Cross‐fraction prior learning for scalable organ‐at‐risk segmentation in abdominal MR‐guided radiotherapy
Medical Physics · 2026
DOI: 10.1002/mp.70648 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2026. Verfasst von Chengyin Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Henry Ford Health, Detroit, Michigan, USA. Hauptthemen laut MEDLINE: Organs at Risk, Magnetic Resonance Imaging, Radiotherapy, Image-Guided, Image Processing, Computer-Assisted. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Manual organ‐at‐risk (OAR) delineation takes 20–40 min per case, a major bottleneck within the 50–90 min treatment window of abdominal MR‐guided adaptive radiotherapy (MRgRT). Most deep learning systems adopt single‐fraction approaches that discard valuable temporal context from prior treatment fractions.
Purpose
This study develops AdaptSeg, a scalable framework leveraging cross‐fraction anatomical priors to substantially improve OAR segmentation without per‐patient retraining.
Methods
We implemented a dual‐path neural architecture conditioning current fraction segmentation on paired image‐mask information from supporting fractions. AdaptSeg was instantiated with convolutional (3D UNet) and transformer‐based (SwinUNETR) backbones. Evaluation used 104 pancreatic cancer patients across 520 treatment fractions for four abdominal organs (colon, duodenum, small bowel, stomach), with patient‐level splitting: 72 training, 10 validation, 22 test patients. Performance metrics included Dice Similarity Coefficient (DSC), 95th percentile Hausdorff Distance (HD95), and Average Symmetric Surface Distance (ASSD); paired comparisons used two‐sided Wilcoxon signed‐rank tests with Benjamini–Hochberg correction, and 95% bootstrap confidence intervals for the means.
Results
Cross‐fraction priors improved segmentation performance for both tested backbones. The 3D UNet achieved 87.22% mean DSC versus 83.78% baseline, while SwinUNETR reached 85.19% versus 82.49% baseline. For highly deformable organs, improvements included up to 7.0 percentage point DSC gains (small bowel: 77.8% to 84.8%, ) and 62% boundary error reduction (colon HD95: 23.13 to 8.74 mm, ). Compared to nine state‐of‐the‐art methods, AdaptSeg achieved the best overall performance with substantial improvements in mean DSC (4.1%), HD95 (43%), and ASSD (39%) over the strongest baseline. All variants maintained computationally feasible inference under 1.6 s per case. Temporal prior selection showed a backbone‐dependent preference: the CNN favored sequential priors, and the transformer additionally benefited from randomized support sampling during training (sequential support is used at inference).
Conclusions
Cross‐fraction anatomical priors improved OAR segmentation for both tested backbone families, indicating that temporal context is an underutilized resource in fractionated radiotherapy. AdaptSeg provides a scalable, computationally feasible framework for accelerating MRgRT workflows without per‐patient adaptation, with sub‐1.6 s inference compatible with the time constraints of online adaptive treatment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiation Oncology, Henry Ford Health, Detroit, Michigan, USA.
- Department of Computer Science, Wayne State University, Detroit, Michigan, USA.
- Department of Radiology, Michigan State University, East Lansing, Michigan, USA.
- College of Osteopathic Medicine, Michigan State University, East Lansing, Michigan, USA.
- Department of Physics, Oakland University, Rochester, Michigan, USA.
- Department of Medicine, Michigan State University, East Lansing, Michigan, USA.
Zitieren
APA
Li, C., Rusu, D., Sultan, R., Bagher-Ebadian, H., Doemer, A., Zhu, D., Parikh, P. J., & Thind, K. (2026). Cross‐fraction prior learning for scalable organ‐at‐risk segmentation in abdominal MR‐guided radiotherapy. Medical Physics. https://doi.org/10.1002/mp.70648
Vancouver
Li C, Rusu D, Sultan R, Bagher-Ebadian H, Doemer A, Zhu D, et al. Cross‐fraction prior learning for scalable organ‐at‐risk segmentation in abdominal MR‐guided radiotherapy. Medical Physics. 2026. doi:10.1002/mp.70648
BibTeX
@article{Li2026,
author = {Li, Chengyin and Rusu, Doris and Sultan, Rafi Ibn and Bagher-Ebadian, Hassan and Doemer, Anthony and Zhu, Dongxiao and Parikh, Parag J and Thind, Kundan},
title = {Cross‐fraction prior learning for scalable organ‐at‐risk segmentation in abdominal MR‐guided radiotherapy},
journal = {Medical Physics},
year = {2026},
doi = {10.1002/mp.70648}
}
EUVIMED