Criteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planning

Abstract Background Knowledge-Based Planning (KBP) pipelines, which integrate machine learning-based models to predict dose distribution, have gained popularity in clinical radiation therapy. However, for patients with specific requirements, the trained models may struggle to rapidly adjust to guide...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongguang Liang, Jingru Yang, Shuoyang Wei, Yanfei Liu, Shumeng He, Kang Zhang, Jie Qiu, Bo Yang
Format: Article
Language:English
Published: BMC 2025-08-01
Series:Radiation Oncology
Subjects:
Online Access:https://doi.org/10.1186/s13014-025-02684-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226074419888128
author Yongguang Liang
Jingru Yang
Shuoyang Wei
Yanfei Liu
Shumeng He
Kang Zhang
Jie Qiu
Bo Yang
author_facet Yongguang Liang
Jingru Yang
Shuoyang Wei
Yanfei Liu
Shumeng He
Kang Zhang
Jie Qiu
Bo Yang
author_sort Yongguang Liang
collection DOAJ
description Abstract Background Knowledge-Based Planning (KBP) pipelines, which integrate machine learning-based models to predict dose distribution, have gained popularity in clinical radiation therapy. However, for patients with specific requirements, the trained models may struggle to rapidly adjust to guide the automatic planning process. Therefore, the aim of this study was to calibrate the dose prediction model to improve the quality and accuracy of automatic planning for cervical cancer radiation therapy. Materials and methods We retrospectively collected a routine cervical cancer dataset (200 cases) to conduct the KBP pipelines for automatically generating radiation planning, and a small number of ovarian-protection and myelosuppressive datasets (21 cases) to calibrate and evaluate the dose prediction model. A total of three criteria-calibration approaches to solve the data imbalance problem in dose prediction were introduced and compared, including Prediction Tolerance function on uTPS (United Imaging Healthcare Co., Ltd., Shanghai), transfer learning, and mixture density network. Results The Prediction Tolerance function allowed for rapid optimization adjustments without model modification, which is suitable for patients with strong desires for ovary protection. The transfer learning approach required minimal training time and data to generate acceptable automatic planning results. The Mixture Density Network (MDN) approach, although the most time-consuming to train, achieved robust prediction results and facilitated dataset analysis. The MDN method showed the greatest consistency between predicted dose distribution and actual optimization outcomes, highlighting its potential as a reliable calibration method for dose prediction. Conclusion This study demonstrated an automatic KBP workflow and compared three criteria-calibration approaches to address the data imbalance problem in dose prediction. These approaches can partially calibrate pre-existing models to accommodate newly added criteria and could be implemented according to specific requirements in different scenarios. Although there are trade-offs in various aspects, they all can generate feasible radiation treatment plans.
format Article
id doaj-art-85c0e4b1a0a94adf90736413a94bfe02
institution Kabale University
issn 1748-717X
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series Radiation Oncology
spelling doaj-art-85c0e4b1a0a94adf90736413a94bfe022025-08-24T11:42:11ZengBMCRadiation Oncology1748-717X2025-08-0120111310.1186/s13014-025-02684-xCriteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planningYongguang Liang0Jingru Yang1Shuoyang Wei2Yanfei Liu3Shumeng He4Kang Zhang5Jie Qiu6Bo Yang7Department of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College HospitalDepartment of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College HospitalDepartment of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College HospitalUnited Imaging Research Institute of Innovative Medical EquipmentUnited Imaging Research Institute of Intelligent ImagingShanghai United Imaging Healthcare Co., Ltd.Department of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College HospitalDepartment of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College HospitalAbstract Background Knowledge-Based Planning (KBP) pipelines, which integrate machine learning-based models to predict dose distribution, have gained popularity in clinical radiation therapy. However, for patients with specific requirements, the trained models may struggle to rapidly adjust to guide the automatic planning process. Therefore, the aim of this study was to calibrate the dose prediction model to improve the quality and accuracy of automatic planning for cervical cancer radiation therapy. Materials and methods We retrospectively collected a routine cervical cancer dataset (200 cases) to conduct the KBP pipelines for automatically generating radiation planning, and a small number of ovarian-protection and myelosuppressive datasets (21 cases) to calibrate and evaluate the dose prediction model. A total of three criteria-calibration approaches to solve the data imbalance problem in dose prediction were introduced and compared, including Prediction Tolerance function on uTPS (United Imaging Healthcare Co., Ltd., Shanghai), transfer learning, and mixture density network. Results The Prediction Tolerance function allowed for rapid optimization adjustments without model modification, which is suitable for patients with strong desires for ovary protection. The transfer learning approach required minimal training time and data to generate acceptable automatic planning results. The Mixture Density Network (MDN) approach, although the most time-consuming to train, achieved robust prediction results and facilitated dataset analysis. The MDN method showed the greatest consistency between predicted dose distribution and actual optimization outcomes, highlighting its potential as a reliable calibration method for dose prediction. Conclusion This study demonstrated an automatic KBP workflow and compared three criteria-calibration approaches to address the data imbalance problem in dose prediction. These approaches can partially calibrate pre-existing models to accommodate newly added criteria and could be implemented according to specific requirements in different scenarios. Although there are trade-offs in various aspects, they all can generate feasible radiation treatment plans.https://doi.org/10.1186/s13014-025-02684-xKnowledge-based planningAuto-planninguTPSPrediction tolerance
spellingShingle Yongguang Liang
Jingru Yang
Shuoyang Wei
Yanfei Liu
Shumeng He
Kang Zhang
Jie Qiu
Bo Yang
Criteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planning
Radiation Oncology
Knowledge-based planning
Auto-planning
uTPS
Prediction tolerance
title Criteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planning
title_full Criteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planning
title_fullStr Criteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planning
title_full_unstemmed Criteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planning
title_short Criteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planning
title_sort criteria calibration approaches to deep learning based cervical cancer radiation treatment auto planning
topic Knowledge-based planning
Auto-planning
uTPS
Prediction tolerance
url https://doi.org/10.1186/s13014-025-02684-x
work_keys_str_mv AT yongguangliang criteriacalibrationapproachestodeeplearningbasedcervicalcancerradiationtreatmentautoplanning
AT jingruyang criteriacalibrationapproachestodeeplearningbasedcervicalcancerradiationtreatmentautoplanning
AT shuoyangwei criteriacalibrationapproachestodeeplearningbasedcervicalcancerradiationtreatmentautoplanning
AT yanfeiliu criteriacalibrationapproachestodeeplearningbasedcervicalcancerradiationtreatmentautoplanning
AT shumenghe criteriacalibrationapproachestodeeplearningbasedcervicalcancerradiationtreatmentautoplanning
AT kangzhang criteriacalibrationapproachestodeeplearningbasedcervicalcancerradiationtreatmentautoplanning
AT jieqiu criteriacalibrationapproachestodeeplearningbasedcervicalcancerradiationtreatmentautoplanning
AT boyang criteriacalibrationapproachestodeeplearningbasedcervicalcancerradiationtreatmentautoplanning