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

Deep learning (DL) 3D dose prediction has recently gained a lot of attention.However, the variability of plan quality in the training dataset, generatedmanually by planners with wide range of expertise, can dramatically effect thequality of the final predictions. Moreover, any changes in the clinicalcriteria requires a new set of manually generated plans by planners to build anew prediction model. In this work, we instead use consistent plans generatedby our in-house automated planning system (named ``ECHO'') to train the DLmodel. ECHO (expedited constrained hierarchical optimization) generatesconsistent/unbiased plans by solving large-scale constrained optimizationproblems sequentially. If the clinical criteria changes, a new training dataset can be easily generated offline using ECHO, with no or limited humanintervention, making the DL-based prediction model easily adaptable to thechanges in the clinical practice. We used 120 conventional lung patients (100for training, 20 for testing) with different beam configurations and trainedour DL-model using manually-generated as well as automated ECHO plans. Weevaluated different inputs: (1) CT+(PTV/OAR)contours, and (2) CT+contours+beamconfigurations, and different loss functions: (1) MAE (mean absolute error),and (2) MAE+DVH (dose volume histograms). The quality of the predictions wascompared using different DVH metrics as well as dose-score and DVH-score,recently introduced by the AAPM knowledge-based planning grand challenge. Thebest results were obtained using automated ECHO plans and CT+contours+beam astraining inputs and MAE+DVH as loss function.

Deep Learning 3D Dose Prediction for Conventional Lung IMRT Using Consistent/Unbiased Automated Plans