2021
DOI: 10.1016/j.ijrobp.2020.11.011
|View full text |Cite
|
Sign up to set email alerts
|

Using Auto-Segmentation to Reduce Contouring and Dose Inconsistency in Clinical Trials: The Simulated Impact on RTOG 0617

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

2
35
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
9
1

Relationship

2
8

Authors

Journals

citations
Cited by 42 publications
(38 citation statements)
references
References 19 publications
2
35
0
Order By: Relevance
“…In addition, in clinical trials including radiotherapy, standardization of treatment is problematic because of the variability in delineating the target and OARs [ 18 ]. In the RTOG 0617 trial [ 19 ], a radiation dose-escalation trial of non-small cell lung cancer, an analysis using deep-learning segmented hearts revealed that the actual heart doses were higher than originally reported owing to inconsistent and insufficient manual heart segmentation. Our results demonstrated that the ACS could solve this issue.…”
Section: Discussionmentioning
confidence: 99%
“…In addition, in clinical trials including radiotherapy, standardization of treatment is problematic because of the variability in delineating the target and OARs [ 18 ]. In the RTOG 0617 trial [ 19 ], a radiation dose-escalation trial of non-small cell lung cancer, an analysis using deep-learning segmented hearts revealed that the actual heart doses were higher than originally reported owing to inconsistent and insufficient manual heart segmentation. Our results demonstrated that the ACS could solve this issue.…”
Section: Discussionmentioning
confidence: 99%
“…One of the advantages of using an automatic contouring model is that intra-and inter-observer variability is eliminated. This is a major benefit when compared to choosing a group of experts to contour a dataset because systematic contour differences between experts might be reflected in systematic differences in the dosimetric parameters and all other computations made using those contours [31]. Moreover, these algorithms can be easily deployed in any given institute, avoiding the time and monetary costs of manual contouring following the same atlas and contouring directions.…”
Section: Discussionmentioning
confidence: 99%
“…Automation not only leads to efficiency gains but also, generally, leads to more standardized/ontological data collection, which in turn may lead to better prognostication and prediction. As an example, a recent paper using AI-based automated heart segmentation led to a better prediction of dose-related cardiac toxicity in a pivotal trial on advanced lung cancer patients (RTOG 0617) compared to human heart segmentations, likely due to interobserver variation [ 24 ].…”
Section: Unmet Clinical Needs In the Management Of La-nsclc Patients: Role Of Imaging Adaptive Rt And Biomarkersmentioning
confidence: 99%