2021
DOI: 10.21873/anticanres.14774
|View full text |Cite
|
Sign up to set email alerts
|

Simultaneous Truth and Performance Level Estimation Method for Evaluation of Target Contouring in Radiosurgery

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 17 publications
0
2
0
Order By: Relevance
“…Dice Similarity Coefficient (DSC), 15 Hausdorff distance (HDD), 16 mean distance to agreement (mDTA), volume comparisons, and visual inspections were the metrics employed to evaluate C Auto . Provided that only three potential reference contours were generated per OAR, and the accuracy of consensus‐driven methods to merge contours, such as STAPLE, is highly dependent on the number of structures included, 17 any of the human delineated OAR(s) scored as clinically usable was used as the ground truth for the comparisons. It should be noted that while only the OARs in C Auto not scored as perfect were rectified, the metrics indicated above were performed on all of them.…”
Section: Methodsmentioning
confidence: 99%
“…Dice Similarity Coefficient (DSC), 15 Hausdorff distance (HDD), 16 mean distance to agreement (mDTA), volume comparisons, and visual inspections were the metrics employed to evaluate C Auto . Provided that only three potential reference contours were generated per OAR, and the accuracy of consensus‐driven methods to merge contours, such as STAPLE, is highly dependent on the number of structures included, 17 any of the human delineated OAR(s) scored as clinically usable was used as the ground truth for the comparisons. It should be noted that while only the OARs in C Auto not scored as perfect were rectified, the metrics indicated above were performed on all of them.…”
Section: Methodsmentioning
confidence: 99%
“…The STAPLE algorithm has been evaluated in a human paper that found it to be a valuable estimation tool with increasing robustness with increasing input contours. The study eval-uated numbers of contours up to 12 28 and the algorithm has been relied on in a number of human studies for establishment of consensus guidelines. [29][30][31][32][33] The dose protocol and organ-at-risk metrics used for this study reflect what is used at this institution, and other protocols and metrics are used elsewhere.…”
Section: Ctmentioning
confidence: 99%