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 fibrosis is a devastating chronic lung disease that causesirreparable lung tissue scarring and damage, resulting in progressive loss inlung capacity and has no known cure. A critical step in the treatment andmanagement of pulmonary fibrosis is the assessment of lung function decline,with computed tomography (CT) imaging being a particularly effective method fordetermining the extent of lung damage caused by pulmonary fibrosis. Motivatedby this, we introduce Fibrosis-Net, a deep convolutional neural network designtailored for the prediction of pulmonary fibrosis progression from chest CTimages. More specifically, machine-driven design exploration was leveraged todetermine a strong architectural design for CT lung analysis, upon which webuild a customized network design tailored for predicting forced vital capacity(FVC) based on a patient's CT scan, initial spirometry measurement, andclinical metadata. Finally, we leverage an explainability-driven performancevalidation strategy to study the decision-making behaviour of Fibrosis-Net asto verify that predictions are based on relevant visual indicators in CTimages. Experiments using a patient cohort from the OSIC Pulmonary FibrosisProgression Challenge showed that the proposed Fibrosis-Net is able to achievea significantly higher modified Laplace Log Likelihood score than the winningsolutions on the challenge. Furthermore, explainability-driven performancevalidation demonstrated that the proposed Fibrosis-Net exhibits correctdecision-making behaviour by leveraging clinically-relevant visual indicatorsin CT images when making predictions on pulmonary fibrosis progress. WhileFibrosis-Net is not yet a production-ready clinical assessment solution, wehope that its release in open source manner will encourage researchers,clinicians, and citizen data scientists alike to leverage and build upon it.

Fibrosis-Net: A Tailored Deep Convolutional Neural Network Design for Prediction of Pulmonary Fibrosis Progression from Chest CT Images