Buchumschlag

Evaluation of compartmentalized automatic segmentation for definition of the GTV in glioblastoma radiotherapy

Background and purpose - Manual delineation of target volumes in glioblastoma (GBM) radiotherapy (RT) is time-consuming and variable. This study evaluates the clinical applicability of a preliminary deep learning model (Neosoma Glioma) for automating gross tumor volume (GTV) segmentation in postoper...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Poel, Robert (VerfasserIn) , Mose, Lucas (VerfasserIn) , Reinhardt, Philipp (VerfasserIn) , Müller, Michael (VerfasserIn) , Meuller, Silvan (VerfasserIn) , Reyes, Mauricio (VerfasserIn) , Brueningk, Sarah (VerfasserIn) , Manser, Peter (VerfasserIn) , Aebersold, Daniel M. (VerfasserIn) , Ermiş, Ekin (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: January 2026
In: Radiotherapy and oncology
Year: 2026, Jahrgang: 214, Pages: 1-8
ISSN:1879-0887
DOI:10.1016/j.radonc.2025.111308
Online-Zugang:Verlag, kostenfrei, Volltext: https://doi.org/10.1016/j.radonc.2025.111308
Verlag, kostenfrei, Volltext: https://www.sciencedirect.com/science/article/pii/S0167814025053125
Volltext
Verfasserangaben:Robert Poel, Lucas Mose, Philipp Reinhardt, Michael Müller, Silvan Meuller, Mauricio Reyes, Sarah Brueningk, Peter Manser, Daniel M. Aebersold, Ekin Ermiş
Beschreibung
Zusammenfassung:Background and purpose - Manual delineation of target volumes in glioblastoma (GBM) radiotherapy (RT) is time-consuming and variable. This study evaluates the clinical applicability of a preliminary deep learning model (Neosoma Glioma) for automating gross tumor volume (GTV) segmentation in postoperative GBM per ESTRO-EANO guidelines. - Materials and methods - We retrospectively analyzed 100 GBM cases treated at Inselspital University Hospital, Bern (2016-2020) with standardized multi-modal MRI. Auto-segmented GTVs were compared to expert-defined contours using geometric metrics. Radiation oncologists reviewed and adjusted the best-performing configuration. Time savings, geometric similarity, and dosimetric impact were assessed. - Results - Optimal auto-segmentation (resection cavity plus enhancing tumor with 1 mm margin) achieved a mean Dice similarity coefficient of 0.79 (SD = 0.14) vs. ground truth. Manual adjustment took 5.9 (SD = 4.6) minutes vs. 12.3 (SD = 6.8) minutes for manual contouring (>50 % time reduction). The mean Dice between auto-segmented and adjusted GTVs was 0.84 (SD = 0.18). Dosimetric evaluation showed plans from adjusted auto-segmentations were equivalent to those based on consensus contours, with no clinically relevant differences in target coverage or organ-at-risk sparing. - Conclusion - The Neosoma Glioma model generates clinically useful postoperative GTV segmentations, with geometric performance comparable to expert variability and dosimetric equivalence to consensus contours. It reduces contouring time by over 50%, enabling faster RT workflows. Its consistency across diverse GBM presentations supports its practical value. AI-based segmentation can help standardize GBM target definition when integrated into RT planning with proper quality assurance.
Beschreibung:Online verfügbar: 25. November 2025, Artikelversion: 27. November 2025
Gesehen am 25.02.2026
Beschreibung:Online Resource
ISSN:1879-0887
DOI:10.1016/j.radonc.2025.111308

Ähnliche Einträge