2018
DOI: 10.1002/mp.12930
|View full text |Cite
|
Sign up to set email alerts
|

Knowledge‐based automated planning for oropharyngeal cancer

Abstract: We automatically generate intensity-modulated radiation therapy plans for oropharyngeal cancer by combining knowledge-based planning (KBP) predictions with an inverse optimization (IO) pipeline into a single automated treatment planning pipeline. We extended two existing KBP methods, which use patients' anatomical geometry to predict achievable dose volume histograms (DVHs), and developed the first IO method that takes DVHs as direct inputs. The DVH predictions from KBP are put into the IO pipeline to automati… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

1
69
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 66 publications
(70 citation statements)
references
References 20 publications
1
69
0
Order By: Relevance
“…For instance, Babier et al found for a PCA-based KB model, that for 50% of the cases, the difference between the predicted and clinically achieved D mean of the parotid glands was within roughly AE5 Gy. 13 In general, more consistency will lead to smaller prediction errors and vice versa, regardless of the KB prediction model, although the dependency may vary based on the type of KB model used. One way to increase consistency of a training dataset could be to update the dataset with treatment plans that were generated using KB planning or for which KB QA was applied.…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…For instance, Babier et al found for a PCA-based KB model, that for 50% of the cases, the difference between the predicted and clinically achieved D mean of the parotid glands was within roughly AE5 Gy. 13 In general, more consistency will lead to smaller prediction errors and vice versa, regardless of the KB prediction model, although the dependency may vary based on the type of KB model used. One way to increase consistency of a training dataset could be to update the dataset with treatment plans that were generated using KB planning or for which KB QA was applied.…”
Section: Discussionmentioning
confidence: 99%
“…Therefore, achieved OAR doses can be highly institution‐, planner‐ and patient dependent. Proposed solutions are knowledge‐based (KB) treatment plan QA or KB (semi‐)automated treatment planning . With KB treatment plan QA, treatment plans of prior patients are used to predict the achievable doses for a new patient.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…has applied a data‐driven KBP model to perform quality assurance of a commercially available automatic planning algorithm and demonstrated the potential of using KBP models to improve the performance of automatic planning algorithms. Another study by Babier et al . incorporated a KBP method into an automated planning method.…”
Section: Discussionmentioning
confidence: 99%
“…Interestingly, a recent study by Wang et al 80 has applied a data-driven KBP model to perform quality assurance of a commercially available automatic planning algorithm and demonstrated the potential of using KBP models to improve the performance of automatic planning algorithms. Another study by Babier et al 81 incorporated a KBP method into an automated planning method. We believe the combination of KBP models and automatic planning algorithms has a great potential to lead to further improvement of planning quality and efficiency in the future.…”
Section: Discussionmentioning
confidence: 99%