Open‐source deep‐learning models for segmentation of normal structures for prostatic and gynecological high‐dose‐rate brachytherapy: Comparison of architectures

TL;DR

This paper compares two deep learning models for automatically segmenting organs in high-dose-rate brachytherapy CT scans, showing both are accurate and useful for clinical planning.

Contribution

The study evaluates and implements open-source deep learning models for HDR brachytherapy segmentation using a large clinical dataset.

Findings

UNet++ and nnU-Net models achieved high Dice-Similarity-Coefficients for bladder and rectum segmentation.

No significant difference in performance was found between the two architectures.

Trained models outperformed clinical contours in a blinded evaluation.

Abstract

The use of deep learning‐based auto‐contouring algorithms in various treatment planning services is increasingly common. There is a notable deficit of commercially or publicly available models trained on large or diverse datasets containing high‐dose‐rate (HDR) brachytherapy treatment scans, leading to poor performance on images that include HDR implants.

To implement and evaluate automatic organs‐at‐risk (OARs) segmentation models for use in prostatic‐and‐gynecological computed tomography (CT)‐guided high‐dose‐rate brachytherapy treatment planning.

1316 computed tomography (CT) scans and corresponding segmentation files from 1105 prostatic‐or‐gynecological HDR patients treated at our institution from 2017 to 2024 were used for model training. Data sources comprised six CT scanners including a mobile CT unit with previously reported susceptibility to image streaking artifacts. Two UNet‐derived model architectures, UNet++ and nnU‐Net, were investigated for bladder and rectum model training. The models were tested on 100 CT scans and clinically‐used segmentation files from 62 prostatic‐or‐gynecological HDR brachytherapy patients, disjoint from the training set, collected in 2024. Performance was evaluated using the Dice‐Similarity‐Coefficient (DSC) between model predicted contours and clinically‐used contours on slices in common with the Clinical‐Target‐Volume (CTV). Additionally, a blinded evaluation of ten random test cases was conducted by three experienced planners.

Median (interquartile range) 3D DSC on CTV‐containing slices were 0.95 (0.04) and 0.87 (0.09) for the UNet++ bladder and rectum models, respectively, and 0.96 (0.03) and 0.88 (0.10) for the nnU‐Net. The rank‐sum test did not reveal statistically significant differences in these DSC (p = 0.15 and 0.27, respectively). The blinded evaluation scored trained models higher than clinically‐used contours.

Both UNet‐derived architectures perform similarly on the bladder and rectum and are adequately accurate to reduce contouring time in a review‐and‐edit context during HDR brachytherapy planning. The UNet++ models were chosen for implementation at our institution due to lower computing hardware requirements and are in routine clinical use.

Figures