Large-scale dose evaluation of deep learning organ contours in head-and-neck radiotherapy by leveraging existing plans

Prerak Mody; Merle Huiskes; Nicolas F Chaves-de-Plaza; Alice Onderwater; Rense Lamsma; Klaus Hildebrandt; Nienke Hoekstra; Eleftheria Astreinidou; Marius Staring; Frank Dankers

doi:10.1016/j.phro.2024.100572

Large-scale dose evaluation of deep learning organ contours in head-and-neck radiotherapy by leveraging existing plans

Phys Imaging Radiat Oncol. 2024 Mar 28:30:100572. doi: 10.1016/j.phro.2024.100572. eCollection 2024 Apr.

Authors

Affiliations

¹ Division of Image Processing (LKEB), Department of Radiology, Leiden University Medical Center, Leiden 2333 ZA, The Netherlands.
² HollandPTC consortium - Erasmus Medical Center, Rotterdam, Holland Proton Therapy Centre, Delft, Leiden University Medical Center (LUMC), Leiden and Delft University of Technology, Delft, The Netherlands.
³ Department of Radiation Oncology, Leiden University Medical Center, Leiden 2333 ZA, The Netherlands.
⁴ Computer Graphics and Visualization Group, EEMCS, TU Delft, Delft 2628 CD, The Netherlands.

Abstract

Background and purpose: Retrospective dose evaluation for organ-at-risk auto-contours has previously used small cohorts due to additional manual effort required for treatment planning on auto-contours. We aimed to do this at large scale, by a) proposing and assessing an automated plan optimization workflow that used existing clinical plan parameters and b) using it for head-and-neck auto-contour dose evaluation.

Materials and methods: Our automated workflow emulated our clinic's treatment planning protocol and reused existing clinical plan optimization parameters. This workflow recreated the original clinical plan ( $P_{OG}$ ) with manual contours ( $P_{MC}$ ) and evaluated the dose effect ( $P_{OG} - P_{MC}$ ) on 70 photon and 30 proton plans of head-and-neck patients. As a use-case, the same workflow (and parameters) created a plan using auto-contours ( $P_{AC}$ ) of eight head-and-neck organs-at-risk from a commercial tool and evaluated their dose effect ( $P_{MC} - P_{AC}$ ).

Results: For plan recreation ( $P_{OG} - P_{MC}$ ), our workflow had a median impact of 1.0% and 1.5% across dose metrics of auto-contours, for photon and proton respectively. Computer time of automated planning was 25% (photon) and 42% (proton) of manual planning time. For auto-contour evaluation ( $P_{MC} - P_{AC}$ ), we noticed an impact of 2.0% and 2.6% for photon and proton radiotherapy. All evaluations had a median $Δ$ NTCP (Normal Tissue Complication Probability) less than 0.3%.

Conclusions: The plan replication capability of our automated program provides a blueprint for other clinics to perform auto-contour dose evaluation with large patient cohorts. Finally, despite geometric differences, auto-contours had a minimal median dose impact, hence inspiring confidence in their utility and facilitating their clinical adoption.

Keywords: Auto contouring; Automated plan optimization; Automated plans; Dose impact; Robot process automation.