An automated knowledge based treatment planning solution for prostate VMAT
Wood, Joe Aznar, Marianne Camille Whitehurst, Philip
Wood, Joe
Aznar, Marianne Camille
Whitehurst, Philip
Citations
Altmetric:
Abstract
Purpose or Objective
This work aimed to develop a novel approach to knowledge
based (KB) prostate VMAT treatment planning.
Material and Methods
Converting well defined PTV dose criteria into optimisation
objectives is relatively straightforward. OARs, however,
present a greater challenge because they sit in steep dose
gradients and their size, shape and position relative to
PTVs vary between patients. Precisely predicting optimal
OAR DVH parameters is therefore difficult and
uncertainties in the predictions ultimately become
manifest in the degree to which treatment plans are
dosimetrically optimal.
The optimal PTV-OAR dose gradient (i.e. dose fall-off per
unit distance) is characterised primarily by delivery
machine parameters and not patient anatomy. On this
basis, a model of the ideal prostate treatment plan was
developed – see Figure 1, where the colour gradients
represent achievable PTV-OAR dose gradients. Results
For 114 of the 142 test cases, at least one of the new plans
(average or 25th percentile) met all of the dose criteria for
prostate radiotherapy at The Christie. Furthermore, for
105 of the test cases, at least one of the new plans was
superior to the original clinical plan. In Figure 2, PTVRectum
dose gradient is plotted against PTV-Bladder dose
gradient for the KB training data (transparent red), clinical
test data (solid red), average new treatment plans (yellow)
and 25th percentile new treatment plans (blue).
Figure 2: Treatment plans generated using KB dose
gradient optimisation (blue and yellow) show more
consistent and steeper PTV-OAR dose gradients than
corresponding clinical treatment plans (red).
Visual review of the new treatment plans for 10 patients
from the test cohort showed that all were considered
clinically acceptable.
Conclusion
A novel approach to KB treatment planning for prostate
VMAT has been proposed, trained and tested. Initial results
show that treatment plans generated automatically from
the predictions of the model are clinically acceptable in
more than 80 % of cases and show superior and more
consistent OAR sparing than their corresponding clinical
treatment plans. Although there is scope for refinement of
the predictions, this method shows promise for realising
significant efficiencies within treatment planning
departments and with the transfer of knowledge between
centres.
Description
Date
2020
Publisher
Collections
Keywords
Type
Meetings and Proceedings
Citation
Wood J, Aznar M, Whitehurst P. PO-1506: An automated knowledge based treatment planning solution for prostate VMAT. Radiotherapy and Oncology . 2020 Nov;152:S813.