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

Deep generative models have enabled the automated synthesis of high-qualitydata for diverse applications. However, the most effective generative modelsare specialized to data from a single domain (e.g., images or text). Real-worldapplications such as healthcare require multi-modal data from multiple domains(e.g., both images and corresponding text), which are difficult to acquire dueto limited availability and privacy concerns and are much harder to synthesize.To tackle this joint synthesis challenge, we propose an End-to-end MultImodalX-ray genERative model (EMIXER) for jointly synthesizing x-ray images andcorresponding free-text reports, all conditional on diagnosis labels. EMIXER isan conditional generative adversarial model by 1) generating an image based ona label, 2) encoding the image to a hidden embedding, 3) producing thecorresponding text via a hierarchical decoder from the image embedding, and 4)a joint discriminator for assessing both the image and the corresponding text.EMIXER also enables self-supervision to leverage vast amount of unlabeled data.Extensive experiments with real X-ray reports data illustrate how dataaugmentation using synthesized multimodal samples can improve the performanceof a variety of supervised tasks including COVID-19 X-ray classification withvery limited samples. The quality of generated images and reports are alsoconfirmed by radiologists. We quantitatively show that EMIXER generatedsynthetic datasets can augment X-ray image classification, report generationmodels to achieve 5.94% and 6.9% improvement on models trained only on realdata samples. Taken together, our results highlight the promise of state ofgenerative models to advance clinical machine learning.

EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision