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

Pulmonary nodule detection using low-dose Computed Tomography (CT) is oftenthe first step in lung disease screening and diagnosis. Recently, algorithmsbased on deep convolutional neural nets have shown great promise for automatednodule detection. Most of the existing deep learning nodule detection systemsare constructed in two steps: a) nodule candidates screening and b) falsepositive reduction, using two different models trained separately. Although itis commonly adopted, the two-step approach not only imposes significantresource overhead on training two independent deep learning models, but also issub-optimal because it prevents cross-talk between the two. In this work, wepresent an end-to-end framework for nodule detection, integrating nodulecandidate screening and false positive reduction into one model, trainedjointly. We demonstrate that the end-to-end system improves the performance by3.88\% over the two-step approach, while at the same time reducing modelcomplexity by one third and cutting inference time by 3.6 fold. Code will bemade publicly available.

An End-to-end Framework For Integrated Pulmonary Nodule Detection and False Positive Reduction