Purpose
Voluming of head and neck organs at risk (OARs) can be a time-consuming process which may delay planning output.
Implementation of atlas-based automated segmentation for radiotherapy planning may have a role in improving workflow and efficiency for a radiation oncology department.
This study addresses the efficiency aspects in terms of assessing the time it takes for an automated process to perform OAR voluming with manual adjustments, compared to conventional planning of OARs.
Methods and materials
Background
Head and neck radiotherapy planning includes delineation of normal structures, or organs at risk (OARs) to report potential dose volume constraints.
Voluming of these structures is time-consuming, as all of the structures of interest need to be delineated for each slice on the applicable computed tomography (CT) data set.
Automation has been of increasing interest to improve efficiency. Deep learning-based auto-segmentation to volume has recently shown promise in providing an accurate representation of organs at risk on CT datasets.1
Automated contouring has also been...
Results
Atlas runtime ranged from 4.6 to 7 minutes.
Adjustment of the atlas contours took 5.85 to 14 minutes.
The full manual voluming time ranged from 20 to 33.56 minutes. [Fig 1]
Compared to manual voluming, atlas-based segmentation with adjustments was significantly faster (mean atlas time 15.17 mins vs mean manual time 25.23 mins, p= 0.009924).
Conclusion
Atlas based automated segmentation can reduce the time needed to outline contours for OARs.
This can improve workflow for a radiotherapy department.
Volumes should still be assessed for accuracy and clinical consistency.
References
Chen X, Sun S, Bai N, Han K, Liu Q, Yao S, et al. A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy. Radiother Oncol. 2021 May 4;160:175-184.
Hvid CA, Elstrøm UV, Jensen K, Alber M, Grau C. Accuracy of software-assisted contour propagation from planning CT to cone beam CT in head and neck radiotherapy. Acta Oncol. 2016 Nov;55(11):1324-1330.
Daisne JF, Blumhofer A. Atlas-based automatic segmentation of head and neck organs at risk and nodal target volumes: a clinical...