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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Chest x-rays are the most common radiology studies for diagnosing lung andheart disease. Hence, a system for automated pre-reporting of pathologicfindings on chest x-rays would greatly enhance radiologists' productivity. Tothis end, we investigate a deep-learning framework with novel training schemesfor classification of different thoracic pathology labels from chest x-rays. Weuse the currently largest publicly available annotated dataset ChestX-ray14 of112,120 chest radiographs of 30,805 patients. Each image was annotated witheither a 'NoFinding' class, or one or more of 14 thoracic pathology labels.Subjects can have multiple pathologies, resulting in a multi-class, multi-labelproblem. We encoded labels as binary vectors using k-hot encoding. We study theResNet34 architecture, pre-trained on ImageNet, where two key modificationswere incorporated into the training framework: (1) Stochastic gradient descentwith momentum and with restarts using cosine annealing, (2) Variable imagesizes for fine-tuning to prevent overfitting. Additionally, we use a heuristicalgorithm to select a good learning rate. Learning with restarts was used toavoid local minima. Area Under receiver operating characteristics Curve (AUC)was used to quantitatively evaluate diagnostic quality. Our results arecomparable to, or outperform the best results of current state-of-the-artmethods with AUCs as follows: Atelectasis:0.81, Cardiomegaly:0.91,Consolidation:0.81, Edema:0.92, Effusion:0.89, Emphysema: 0.92, Fibrosis:0.81,Hernia:0.84, Infiltration:0.73, Mass:0.85, Nodule:0.76, PleuralThickening:0.81, Pneumonia:0.77, Pneumothorax:0.89 and NoFinding:0.79. Ourresults suggest that, in addition to using sophisticated network architectures,a good learning rate, scheduler and a robust optimizer can boost performance.

Automated Identification of Thoracic Pathology from Chest Radiographs with Enhanced Training Pipeline