessential in defining the corresponding resection/irradiating regions for thedownstream workflows of surgical resection and radiotherapy of various cancers.For patients who are treated with radiotherapy, this task is performed byexperienced radiation oncologists that involves high-level reasoning on whetherLNs are metastasized, which is subject to high inter-observer variations. Inthis work, we propose a divide-and-conquer decision stratification approachthat divides OSLNs into tumor-proximal and tumor-distal categories. This ismotivated by the observation that each category has its own differentunderlying distributions in appearance, size and other characteristics. Twoseparate detection-by-segmentation networks are trained per category and fused.To further reduce false positives (FP), we present a novel global-local network(GLNet) that combines high-level lesion characteristics with features learnedfrom localized 3D image patches. Our method is evaluated on a dataset of 141esophageal cancer patients with PET and CT modalities (the largest to-date).Our results significantly improve the recall from $45\%$ to $67\%$ at $3$ FPsper patient as compared to previous state-of-the-art methods. The highestachieved OSLN recall of $0.828$ is clinically relevant and valuable.

Detecting Scatteredly-Distributed, Small, andCritically Important Objects in 3D OncologyImaging via Decision Stratification