Contour subregion error detection methodology using deep learning auto‐segmentation
Medical Physics · 2023
DOI: 10.1002/mp.16768 ↗At a glance
Journal article in Medical Physics, 2023. Written by Jingwei Duan and 6 co-authors. Institution: Department of Radiation Medicine, University of Kentucky, Lexington, Kentucky, USA. Major MEDLINE topics: Deep Learning, Head and Neck Neoplasms. Cited 6 times so far (Crossref); 36 references. Funded by: NCI NIH HHS, Varian Medical Systems.
Abstract (original language)
Background
Inaccurate manual organ delineation is one of the high‐risk failure modes in radiation treatment. Numerous automated contour quality assurance (QA) systems have been developed to assess contour acceptability; however, manual inspection of flagged cases is a time‐consuming and challenging process, and can lead to users overlooking the exact error location.
Purpose
Our aim is to develop and validate a contour QA system that can effectively detect and visualize subregional contour errors, both qualitatively and quantitatively. Methods/Materials A novel contour subregion error detection (CSED) system was developed using subregional surface distance discrepancies between manual and deep learning auto‐segmentation (DLAS) contours. A validation study was conducted using a head and neck public dataset containing 339 cases and evaluated according to knowledge‐based pass criteria derived from a clinical training dataset of 60 cases. A blind qualitative evaluation was conducted, comparing the results from the CSED system with manual labels. Subsequently, the CSED‐flagged cases were re‐examined by a radiation oncologist.
Results
The CSED system could visualize the diverse types of subregional contour errors qualitatively and quantitatively. In the validation dataset, the CSED system resulted in true positive rates (TPR) of 0.814, 0.800, and 0.771; false positive rates (FPR) of 0.310, 0.267, and 0.298; and accuracies of 0.735, 0.759, and 0.730, for brainstem and left and right parotid contours, respectively. The CSED‐assisted manual review caught 13 brainstem, 19 left parotid, and 21 right parotid contour errors missed by conventional human review. The TPR/FPR/accuracy of the CSED‐assisted manual review improved to 0.836/0.253/0.784, 0.831/0.171/0.830, and 0.808/0.193/0.807 for each structure, respectively. Further, the time savings achieved through CSED‐assisted review improved by 75%, with the time for review taking 24.81 ± 12.84, 26.75 ± 10.41, and 28.71 ± 13.72 s for each structure, respectively.
Conclusions
The CSED system enables qualitative and quantitative detection, localization, and visualization of manual segmentation subregional errors utilizing DLAS contours as references. The use of this system has been shown to help reduce the risk of high‐risk failure modes resulting from inaccurate organ segmentation.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Radiation Medicine, University of Kentucky, Lexington, Kentucky, USA.
- Department of Radiation Oncology, Mayo Clinic, Phoenix, Arizona, USA.
- Carina Medical LLC, Lexington, Kentucky, USA.
- Department of Radiation Oncology, City of Hope Comprehensive Cancer Center, Duarte, California, USA.
Funding
- NCI NIH HHS
- Varian Medical Systems
Cite
APA
Duan, J., Bernard, M. E., Rong, Y., Castle, J. R., Feng, X., Johnson, J. D., & Chen, Q. (2023). Contour subregion error detection methodology using deep learning auto‐segmentation. Medical Physics. https://doi.org/10.1002/mp.16768
Vancouver
Duan J, Bernard ME, Rong Y, Castle JR, Feng X, Johnson JD, et al. Contour subregion error detection methodology using deep learning auto‐segmentation. Medical Physics. 2023. doi:10.1002/mp.16768
BibTeX
@article{Duan2023,
author = {Duan, Jingwei and Bernard, Mark E and Rong, Yi and Castle, James R and Feng, Xue and Johnson, Jeremiah D and Chen, Quan},
title = {Contour subregion error detection methodology using deep learning auto‐segmentation},
journal = {Medical Physics},
year = {2023},
doi = {10.1002/mp.16768}
}
EUVIMED