EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 3.0

Interobserver delineation variability of computed tomography-based radiomic features of the parotid gland

Kanyapat Buasawat, Sasikarn Chamchod, Todsaporn Fuangrod, Sawanee Suntiwong, Thiansin Liamsuwan

Radiation Oncology Journal · 31.03.2024 · 42 (1) · 63-73

DOI: 10.3857/roj.2023.00605 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiation Oncology Journal, erschienen am 31.03.2024. Verfasst von Kanyapat Buasawat und 4 weiteren Autor:innen. Beteiligte Einrichtung: Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy, Bangkok, Thailand. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: Chulabhorn Royal Academy, National Science Research and Innovation Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To assess the interobserver delineation variability of radiomic features of the parotid gland from computed tomography (CT) images and evaluate the correlation of these features for head and neck cancer (HNC) radiotherapy patients.Materials and Methods: Contrast-enhanced CT images of 20 HNC patients were utilized. The parotid glands were delineated by treating radiation oncologists (ROs), a selected RO and AccuContour auto-segmentation software. Dice similarity coefficients (DSCs) between each pair of observers were calculated. A total of 107 radiomic features were extracted, whose robustness to interobserver delineation was assessed using the intraclass correlation coefficient (ICC). Pearson correlation coefficients (r) were calculated to determine the relationship between the features. The influence of excluding unrobust features from normal tissue complication probability (NTCP) modeling was investigated for severe oral mucositis (grade ≥3).

Results

The average DSC was 0.84 (95% confidence interval, 0.83–0.86). Most of the shape features demonstrated robustness (ICC ≥0.75), while the first-order and texture features were influenced by delineation variability. Among the three observers investigated, 42 features were sufficiently robust, out of which 36 features exhibited weak correlation (|r|

Schlagwörter

Stichwörter der Autor:innen

AutosegmentationHead and neck cancerInterobserver variabilityParotid glandRadiomics

Autor:innen und Institutionen

  • Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy, Bangkok, Thailand.
  • Department of Radiation Oncology, Chulabhorn Hospital, Chulabhorn Royal Academy, Bangkok, Thailand.

Förderung

  • Chulabhorn Royal Academy
  • National Science Research and Innovation Fund

Zitieren

APA

Buasawat, K., Chamchod, S., Fuangrod, T., Suntiwong, S., & Liamsuwan, T. (2024). Interobserver delineation variability of computed tomography-based radiomic features of the parotid gland. Radiation Oncology Journal, 42(1), 63-73. https://doi.org/10.3857/roj.2023.00605

Vancouver

Buasawat K, Chamchod S, Fuangrod T, Suntiwong S, Liamsuwan T. Interobserver delineation variability of computed tomography-based radiomic features of the parotid gland. Radiation Oncology Journal. 2024;42(1):63-73. doi:10.3857/roj.2023.00605

BibTeX
@article{Buasawat2024,
  author = {Buasawat, Kanyapat and Chamchod, Sasikarn and Fuangrod, Todsaporn and Suntiwong, Sawanee and Liamsuwan, Thiansin},
  title = {Interobserver delineation variability of computed tomography-based radiomic features of the parotid gland},
  journal = {Radiation Oncology Journal},
  year = {2024},
  volume = {42},
  number = {1},
  pages = {63--73},
  doi = {10.3857/roj.2023.00605}
}
Kostenlos starten →