Establishing prospective performance monitoring for real-world implementation of deep learning-based auto-segmentation in prostate cancer radiotherapy.

ABSTRACT:

Background and purpose

Deep-learning auto-segmentation (DLAS) performance in radiotherapy may change over time due to data shift/drift or practice changes, yet guidance for quality assurance is lacking. This study developed a practical framework for prospective performance monitoring using retrospective data.

Methods

A total of 464 prostate cases over 20 months were retrospectively collected. Two commercial DLAS models were clinically used: model A (2D U-Net, January 2022-January 2023) and model B (3D U-Net, February-August 2023). The agreement between DLAS and clinical contours was assessed using Dice Similarity Coefficient (DSC), 95th percentile Hausdorff Distance (HD95), and Surface DSC with a 2 mm tolerance (SDSC). Statistical process control charts were created to monit

SUBMITTER: Zhu L 

PROVIDER: S-EPMC12756037 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature