EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models

Wencheng Shao iD, Liangyong Qu, Xin Lin, Ying Huang, Weihai Zhuo, Haikuan Liu

Precision Radiation Oncology · 2025-06 · 9 (2) · 77-86

DOI: 10.1002/pro6.70016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Precision Radiation Oncology, online erschienen am 29.05.2025. Verfasst von Wencheng Shao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Radiation Medicine Fudan University Shanghai China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Computed Tomography (CT) imaging is essential for disease detection but carries a risk of cancer due to X‐ray exposure. Typically, assessing this risk requires segmentation of the internal organ contours to predict organ doses, which hinders its clinical application. This study introduces a method that uses support vector regression (SVR) models trained on skin outline radiomic features to predict organ doses without organ segmentation, thus streamlining the process for clinical use.

Methods

CT scans of the head and abdomen were used to extract radiomic features of the skin outline. These features were used as inputs, with organ doses from Monte Carlo simulations as benchmarks to train the SVR models for predicting organ doses. The accuracy of the models was evaluated using the mean absolute percentage error (MAPE) and coefficient of determination (R 2 ).

Results

The results showed a high precision in dose prediction for various organs, including the brain (MAPE: 1.5%, R 2 : 0.9), eyes (MAPE: 5%, R 2 : 0.84), lens (MAPE: 5%, R 2 : 0.82), bowel (MAPE: 6%, R 2 : 0.84), kidneys (MAPE: 7.5%, R 2 : 0.7), and liver (MAPE: 8%, R 2 : 0.67). Internal organ disturbances had a minimal impact on accuracy.

Conclusions

The SVR models efficiently predicted patient‐specific organ doses from CT scans, offering a user‐friendly tool for rapid segmentation‐free dose prediction. This innovation can significantly enhance clinical efficiency and accessibility in predicting patient‐specific organ doses using CT.

Schlagwörter

Stichwörter der Autor:innen

computed tomographyorgan doseradiomics featuressegmentation‐freesupport vector regression

Autor:innen und Institutionen

  • Institute of Radiation Medicine Fudan University Shanghai China.
  • Department of Radiology Shanghai Zhongye Hospital Shanghai China.
  • Department of Nuclear Science and Technology Institute of Modern Physics Fudan University Shanghai China.

ORCID-Profile: Wencheng Shao

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Shao, W., Qu, L., Lin, X., Huang, Y., Zhuo, W., & Liu, H. (2025). Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models. Precision Radiation Oncology, 9(2), 77-86. https://doi.org/10.1002/pro6.70016

Vancouver

Shao W, Qu L, Lin X, Huang Y, Zhuo W, Liu H. Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models. Precision Radiation Oncology. 2025;9(2):77-86. doi:10.1002/pro6.70016

BibTeX
@article{Shao2025,
  author = {Shao, Wencheng and Qu, Liangyong and Lin, Xin and Huang, Ying and Zhuo, Weihai and Liu, Haikuan},
  title = {Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models},
  journal = {Precision Radiation Oncology},
  year = {2025},
  volume = {9},
  number = {2},
  pages = {77--86},
  doi = {10.1002/pro6.70016}
}
Kostenlos starten →