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

Automated segmentation of esophagus is critical in image guided/adaptiveradiotherapy of lung cancer to minimize radiation-induced toxicities such asacute esophagitis. We developed a semantic physics-based data augmentationmethod for segmenting esophagus in both planning CT (pCT) and cone-beam CT(CBCT) using 3D convolutional neural networks. 191 cases with their pCT andCBCTs from four independent datasets were used to train a modified 3D-Unetarchitecture with a multi-objective loss function specifically designed forsoft-tissue organs such as esophagus. Scatter artifacts and noise wereextracted from week 1 CBCTs using power law adaptive histogram equalizationmethod and induced to the corresponding pCT followed by reconstruction usingCBCT reconstruction parameters. Moreover, we leverage physics-based artifactinduced pCTs to drive the esophagus segmentation in real weekly CBCTs.Segmentations were evaluated using geometric Dice and Hausdorff distance aswell as dosimetrically using mean esophagus dose and D5cc. Due to thephysics-based data augmentation, our model trained just on the synthetic CBCTswas robust and generalizable enough to also produce state-of-the-art results onthe pCTs and CBCTs, achieving 0.81 and 0.74 Dice overlap. Our physics-baseddata augmentation spans the realistic noise/artifact spectrum across patientCBCT/pCT data and can generalize well across modalities with the potential toimprove the accuracy of treatment setup and response analysis.

Generalizable Cone Beam CT Esophagus Segmentation Using Physics-Based Data Augmentation