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

Abstract 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 i...

Full description

Saved in:
Bibliographic Details
Main Authors: Wencheng Shao, Liangyong Qu, Xin Lin, Ying Huang, Weihai Zhuo, Haikuan Liu
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:Precision Radiation Oncology
Subjects:
Online Access:https://doi.org/10.1002/pro6.70016
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849708111124758528
author Wencheng Shao
Liangyong Qu
Xin Lin
Ying Huang
Weihai Zhuo
Haikuan Liu
author_facet Wencheng Shao
Liangyong Qu
Xin Lin
Ying Huang
Weihai Zhuo
Haikuan Liu
author_sort Wencheng Shao
collection DOAJ
description Abstract 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 (R2). Results The results showed a high precision in dose prediction for various organs, including the brain (MAPE: 1.5%, R2: 0.9), eyes (MAPE: 5%, R2: 0.84), lens (MAPE: 5%, R2: 0.82), bowel (MAPE: 6%, R2: 0.84), kidneys (MAPE: 7.5%, R2: 0.7), and liver (MAPE: 8%, R2: 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.
format Article
id doaj-art-74753c2951ea4b8caca2a6a619f5a71f
institution DOAJ
issn 2398-7324
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series Precision Radiation Oncology
spelling doaj-art-74753c2951ea4b8caca2a6a619f5a71f2025-08-20T03:15:46ZengWileyPrecision Radiation Oncology2398-73242025-06-0192778610.1002/pro6.70016Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning modelsWencheng Shao0Liangyong Qu1Xin Lin2Ying Huang3Weihai Zhuo4Haikuan Liu5Institute of Radiation Medicine Fudan University Shanghai ChinaDepartment of Radiology Shanghai Zhongye Hospital Shanghai ChinaInstitute of Radiation Medicine Fudan University Shanghai ChinaDepartment of Nuclear Science and Technology Institute of Modern Physics Fudan University Shanghai ChinaInstitute of Radiation Medicine Fudan University Shanghai ChinaInstitute of Radiation Medicine Fudan University Shanghai ChinaAbstract 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 (R2). Results The results showed a high precision in dose prediction for various organs, including the brain (MAPE: 1.5%, R2: 0.9), eyes (MAPE: 5%, R2: 0.84), lens (MAPE: 5%, R2: 0.82), bowel (MAPE: 6%, R2: 0.84), kidneys (MAPE: 7.5%, R2: 0.7), and liver (MAPE: 8%, R2: 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.https://doi.org/10.1002/pro6.70016computed tomographyorgan doseradiomics featuressegmentation‐freesupport vector regression
spellingShingle Wencheng Shao
Liangyong Qu
Xin Lin
Ying Huang
Weihai Zhuo
Haikuan Liu
Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models
Precision Radiation Oncology
computed tomography
organ dose
radiomics features
segmentation‐free
support vector regression
title Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models
title_full Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models
title_fullStr Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models
title_full_unstemmed Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models
title_short Fast estimation of patient‐specific organ doses from abdomen and head CT examinations without segmenting internal organs using machine learning models
title_sort fast estimation of patient specific organ doses from abdomen and head ct examinations without segmenting internal organs using machine learning models
topic computed tomography
organ dose
radiomics features
segmentation‐free
support vector regression
url https://doi.org/10.1002/pro6.70016
work_keys_str_mv AT wenchengshao fastestimationofpatientspecificorgandosesfromabdomenandheadctexaminationswithoutsegmentinginternalorgansusingmachinelearningmodels
AT liangyongqu fastestimationofpatientspecificorgandosesfromabdomenandheadctexaminationswithoutsegmentinginternalorgansusingmachinelearningmodels
AT xinlin fastestimationofpatientspecificorgandosesfromabdomenandheadctexaminationswithoutsegmentinginternalorgansusingmachinelearningmodels
AT yinghuang fastestimationofpatientspecificorgandosesfromabdomenandheadctexaminationswithoutsegmentinginternalorgansusingmachinelearningmodels
AT weihaizhuo fastestimationofpatientspecificorgandosesfromabdomenandheadctexaminationswithoutsegmentinginternalorgansusingmachinelearningmodels
AT haikuanliu fastestimationofpatientspecificorgandosesfromabdomenandheadctexaminationswithoutsegmentinginternalorgansusingmachinelearningmodels