Improving deep learning organ segmentation accuracy in cone-beam CT-guided radiotherapy using a robust scatter suppression method
In brief
Scatter-suppressed CBCT lifts segmentation scores from 0.61-0.63 to 0.66
In 26 patients, a scatter-suppression method improved deep-learning segmentation overall on cone-beam CT, raising the average Dice score from 0.61-0.63 to 0.66. Gains were strongest for pelvic organs, including the bladder and rectum, while head-and-neck segmentation did not improve; whether these accuracy gains translate into better radiotherapy decisions remains unknown.
- Journal
- Physics and imaging in radiation oncology (Q1)
- Published
- 12 September 2026
- Study design
- Cohort / observational study
- Evidence level
- Level 3, Low (CEBM 3b)
- Authors
- Rupesh Dotel, Farhang Bayat, Junxiao Hu, Uttam Pyakurel, Ryan Sabounchi, Roy Bliley, et al.
- PMID
- 42787476
- DOI
- 10.1016/j.phro.2026.101084
Why clinicians should know about it
- Picked for Medical Physics (paper of the day, 28 September 2026): Scatter‑suppressed CBCT boosts deep‑learning organ segmentation
Abstract
BACKGROUND AND PURPOSE: Deep learning-based segmentation of organs and tumors in cone-beam computed tomography (CBCT) is critical for improving workflow efficiency and accuracy in dose delivery monitoring and adaptive radiotherapy. However, degraded CBCT image quality, primarily due to scatter, can adversely affect segmentation performance. This study evaluated whether improving CBCT image quality through enhanced scatter mitigation improves deep learning (DL) segmentation accuracy. MATERIALS AND METHODS: A quantitative CBCT method incorporating a novel antiscatter grid and dedicated reconstruction pipeline was evaluated in a prospective study of 26 patients with cancers in the prostate, head and neck (H&N), and pelvis/abdomen regions. Each patient underwent both standard-of-care CBCT and quantitative CBCT scans. A foundation model, agnostic to CBCT images, was used to segment 13 organs and targets across CBCT and planning computed tomography (CT) images. DL segmentation accuracy was evaluated using Dice similarity coefficient and maximum Hausdorff distance with respect to clinician-drawn contours. RESULTS: Mean Dice coefficients were higher for quantitative CBCT (0.66) compared to standard-of-care CBCT (0.61-0.63, p < 0.05). For the prostate, bladder, and rectum, Dice coefficients improved from 0.68 to 0.81 to 0.80-0.86, with significant gains for the bladder and rectum (p < 0.05). Hausdorff distances were lower for quantitative CBCT in the prostate and pelvis/abdomen regions, indicating improved boundary agreement. In the H&N region, quantitative CBCT did not improve segmentation accuracy. CONCLUSIONS: Improved quantitative accuracy in CBCT through robust scatter suppression enhances deep learning-based segmentation, particularly for large organs, supporting its role in improving adaptive radiotherapy workflows.
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.