Impact of contrast-enhanced agent on segmentation using a deep learning-based software “Ai-Seg” for head and neck cancer
British Journal of Radiology · 2025
DOI: 10.1093/bjr/tqaf108 ↗Kurz gefasst
Fachartikel in der Zeitschrift British Journal of Radiology, 2025. Verfasst von Sayaka Kihara und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Osaka International Cancer Institute, Osaka 541-8567, Japan. Hauptthemen laut MEDLINE: Deep Learning, Contrast Media, Head and Neck Neoplasms, Tomography, X-Ray Computed. Die Arbeit nennt 38 Literaturangaben.
Abstract (Originalsprache)
Objectives
In radiotherapy, auto-segmentation tools using deep learning assist in contouring organs-at-risk (OARs). We developed a segmentation model for head and neck (HN) OARs dedicated to contrast-enhanced (CE) computed tomography (CT) using the segmentation software, Ai-Seg, and compared the performance between CE and non-CE (nCE) CT.
Methods
The retrospective study recruited 321 patients with HN cancers and trained a segmentation model using CE CT (CE model). The CE model was installed in Ai-Seg and applied to additional 25 patients with CE and nCE CT. The Dice similarity coefficient (DSC) and average Hausdorff distance (AHD) were calculated between the ground truth and Ai-Seg contours for brain, brainstem, chiasm, optic nerves, cochleae, oral cavity, parotid glands, pharyngeal constrictor muscle, and submandibular glands (SMGs). We compared the CE model and the existing model trained with nCE CT available in Ai-Seg for 6 OARs.
Results
The CE model obtained significantly higher DSCs on CE CT for parotid and SMGs compared to the existing model. The CE model provided significantly lower DSC values and higher AHD values on nCE CT for SMGs than on CE CT, but comparable values for other OARs.
Conclusions
The CE model achieved significantly better performance than the existing model and can be used on nCE CT images without significant performance difference, except SMGs. Our results may facilitate the adoption of segmentation tools in clinical practice. Advances in knowledge We developed a segmentation model for HN OARs dedicated to CE CT using Ai-Seg and evaluated its usability on nCE CT.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Radiation Oncology, Osaka International Cancer Institute, Osaka 541-8567, Japan.
- Medical Physics Laboratory, Division of Health Science, Graduate School of Medicine, The University of Osaka, Osaka 565-0871, Japan.
- AI Solution Division, Hyogo Ion Beam Medical Support Co., Ltd., Kakogawa City, Hyogo 675-0064, Japan.
ORCID-Profile: Sayaka Kihara, Yoshihiro Ueda, Naoyuki Kanayama
Zitieren
APA
Kihara, S., Ueda, Y., Harada, S., Masaoka, A., Kanayama, N., Ikawa, T., Inui, S., Akagi, T., Nishio, T., & Konishi, K. (2025). Impact of contrast-enhanced agent on segmentation using a deep learning-based software “Ai-Seg” for head and neck cancer. British Journal of Radiology. https://doi.org/10.1093/bjr/tqaf108
Vancouver
Kihara S, Ueda Y, Harada S, Masaoka A, Kanayama N, Ikawa T, et al. Impact of contrast-enhanced agent on segmentation using a deep learning-based software “Ai-Seg” for head and neck cancer. British Journal of Radiology. 2025. doi:10.1093/bjr/tqaf108
BibTeX
@article{Kihara2025,
author = {Kihara, Sayaka and Ueda, Yoshihiro and Harada, Shuichi and Masaoka, Akira and Kanayama, Naoyuki and Ikawa, Toshiki and Inui, Shoki and Akagi, Takashi and Nishio, Teiji and Konishi, Koji},
title = {Impact of contrast-enhanced agent on segmentation using a deep learning-based software “Ai-Seg” for head and neck cancer},
journal = {British Journal of Radiology},
year = {2025},
doi = {10.1093/bjr/tqaf108}
}
EUVIMED