PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 14, 2026Journal of Applied Clinical Medical Physics0 citationsOpen Access

Automatic target volume segmentation for offline adaptive head–and‐neck radiotherapy

View Full Paper
GMGilles MolinerMMMaxime MichaudAGAntoine Guerin

Key Points

  • To assess the utility of Smartfuse for automatic target volume propagation in head-and-neck radiotherapy.
  • Ten patients underwent offline re-planning during head-and-neck radiotherapy
  • Target volumes were delineated by radiation oncologists and compared to Smartfuse-propagated volumes
  • Geometric agreement and dosimetric evaluation were conducted to assess accuracy
  • Median DSC was 0.86 and HD 95 was 4.0 mm
  • All GTV RO + CTV RO reached V95% ≥ 95% with DIR plans
  • Spatial DD analysis showed median pass rates of 99.2% (DD 5%) for GTV RO + CTV RO

Abstract

Abstract Purpose To assess the clinical utility of Smartfuse (Therapanacea, France), a deformable image registration (DIR) algorithm for automatic propagation of target volumes in the context of offline adaptive head‐and‐neck radiotherapy. Materials and methods Ten patients underwent offline re‐planning during head‐and‐neck radiotherapy. Target volumes (GTV and CTV) were manually delineated by radiation oncologists (ROs) on both the initial CT (CT i ) and one re‐planning CT (CT R ). These manual contours were compared to those propagated by Smartfuse from CT i to CT R . The geometric agreement between DIR‐propagated and RO‐delineated contours was assessed using Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD 95 ), and surface Dice similarity coefficient (sDSC) with 0 and 2 mm thresholds. Dosimetric evaluation was conducted by comparing dose distributions from generated plans using automatically propagated target volumes (PTV DIR ) with reference plans based on RO‐delineated targets (PTV RO ). Coverage of RO‐delineated targets (GTV RO + CTV RO and PTV RO ) was assessed using D95%, D50%, Dmax, and V95% ≥ 95%. Spatial dose differences were analyzed using dose difference (DD) metrics at 5% and 2% thresholds. Results Median DSC, HD 95 , sDSC 0 mm and sDSC 2 mm were 0.86, 4.0 mm, 0.29 and 0.73, respectively. For D 95% , median relative differences between DIR and RO plans were −0.6% for GTV RO + CTV RO and −2.1% for PTV RO for D 95% . All GTV RO + CTV RO reached V95% ≥ 95% with DIR plans, but only 61% of PTV RO did. Spatial DD analysis showed median pass rates of 99.2% (DD 5% ) and 74.5% (DD 2% ) for GTV RO + CTV RO , and 85.5% (DD 5% ) and 54.9% (DD 2% ) for PTV RO . Conclusion Smartfuse may facilitate efficient propagation of target volumes in this study. However, medical review of auto‐propagated volumes remains essential, as dosimetric discrepancies may arise when relying solely on automatically generated PTV.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Moliner et al. (2026) studied this question.

synapsesocial.com/papers/69b4ba0818185d8a39802858https://doi.org/10.1002/acm2.70479
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Nonrigid registration using free-form deformations: application to breast MR images1999 · 5,313 citations
  2. 2Free-form deformation of solid geometric models1986 · 2,590 citations
  3. 3Fast, Approximately Optimal Solutions for Single and Dynamic MRFs2007 · 183 citations
  4. 4A Blinded Prospective Evaluation Of Clinical Applicability Of Deep Learning-Based Auto Contouring Of OAR For Head and Neck Radiotherapy2020 · 6 citations
  5. 5Biomedical Data Annotation: An OCT Imaging Case Study2023 · 5 citations