EUVIMEDEUVIMED entdecken
Crossref

Deep learning-based dose prediction to enhance planning efficiency in cervical brachytherapy with hybrid applicators

Sangutid Thongsawad iD, Nawarat Rinjan, Ekkasit Tharavichitkul, Chirasak Khamfongkhruea iD, Chirapha Tannanonta, Thananya Chanpanya

Physics in Medicine & Biology · 14.07.2026 · 71 (13) · 135008

DOI: 10.1088/1361-6560/ae7cd4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics in Medicine & Biology, online erschienen am 01.07.2026. Verfasst von Sangutid Thongsawad und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Chulabhorn Hospital, Bangkok, Thailand. Hauptthemen laut MEDLINE: Brachytherapy, Uterine Cervical Neoplasms, Radiotherapy Planning, Computer-Assisted, Deep Learning. Die Arbeit nennt 37 Literaturangaben. Gefördert von: National Research Council of Thailand.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective. This study aimed to develop a dose prediction model for hybrid applicators in cervical cancer brachytherapy. Approach. A total of 216 previous treatment plans were collected and divided into three datasets: training (161 plans), testing (40 plans), and clinical evaluation (15 plans). The treatment plans included three hybrid applicator types: tandem and ovoids combined with interstitial needles, tandem and ring combined with interstitial needles, and tandem and cylinder combined with interstitial needles. The model was validated on the testing dataset using mean absolute error (MAE) for voxel-wise dose evaluation and on the clinical evaluation dataset using dice similarity coefficient (DSC) and dose statistic differences. Main results. The model achieved a voxel-wise MAE of 0.45 ± 0.27 Gy and showed no statistically significant differences ( p > 0.05) in all key dose-volume histogram parameters when compared to clinical plans. The DSC values ranged from 0.74 to 0.77. Small dosimetric differences between the optimized and manually generated plans were observed for the high-risk clinical target volume (HR-CTV) D98%, HR-CTV D90%, and bladder D2cc. Significance. The developed dose prediction model demonstrates significant potential for application in hybrid applicator brachytherapy. This model can provide guidance for dose delivery during dwell time optimization. As a reference for optimization, it has the potential to streamline the planning process, reduce planning time, and improve consistency in adaptive workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BrachytherapyUterine Cervical NeoplasmsRadiotherapy Planning, Computer-AssistedDeep LearningRadiation DosageHumansRadiotherapy DosageFemale

Stichwörter der Autor:innen

Artificial Intelligencebrachytherapydeep learningdose prediction

Autor:innen und Institutionen

  • Department of Radiation Oncology, Chulabhorn Hospital, Bangkok, Thailand.
  • Medical Physics Program, Princess Srisavangavadhana Faculty of Medicine, Chulabhorn Royal Academy, Bangkok, Thailand.
  • Personalized Radiotherapy and Imaging in Medicine (PRIME) Research Center, Chulabhorn Royal Academy, Bangkok, Thailand.
  • Division of Radiation Oncology, Department of Radiology , Faculty of medicine, Chiang Mai University, Chiang Mai, Thailand.

ORCID-Profile: Sangutid Thongsawad, Chirasak Khamfongkhruea

Förderung

  • National Research Council of Thailand

Zitieren

APA

Thongsawad, S., Rinjan, N., Tharavichitkul, E., Khamfongkhruea, C., Tannanonta, C., & Chanpanya, T. (2026). Deep learning-based dose prediction to enhance planning efficiency in cervical brachytherapy with hybrid applicators. Physics in Medicine & Biology, 71(13), 135008. https://doi.org/10.1088/1361-6560/ae7cd4

Vancouver

Thongsawad S, Rinjan N, Tharavichitkul E, Khamfongkhruea C, Tannanonta C, Chanpanya T. Deep learning-based dose prediction to enhance planning efficiency in cervical brachytherapy with hybrid applicators. Physics in Medicine & Biology. 2026;71(13):135008. doi:10.1088/1361-6560/ae7cd4

BibTeX
@article{Thongsawad2026,
  author = {Thongsawad, Sangutid and Rinjan, Nawarat and Tharavichitkul, Ekkasit and Khamfongkhruea, Chirasak and Tannanonta, Chirapha and Chanpanya, Thananya},
  title = {Deep learning-based dose prediction to enhance planning efficiency in cervical brachytherapy with hybrid applicators},
  journal = {Physics in Medicine & Biology},
  year = {2026},
  volume = {71},
  number = {13},
  pages = {135008},
  doi = {10.1088/1361-6560/ae7cd4}
}
Kostenlos starten →