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/

Zendy Plus

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

Zendy Tools

Zendy Open

Data availability plays a critical role for the performance of deep learningsystems. This challenge is especially acute within the medical image domain,particularly when pathologies are involved, due to two factors: 1) limitednumber of cases, and 2) large variations in location, scale, and appearance. Inthis work, we investigate whether augmenting a dataset with artificiallygenerated lung nodules can improve the robustness of the progressiveholistically nested network (P-HNN) model for pathological lung segmentation ofCT scans. To achieve this goal, we develop a 3D generative adversarial network(GAN) that effectively learns lung nodule property distributions in 3D space.In order to embed the nodules within their background context, we condition theGAN based on a volume of interest whose central part containing the nodule hasbeen erased. To further improve realism and blending with the background, wepropose a novel multi-mask reconstruction loss. We train our method on over1000 nodules from the LIDC dataset. Qualitative results demonstrate theeffectiveness of our method compared to the state-of-art. We then use our GANto generate simulated training images where nodules lie on the lung border,which are cases where the published P-HNN model struggles. Qualitative andquantitative results demonstrate that armed with these simulated images, theP-HNN model learns to better segment lung regions under these challengingsituations. As a result, our system provides a promising means to help overcomethe data paucity that commonly afflicts medical imaging.

CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation