EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning

J John Lucido, Todd A DeWees, Todd R Leavitt, Aman Anand, Chris J Beltran, Mark D Brooke, Justine R Buroker, Robert L Foote, Olivia R Foss, Angela M Gleason, Teresa L Hodge, Cían O Hughes und 12 weitere

Frontiers in Oncology · 06.04.2023 · 13

DOI: 10.3389/fonc.2023.1137803 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 06.04.2023. Verfasst von J John Lucido und 23 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Mayo Clinic, Rochester, MN, United States. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Organ-at-risk segmentation for head and neck cancer radiation therapy is a complex and time-consuming process (requiring up to 42 individual structure, and may delay start of treatment or even limit access to function-preserving care. Feasibility of using a deep learning (DL) based autosegmentation model to reduce contouring time without compromising contour accuracy is assessed through a blinded randomized trial of radiation oncologists (ROs) using retrospective, de-identified patient data.

Methods

Two head and neck expert ROs used dedicated time to create gold standard (GS) contours on computed tomography (CT) images. 445 CTs were used to train a custom 3D U-Net DL model covering 42 organs-at-risk, with an additional 20 CTs were held out for the randomized trial. For each held-out patient dataset, one of the eight participant ROs was randomly allocated to review and revise the contours produced by the DL model, while another reviewed contours produced by a medical dosimetry assistant (MDA), both blinded to their origin. Time required for MDAs and ROs to contour was recorded, and the unrevised DL contours, as well as the RO-revised contours by the MDAs and DL model were compared to the GS for that patient.

Results

Mean time for initial MDA contouring was 2.3 hours (range 1.6-3.8 hours) and RO-revision took 1.1 hours (range, 0.4-4.4 hours), compared to 0.7 hours (range 0.1-2.0 hours) for the RO-revisions to DL contours. Total time reduced by 76% (95%-Confidence Interval: 65%-88%) and RO-revision time reduced by 35% (95%-CI,-39%-91%). All geometric and dosimetric metrics computed, agreement with GS was equivalent or significantly greater (p<0.05) for RO-revised DL contours compared to the RO-revised MDA contours, including volumetric Dice similarity coefficient (VDSC), surface DSC, added path length, and the 95%-Hausdorff distance. 32 OARs (76%) had mean VDSC greater than 0.8 for the RO-revised DL contours, compared to 20 (48%) for RO-revised MDA contours, and 34 (81%) for the unrevised DL OARs.

Conclusion

DL autosegmentation demonstrated significant time-savings for organ-at-risk contouring while improving agreement with the institutional GS, indicating comparable accuracy of DL model. Integration into the clinical practice with a prospective evaluation is currently underway.

Schlagwörter

Stichwörter der Autor:innen

autosegmentationclinical validationcomprehensivedeep learninghead and neck cancerorgans-at-riskradiation therapy

Autor:innen und Institutionen

  • Department of Radiation Oncology, Mayo Clinic, Rochester, MN, United States.
  • Department of Health Sciences Research, Mayo Clinic, Phoenix, AZ, United States.
  • Department of Radiation Oncology, Mayo Clinic, Phoenix, AZ, United States.
  • Department of Radiation Oncology, Mayo Clinic, Jacksonville, FL, United States.
  • Google Health, Mountain View, CA, United States.
  • Research Services, Comprehensive Cancer Center, Mayo Clinic, Rochester, MN, United States.

Zitieren

APA

Lucido, J. J., DeWees, T. A., Leavitt, T. R., Anand, A., Beltran, C. J., Brooke, M. D., Buroker, J. R., Foote, R. L., Foss, O. R., Gleason, A. M., Hodge, T. L., Hughes, C. O., Hunzeker, A. E., Laack, N. N., Lenz, T. K., Livne, M., Morigami, M., Moseley, D. J., Undahl, L. M., …, & Patel, S. H. (2023). Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning. Frontiers in Oncology, 13. https://doi.org/10.3389/fonc.2023.1137803

Vancouver

Lucido JJ, DeWees TA, Leavitt TR, Anand A, Beltran CJ, Brooke MD, et al. Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning. Frontiers in Oncology. 2023;13. doi:10.3389/fonc.2023.1137803

BibTeX
@article{Lucido2023,
  author = {Lucido, J John and DeWees, Todd A and Leavitt, Todd R and Anand, Aman and Beltran, Chris J and Brooke, Mark D and Buroker, Justine R and Foote, Robert L and Foss, Olivia R and Gleason, Angela M and Hodge, Teresa L and Hughes, Cían O and Hunzeker, Ashley E and Laack, Nadia N and Lenz, Tamra K and Livne, Michelle and Morigami, Megumi and Moseley, Douglas J and Undahl, Lisa M and Patel, Yojan and Tryggestad, Erik J and Walker, Megan Z and Zverovitch, Alexei and Patel, Samir H},
  title = {Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning},
  journal = {Frontiers in Oncology},
  year = {2023},
  volume = {13},
  doi = {10.3389/fonc.2023.1137803}
}
Kostenlos starten →