Automated applicator digitization for high-dose-rate cervix brachytherapy using image thresholding and density-based clustering

Christopher L. Deufel, Shulan Tian, Benjamin B. Yan, Birjoo D. Vaishnav, Michael G. Haddock, Ivy A. Petersen

Research output: Contribution to journalArticle

Abstract

Purpose: The purpose of the study was to develop and evaluate an automated digitization algorithm for high-dose-rate cervix brachytherapy, with the goal of reducing the duration of treatment planning, staff resources, variability, and potential for human error. Methods: An automated digitization algorithm was developed and retrospectively evaluated using treatment planning data from 10 patients with cervix cancer who were treated with a titanium tandem and ovoids applicator set. Applicators were segmented, without human interaction, by thresholding CT images to isolate high-density voxels and assigning the voxels to applicator and nonapplicator structures using HDBSCAN, a density-based linkage clustering algorithm. The applicator contours were determined from the centroid of the clustered voxels on each image slice and written to a treatment plan file. Automated contours were evaluated against manual digitization using distance and dosimetric metrics. Results: A close agreement between automatic and manual digitization was observed. The mean magnitude of contour disagreement for 10 patients equaled 0.3 mm. Hausdorff distances were ≤1.0 mm. The applicator tip coordinates had submillimeter agreement. The median and mean dose volume histogram parameter differences were less than or equal to 1% for high-risk clinical target volume D90, high-risk clinical target volume D95, bladder D2cc, rectum D2cc, large bowel D2cc, and small bowel D2cc. The average execution time for the automated algorithm was less than 30 s. Conclusion: The digitization of titanium tandem and ovoids applicators for high-dose-rate brachytherapy treatment planning can be automated using straightforward thresholding and clustering algorithms. The adoption of automated digitization is expected to improve the consistency of treatment plans and reduce the duration of treatment planning.

Original languageEnglish (US)
JournalBrachytherapy
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Brachytherapy
Cervix Uteri
Cluster Analysis
Titanium
Therapeutics
Rectum
Uterine Cervical Neoplasms
Urinary Bladder

Keywords

  • Automation
  • Brachytherapy
  • Cervix
  • Clustering
  • Digitization
  • HDR
  • Segmentation
  • Tandem and ovoids
  • Threshold

ASJC Scopus subject areas

  • Oncology
  • Radiology Nuclear Medicine and imaging

Cite this

Automated applicator digitization for high-dose-rate cervix brachytherapy using image thresholding and density-based clustering. / Deufel, Christopher L.; Tian, Shulan; Yan, Benjamin B.; Vaishnav, Birjoo D.; Haddock, Michael G.; Petersen, Ivy A.

In: Brachytherapy, 01.01.2019.

Research output: Contribution to journalArticle

@article{8608360f5b474c50a44c055becf10242,
title = "Automated applicator digitization for high-dose-rate cervix brachytherapy using image thresholding and density-based clustering",
abstract = "Purpose: The purpose of the study was to develop and evaluate an automated digitization algorithm for high-dose-rate cervix brachytherapy, with the goal of reducing the duration of treatment planning, staff resources, variability, and potential for human error. Methods: An automated digitization algorithm was developed and retrospectively evaluated using treatment planning data from 10 patients with cervix cancer who were treated with a titanium tandem and ovoids applicator set. Applicators were segmented, without human interaction, by thresholding CT images to isolate high-density voxels and assigning the voxels to applicator and nonapplicator structures using HDBSCAN, a density-based linkage clustering algorithm. The applicator contours were determined from the centroid of the clustered voxels on each image slice and written to a treatment plan file. Automated contours were evaluated against manual digitization using distance and dosimetric metrics. Results: A close agreement between automatic and manual digitization was observed. The mean magnitude of contour disagreement for 10 patients equaled 0.3 mm. Hausdorff distances were ≤1.0 mm. The applicator tip coordinates had submillimeter agreement. The median and mean dose volume histogram parameter differences were less than or equal to 1{\%} for high-risk clinical target volume D90, high-risk clinical target volume D95, bladder D2cc, rectum D2cc, large bowel D2cc, and small bowel D2cc. The average execution time for the automated algorithm was less than 30 s. Conclusion: The digitization of titanium tandem and ovoids applicators for high-dose-rate brachytherapy treatment planning can be automated using straightforward thresholding and clustering algorithms. The adoption of automated digitization is expected to improve the consistency of treatment plans and reduce the duration of treatment planning.",
keywords = "Automation, Brachytherapy, Cervix, Clustering, Digitization, HDR, Segmentation, Tandem and ovoids, Threshold",
author = "Deufel, {Christopher L.} and Shulan Tian and Yan, {Benjamin B.} and Vaishnav, {Birjoo D.} and Haddock, {Michael G.} and Petersen, {Ivy A.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.brachy.2019.09.002",
language = "English (US)",
journal = "Brachytherapy",
issn = "1538-4721",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Automated applicator digitization for high-dose-rate cervix brachytherapy using image thresholding and density-based clustering

AU - Deufel, Christopher L.

AU - Tian, Shulan

AU - Yan, Benjamin B.

AU - Vaishnav, Birjoo D.

AU - Haddock, Michael G.

AU - Petersen, Ivy A.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Purpose: The purpose of the study was to develop and evaluate an automated digitization algorithm for high-dose-rate cervix brachytherapy, with the goal of reducing the duration of treatment planning, staff resources, variability, and potential for human error. Methods: An automated digitization algorithm was developed and retrospectively evaluated using treatment planning data from 10 patients with cervix cancer who were treated with a titanium tandem and ovoids applicator set. Applicators were segmented, without human interaction, by thresholding CT images to isolate high-density voxels and assigning the voxels to applicator and nonapplicator structures using HDBSCAN, a density-based linkage clustering algorithm. The applicator contours were determined from the centroid of the clustered voxels on each image slice and written to a treatment plan file. Automated contours were evaluated against manual digitization using distance and dosimetric metrics. Results: A close agreement between automatic and manual digitization was observed. The mean magnitude of contour disagreement for 10 patients equaled 0.3 mm. Hausdorff distances were ≤1.0 mm. The applicator tip coordinates had submillimeter agreement. The median and mean dose volume histogram parameter differences were less than or equal to 1% for high-risk clinical target volume D90, high-risk clinical target volume D95, bladder D2cc, rectum D2cc, large bowel D2cc, and small bowel D2cc. The average execution time for the automated algorithm was less than 30 s. Conclusion: The digitization of titanium tandem and ovoids applicators for high-dose-rate brachytherapy treatment planning can be automated using straightforward thresholding and clustering algorithms. The adoption of automated digitization is expected to improve the consistency of treatment plans and reduce the duration of treatment planning.

AB - Purpose: The purpose of the study was to develop and evaluate an automated digitization algorithm for high-dose-rate cervix brachytherapy, with the goal of reducing the duration of treatment planning, staff resources, variability, and potential for human error. Methods: An automated digitization algorithm was developed and retrospectively evaluated using treatment planning data from 10 patients with cervix cancer who were treated with a titanium tandem and ovoids applicator set. Applicators were segmented, without human interaction, by thresholding CT images to isolate high-density voxels and assigning the voxels to applicator and nonapplicator structures using HDBSCAN, a density-based linkage clustering algorithm. The applicator contours were determined from the centroid of the clustered voxels on each image slice and written to a treatment plan file. Automated contours were evaluated against manual digitization using distance and dosimetric metrics. Results: A close agreement between automatic and manual digitization was observed. The mean magnitude of contour disagreement for 10 patients equaled 0.3 mm. Hausdorff distances were ≤1.0 mm. The applicator tip coordinates had submillimeter agreement. The median and mean dose volume histogram parameter differences were less than or equal to 1% for high-risk clinical target volume D90, high-risk clinical target volume D95, bladder D2cc, rectum D2cc, large bowel D2cc, and small bowel D2cc. The average execution time for the automated algorithm was less than 30 s. Conclusion: The digitization of titanium tandem and ovoids applicators for high-dose-rate brachytherapy treatment planning can be automated using straightforward thresholding and clustering algorithms. The adoption of automated digitization is expected to improve the consistency of treatment plans and reduce the duration of treatment planning.

KW - Automation

KW - Brachytherapy

KW - Cervix

KW - Clustering

KW - Digitization

KW - HDR

KW - Segmentation

KW - Tandem and ovoids

KW - Threshold

UR - http://www.scopus.com/inward/record.url?scp=85072840861&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072840861&partnerID=8YFLogxK

U2 - 10.1016/j.brachy.2019.09.002

DO - 10.1016/j.brachy.2019.09.002

M3 - Article

AN - SCOPUS:85072840861

JO - Brachytherapy

JF - Brachytherapy

SN - 1538-4721

ER -