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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Pancreatic cancer with more than 60,000 new cases each year has less than 10percent 5-year overall survival. Radiation therapy (RT) is an effectivetreatment for Locally advanced pancreatic cancer (LAPC). The current clinicalRT workflow is lengthy and involves separate image acquisition for diagnosticCT (dCT) and planning CT (pCT). Studies have shown a reduction in mortalityrate from expeditious radiotherapy treatment. dCT and pCT are acquiredseparately because of the differences in the image acquisition setup andpatient body. We are presenting deepPERFECT: deep learning-based model to adaptthe shape of the patient body on dCT to the treatment delivery setup. Ourmethod expedites the treatment course by allowing the design of the initial RTplanning before the pCT acquisition. Thus, the physicians can evaluate thepotential RT prognosis ahead of time, verify the plan on the treatment day-oneCT and apply any online adaptation if needed. We used the data from 25pancreatic cancer patients. The model was trained on 15 cases and tested on theremaining ten cases. We evaluated the performance of four differentdeep-learning architectures for this task. The synthesized CT (sCT) and regionsof interest (ROIs) were compared with ground truth (pCT) using Dice similaritycoefficient (DSC) and Hausdorff distance (HD). We found that thethree-dimensional Generative Adversarial Network (GAN) model trained on largepatches has the best performance. The average DSC and HD for body contours were0.93, and 4.6 mm. We found no statistically significant difference between thesynthesized CT plans and the ground truth. We showed that employing deepPERFECTshortens the current lengthy clinical workflow by at least one week andimproves the effectiveness of treatment and the quality of life of pancreaticcancer patients.

deepPERFECT: Novel Deep Learning CT Synthesis Method for Expeditious Pancreatic Cancer Radiotherapy