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

While medical image segmentation is an important task for computer aideddiagnosis, the high expertise requirement for pixelwise manual annotationsmakes it a challenging and time consuming task. Since conventional dataaugmentations do not fully represent the underlying distribution of thetraining set, the trained models have varying performance when tested on imagescaptured from different sources. Most prior work on image synthesis for dataaugmentation ignore the interleaved geometric relationship between differentanatomical labels. We propose improvements over previous GAN-based medicalimage synthesis methods by learning the relationship between differentanatomical labels. We use a weakly supervised segmentation method to obtainpixel level semantic label map of images which is used learn the intrinsicrelationship of geometry and shape across semantic labels. Latent spacevariable sampling results in diverse generated images from a base image andimproves robustness. We use the synthetic images from our method to trainnetworks for segmenting COVID-19 infected areas from lung CT images. Theproposed method outperforms state-of-the-art segmentation methods on a publicdataset. Ablation studies also demonstrate benefits of integrating geometry anddiversity.

CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis