Comparison of Deep Learning-Based Auto-Segmentation Results on Daily Kilovoltage, Megavoltage, and Cone Beam CT Images in Image-Guided Radiotherapy
Technology in Cancer Research & Treatment · 2025
DOI: 10.1177/15330338251344198 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Technology in Cancer Research & Treatment, 2025. Verfasst von Zhixing Wang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, City of Hope, Duarte, CA, USA. Hauptthemen laut MEDLINE: Deep Learning, Cone-Beam Computed Tomography, Radiotherapy, Image-Guided, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: RefleXion Medical, Inc..
Abstract (Originalsprache)
Introduction
This study aims to evaluate auto-segmentation results using deep learning-based auto-segmentation models on different online CT imaging modalities in image-guided radiotherapy.
Methods
Phantom studies were first performed to benchmark image quality. Daily CT images for sixty patients were retrospectively retrieved from fan-beam kilovoltage CT (kVCT), kV cone-beam CT (kV-CBCT), and megavoltage CT (MVCT) scans. For each imaging modality, half of the patients received CT scans in the pelvic region, while the other half in the thoracic region. Deep learning auto-segmentation models using a convolutional neural network algorithm were used to generate organs-at-risk contours. Quantitative metrics were calculated to compare auto-segmentation results with manual contours.
Results
The auto-segmentation contours on kVCT images showed statistically significant difference in Dice similarity coefficient (DSC), Jaccard similarity coefficient, sensitivity index, inclusiveness index, and the 95 th percentile Hausdorff distance, compared to those on kV-CBCT and MVCT images for most major organs. In the pelvic region, the largest difference in DSC was observed for the bowel volume with an average DSC of 0.84 ± 0.05, 0.35 ± 0.23, and 0.48 ± 0.27 for kVCT, kV-CBCT, and MVCT images, respectively ( p -value < 0.05); in the thoracic region, the largest difference in DSC was found for the esophagus with an average DSC of 0.63 ± 0.16, 0.18 ± 0.13, and 0.22 ± 0.08 for kVCT, kV-CBCT, and MVCT images, respectively ( p -value < 0.05).
Conclusion
Deep learning-based auto-segmentation models showed better agreement with manual contouring when using kVCT images compared to kV-CBCT or MVCT images. However, manual correction remains necessary after auto-segmentation with all imaging modalities, particularly for organs with limited contrast from surrounding tissues. These findings underscore the potential and limits in applying deep learning-based auto-segmentation models for adaptive radiotherapy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiation Oncology, City of Hope, Duarte, CA, USA.
- RefleXion Medical, Hayward, CA, USA.
ORCID-Profile: Bo Liu, An Liu, Chunhui Han
Förderung
- RefleXion Medical, Inc.
Zitieren
APA
Wang, Z., Shi, C., Wong, C., Oderinde, S. M., Watkins, W. T., Qing, K., Liu, B., Williams, T. M., Liu, A., & Han, C. (2025). Comparison of Deep Learning-Based Auto-Segmentation Results on Daily Kilovoltage, Megavoltage, and Cone Beam CT Images in Image-Guided Radiotherapy. Technology in Cancer Research & Treatment. https://doi.org/10.1177/15330338251344198
Vancouver
Wang Z, Shi C, Wong C, Oderinde SM, Watkins WT, Qing K, et al. Comparison of Deep Learning-Based Auto-Segmentation Results on Daily Kilovoltage, Megavoltage, and Cone Beam CT Images in Image-Guided Radiotherapy. Technology in Cancer Research & Treatment. 2025. doi:10.1177/15330338251344198
BibTeX
@article{Wang2025,
author = {Wang, Zhixing and Shi, Chengyu and Wong, Carson and Oderinde, Seyi M and Watkins, William T and Qing, Kun and Liu, Bo and Williams, Terence M and Liu, An and Han, Chunhui},
title = {Comparison of Deep Learning-Based Auto-Segmentation Results on Daily Kilovoltage, Megavoltage, and Cone Beam CT Images in Image-Guided Radiotherapy},
journal = {Technology in Cancer Research & Treatment},
year = {2025},
doi = {10.1177/15330338251344198}
}
EUVIMED