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

The identification of lesion within medical image data is necessary fordiagnosis, treatment and prognosis. Segmentation and classification approachesare mainly based on supervised learning with well-paired image-level orvoxel-level labels. However, labeling the lesion in medical images is laboriousrequiring highly specialized knowledge. We propose a medical image synthesismodel named abnormal-to-normal translation generative adversarial network(ANT-GAN) to generate a normal-looking medical image based on itsabnormal-looking counterpart without the need for paired training data. Unliketypical GANs, whose aim is to generate realistic samples with variations, ourmore restrictive model aims at producing a normal-looking image correspondingto one containing lesions, and thus requires a special design. Being able toprovide a "normal" counterpart to a medical image can provide useful sideinformation for medical imaging tasks like lesion segmentation orclassification validated by our experiments. In the other aspect, the ANT-GANmodel is also capable of producing highly realistic lesion-containing imagecorresponding to the healthy one, which shows the potential in dataaugmentation verified in our experiments.

An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection