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

Medical Ultrasound (US) is one of the most widely used imaging modalities inclinical practice, but its usage presents unique challenges such as variableimaging quality. Deep Learning (DL) models can serve as advanced medical USimage analysis tools, but their performance is greatly limited by the scarcityof large datasets. To solve the common data shortage, we develop GSDA, aGenerative Adversarial Network (GAN)-based semi-supervised data augmentationmethod. GSDA consists of the GAN and Convolutional Neural Network (CNN). TheGAN synthesizes and pseudo-labels high-resolution, high-quality US images, andboth real and synthesized images are then leveraged to train the CNN. Toaddress the training challenges of both GAN and CNN with limited data, weemploy transfer learning techniques during their training. We also introduce anovel evaluation standard that balances classification accuracy withcomputational time. We evaluate our method on the BUSI dataset and GSDAoutperforms existing state-of-the-art methods. With the high-resolution andhigh-quality images synthesized, GSDA achieves a 97.9% accuracy using merely780 images. Given these promising results, we believe that GSDA holds potentialas an auxiliary tool for medical US analysis.

GSDA: Generative Adversarial Network-based Semi-Supervised Data Augmentation for Ultrasound Image Classification