Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions

Linda Chen; Patricia Platzer; Christian Reschl; Mansure Schafasand; Ankita Nachankar; Christoph Lukas Hajdusich; Peter Kuess; Markus Stock; Steven Habraken; Antonio Carlino

doi:10.1016/j.phro.2023.100527

Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions

Phys Imaging Radiat Oncol. 2023 Dec 27:29:100527. doi: 10.1016/j.phro.2023.100527. eCollection 2024 Jan.

Authors

Linda Chen^{1

2

3

4}, Patricia Platzer^{1

5}, Christian Reschl¹, Mansure Schafasand^{1

6

7}, Ankita Nachankar^{1

8}, Christoph Lukas Hajdusich¹, Peter Kuess⁶, Markus Stock^{1

7}, Steven Habraken^{2

9}, Antonio Carlino¹

Affiliations

¹ MedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, Austria.
² Erasmus MC Cancer Institute, University Medical Center, Department of Radiotherapy, Rotterdam, the Netherlands.
³ Delft University of Technology, Faculty of Mechanical, Maritime and Materials Engineering, Delft, the Netherlands.
⁴ Leiden University Medical Center, Faculty of Medicine, Leiden, the Netherlands.
⁵ Fachhochschule Wiener Neustadt, Department MedTech, Wiener Neustadt, Austria.
⁶ Medical University of Vienna, Department of Radiation Oncology, Vienna, Austria.
⁷ Karl Landsteiner University of Health Sciences, Department of Oncology, Krems an der Donau, Austria.
⁸ ACMIT Gmbh, Department of Medicine, Wiener Neustadt, Austria.
⁹ Holland Proton Therapy Center, Department of Medical Physics & Informatics, Delft, the Netherlands.

Abstract

Background and purpose: Autocontouring for radiotherapy has the potential to significantly save time and reduce interobserver variability. We aimed to assess the performance of a commercial autocontouring model for head and neck (H&N) patients in eight orientations relevant to particle therapy with fixed beam lines, focusing on validation and implementation for routine clinical use.

Materials and methods: Autocontouring was performed on sixteen organs at risk (OARs) for 98 adult and pediatric patients with 137 H&N CT scans in eight orientations. A geometric comparison of the autocontours and manual segmentations was performed using the Hausdorff Distance 95th percentile, Dice Similarity Coefficient (DSC) and surface DSC and compared to interobserver variability where available. Additional qualitative scoring and dose-volume-histogram (DVH) parameters analyses were performed for twenty patients in two positions, consisting of scoring on a 0-3 scale based on clinical usability and comparing the mean (D_mean) and near-maximum (D_2%) dose, respectively.

Results: For the geometric analysis, the model performance in head-first-supine straight and hyperextended orientations was in the same range as the interobserver variability. HD95, DSC and surface DSC was heterogeneous in other orientations. No significant geometric differences were found between pediatric and adult autocontours. The qualitative scoring yielded a median score of ≥ 2 for 13/16 OARs while 7/32 DVH parameters were significantly different.

Conclusions: For head-first-supine straight and hyperextended scans, we found that 13/16 OAR autocontours were suited for use in daily clinical practice and subsequently implemented. Further development is needed for other patient orientations before implementation.

Keywords: Artificial Intelligence; Auto-segmentation; Autocontouring; Head and neck cancer; Organs-at-risk; Radiation therapy.