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

Diagnosing knee joint osteoarthritis (KOA), a major cause of disabilityworldwide, is challenging due to subtle radiographic indicators and the variedprogression of the disease. Using deep learning for KOA diagnosis requiresbroad, comprehensive datasets. However, obtaining these datasets posessignificant challenges due to patient privacy concerns and data collectionrestrictions. Additive data augmentation, which enhances data variability,emerges as a promising solution. Yet, it's unclear which augmentationtechniques are most effective for KOA. This study explored various dataaugmentation methods, including adversarial augmentations, and their impact onKOA classification model performance. While some techniques improvedperformance, others commonly used underperformed. We identified potentialconfounding regions within the images using adversarial augmentation. This wasevidenced by our models' ability to classify KL0 and KL4 grades accurately,with the knee joint omitted. This observation suggested a model bias, whichmight leverage unrelated features for classification currently present inradiographs. Interestingly, removing the knee joint also led to an unexpectedimprovement in KL1 classification accuracy. To better visualize theseparadoxical effects, we employed Grad-CAM, highlighting the associated regions.Our study underscores the need for careful technique selection for improvedmodel performance and identifying and managing potential confounding regions inradiographic KOA deep learning.

Exploring the Efficacy of Base Data Augmentation Methods in Deep Learning-Based Radiograph Classification of Knee Joint Osteoarthritis