2021
DOI: 10.1016/s0167-8140(21)08124-x
|View full text |Cite
|
Sign up to set email alerts
|

PO-1673 Improving data collection for deep-learning auto-segmentation models

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 0 publications
0
1
0
Order By: Relevance
“…In other words, institutions without access to established experts may still be able to produce high-quality data for algorithmic development. Notably, recent literature suggests that DL models trained on consensus contours can be influenced by biased annotations, 11 underscoring the importance of judicious application of these consensus methods.
Figure 2 Consensus from a limited number of nonexpert contours can approximate expert reference standard benchmarks.
…”
Section: Insight 1: DL Auto-contouring Algorithms Require High-qualit...mentioning
confidence: 99%
“…In other words, institutions without access to established experts may still be able to produce high-quality data for algorithmic development. Notably, recent literature suggests that DL models trained on consensus contours can be influenced by biased annotations, 11 underscoring the importance of judicious application of these consensus methods.
Figure 2 Consensus from a limited number of nonexpert contours can approximate expert reference standard benchmarks.
…”
Section: Insight 1: DL Auto-contouring Algorithms Require High-qualit...mentioning
confidence: 99%