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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We aim to optimize the binary detection of Chronic Obstructive PulmonaryDisease (COPD) based on emphysema presence in the lung with convolutionalneural networks (CNN) by exploring manually adjusted versus automatedwindow-setting optimization (WSO) on computed tomography (CT) images. 7,194 CTimages (3,597 with COPD; 3,597 healthy controls) from 78 subjects (43 withCOPD; 35 healthy controls) were selected retrospectively (10.2018-12.2019) andpreprocessed. For each image, intensity values were manually clipped to theemphysema window setting and a baseline 'full-range' window setting.Class-balanced train, validation, and test sets contained 3,392, 1,114, and2,688 images. The network backbone was optimized by comparing various CNNarchitectures. Furthermore, automated WSO was implemented by adding acustomized layer to the model. The image-level area under the ReceiverOperating Characteristics curve (AUC) [lower, upper limit 95% confidence] wasutilized to compare model variations. Repeated inference (n=7) on the test setshowed that the DenseNet was the most efficient backbone and achieved a meanAUC of 0.80 [0.76, 0.85] without WSO. Comparably, with input images manuallyadjusted to the emphysema window, the DenseNet model predicted COPD with a meanAUC of 0.86 [0.82, 0.89]. By adding a customized WSO layer to the DenseNet, anoptimal window in the proximity of the emphysema window setting was learnedautomatically, and a mean AUC of 0.82 [0.78, 0.86] was achieved. Detection ofCOPD with DenseNet models was improved by WSO of CT data to the emphysemawindow setting range.

Optimizing Convolutional Neural Networks for Chronic Obstructive Pulmonary Disease Detection in Clinical Computed Tomography Imaging