Personalized deep learning auto‐segmentation models for adaptive fractionated magnetic resonance‐guided radiation therapy of the abdomen

Kawula, Maria ; Marschner, Sebastian ; Wei, Chengtao; Ribeiro, Marvin F.; Corradini, Stefanie ; Belka, Claus ; Landry, Guillaume und Kurz, Christopher (2025): Personalized deep learning auto‐segmentation models for adaptive fractionated magnetic resonance‐guided radiation therapy of the abdomen. In: Medical Physics, Bd. 52, Nr. 4: S. 2295-2304

Abstract

Background: Manual contour corrections during fractionated magnetic resonance (MR)-guided radiotherapy (MRgRT) are time-consuming. Conventional population models for deep learning auto-segmentation might be suboptimal for MRgRT at MR-Linacs since they do not incorporate manual segmentation from treatment planning and previous fractions.

Purpose: In this work, we investigate patient-specific (PS) auto-segmentation methods leveraging expert-segmented planning and prior fraction MR images (MRIs) to improve auto-segmentation on consecutive treatment days.

Conclusion: Personalized auto-segmentation models outperformed the population BMs. In most cases, PS(BM) delineations were judged to be directly usable for treatment adaptation without further corrections, suggesting a potential time saving during fractionated treatment.

• Dokumententyp: Zeitschriftenartikel
• Fakultät: Medizin > Klinikum der LMU München > Klinik und Poliklinik für Strahlentherapie und Radioonkologie
• Themengebiete: 600 Technik, Medizin, angewandte Wissenschaften > 610 Medizin und Gesundheit
• ISSN: 0094-2405
• Sprache: Englisch