Impact of patient-specific deep learning lung organs-at-risk segmentation on accumulated dose in online adaptive 0.35T MR-guided radiotherapy.
Authors
Affiliations (7)
Affiliations (7)
- Department of Radiation Oncology, University Hospital, LMU Munich, Marchioninistraße 15, Munich, 81377, GERMANY.
- Department of Radiation Oncology, LMU University Hospital, LMU Munich, Marchioninistr. 15, Munich, BY, 81377, GERMANY.
- Department of Radiation Oncology, LMU University Hospital, LMU Munich, Marchioninistraße 15, Munich, 81377, GERMANY.
- Department of Radiation Oncology, LMU University Hospital, LMU Munich, Marchioninistr. 15, LMU Munich, 81377, GERMANY.
- Department of Radiation Oncology, LMU University Hospital, LMU Munich, Marchioninistr. 15, Munchen, 81377, GERMANY.
- Department of Radiation Oncology, LMU University Hospital, LMU Munich, Marchioninistr. 15, Munich, 81377, GERMANY.
- Department of Radiation Oncology, LMU University Hospital, LMU Munich, Marchioninistr. 15, Munich, Bavaria, 81377, GERMANY.
Abstract
Objective
Online adaptation in magnetic resonance imaging-guided radiotherapy (MRgRT) for lung cancer is hindered by time-consuming organs-at-risk (OARs) recontouring on daily MR images (dMRIs) and inter-/intra-observer variability. Deep learning auto-segmentation (DLAS) of OARs offers an efficient alternative. While baseline models (BMs) provide general segmentation, patient-specific (PS) training using expert-delineated planning MR images (pMRI) can enhance accuracy. This study evaluated accumulated dose differences between BM and PS OAR models without manual modification in online plan adaptation.

Approach
Eleven lung cancer patients treated with a 0.35 T magnetic resonance linear accelerator were retrospectively analyzed. Pre-trained population-based 3D U-Nets (BM) for nine thoracic OARs served as initial models for PS fine-tuning on planning MRIs. BM- and PS-generated OAR contours per fraction were imported into an MRgRT treatment planning system, along with clinical expert target contours. Online adaptive doses were re-optimized using both models' OAR contours with the same clinical objective functions. Fraction doses were accumulated on the pMRI, and dose-volume histogram (DVH) parameters of PTV, GTV, and other OARs within PTV+3 cm were calculated using clinical contours on pMRI. A Wilcoxon signed-rank test was used to test for statistical differences (α= 0.05) compared to accumulated clinical doses.

Main results
PS models improved segmentation accuracy for all OARs compared to BM. They also mitigated substantial outliers in D<sup>BM</sup><sub>1cc</sub>versus D<sup>clinical</sup><sub>1cc</sub>and resulted in higher PTV D<sub>95%</sub>and GTV D<sub>98%</sub>than clinical plans. Overall, D<sup>BM</sup>met 48/61 OAR constraints, while D<sup>PS</sup>met 53. For PTVs, both D<sup>PS</sup>and D<sup>BM</sup>satisfied 21/25 constraints.

Significance
Unmodified BM and PS model contours yielded median accumulated doses comparable to clinically delivered doses. However, PS models demonstrated superior geometric alignment, improved OAR sparing, and enhanced target coverage compared to BM, potentially benefiting MRgRT lung cancer patients.
.