Efficient dose–volume histogram–based pretreatment patient‐specific quality assurance methodology with combined deep learning and machine learning models for volumetric modulated arc radiotherapy

Changfei Gong; Kecheng Zhu; Chengyin Lin; Ce Han; Zhongjie Lu; Yuanhua Chen; Changhui Yu; Liqiao Hou; Yongqiang Zhou; Jinling Yi; Yao Ai; Xiaojun Xiang; Congying Xie; Xiance Jin

doi:10.1002/mp.16010

journal article Oct 17, 2022

Efficient dose–volume histogram–based pretreatment patient‐specific quality assurance methodology with combined deep learning and machine learning models for volumetric modulated arc radiotherapy

Changfei Gong Kecheng Zhu

Chengyin Lin Ce Han

Zhongjie Lu Yuanhua Chen

Changhui Yu

Liqiao Hou Yongqiang Zhou

Jinling Yi Yao Ai Xiaojun Xiang Congying Xie Xiance Jin

Medical Physics Vol. 49 No. 12 pp. 7779-7790 · Wiley

View at Publisher Save 10.1002/mp.16010

Abstract

AbstractBackgroundWeak correlation between gamma passing rates and dose differences in target volumes and organs at risk (OARs) has been reported in several studies. Evaluation on the differences between planned dose–volume histogram (DVH) and reconstructed DVH from measurement was adopted and incorporated into patient‐specific quality assurance (PSQA). However, it is difficult to develop a methodology allowing the evaluation of errors on DVHs accurately and quickly.PurposeTo develop a DVH‐based pretreatment PSQA for volumetric modulated arc therapy (VMAT) with combined deep learning (DL) and machine learning models to overcome the limitation of conventional gamma index (GI) and improve the efficiency of DVH‐based PSQA.MethodsA DL model with a three‐dimensional squeeze‐and‐excitation residual blocks incorporated into a modified U‐net was developed to predict the measured PSQA DVHs of 208 head‐and‐neck (H&N) cancer patients underwent VMAT between 2018 and 2021 from two hospitals, in which 162 cases was randomly selected for training, 18 for validation, and 28 for testing. After evaluating the differences between treatment planning system (TPS) and PSQA DVHs predicted by DL model with multiple metrics, a pass or fail (PoF) classification model was developed using XGBoost algorithm. Evaluation of domain experts on dose errors between TPS and reconstructed PSQA DVHs was taken as ground truth for PoF classification model training.ResultsThe prediction model was able to achieve a good agreement between predicted, measured, and TPS doses. Quantitative evaluation demonstrated no significant difference between predicted PSQA dose and measured dose for target and OARs, except for Dmean of PTV6900 (p = 0.001), D50 of PTV6000 (p = 0.014), D2 of PTV5400 (p = 0.009), D50 of left parotid (p = 0.015), and Dmax of left inner ear (p = 0.007). The XGBoost model achieved an area under curves, accuracy, sensitivity, and specificity of 0.89 versus 0.88, 0.89 versus 0.86, 0. 71 versus 0.71, and 0.95 versus 0.91 with measured and predicted PSQA doses, respectively. The agreement between domain experts and the classification model was 86% for 28 test cases.ConclusionsThe successful prediction of PSQA doses and classification of PoF for H&N VMAT PSQA indicating that this DVH‐based PSQA method is promising to overcome the limitations of GI and to improve the efficiency and accuracy of VMAT delivery.

Topics

No keywords indexed for this article. Browse by subject →

References

48

[1]

10.1118/1.1591194

[2]

10.1016/j.ijrobp.2008.04.049

[3]

A technique for the quantitative evaluation of dose distributions

Daniel A. Low, William B. Harms, Sasa Mutic et al.

Medical Physics 10.1118/1.598248

[4]

10.1118/1.2721657

[5]

10.7785/tcrt.2012.500353

[6]

10.1002/mp.13297

[7]

10.1118/1.4826166

[8]

10.1118/1.3633904

[9]

10.1118/1.4767763

[10]

10.1118/1.4899177

[11]

10.1016/j.ijrobp.2014.08.334

[12]

10.1002/acm2.12114

[13]

10.1002/mp.12810

[14]

10.1118/1.4736949

[15]

10.1118/1.4788645

[16]

10.1259/bjr.20140577

[17]

10.1002/acm2.12062

[18]

10.3389/frai.2020.577620

[19]

10.1002/mp.13445

[20]

10.1016/j.jacr.2019.06.001

[21]

10.1118/1.4953835

[22]

10.1002/mp.13112

[23]

10.1002/mp.13752

[24]

10.1016/j.imu.2020.100292

[25]

10.1016/j.ijrobp.2019.07.049

[26]

10.1002/mp.14670

[27]

10.1088/1361-6560/ab142e

[28]

10.1002/mp.14559

[29]

10.1002/mp.14014

[30]

10.1002/mp.14699

[31]

10.1016/j.ejmp.2020.03.022

[32]

10.1002/acm2.13375

[33]

10.1002/mp.14870

[34]

10.1259/bjr.20190001

[35]

10.1016/j.meddos.2013.05.004

[36]

10.1016/j.ejmp.2019.01.016

[37]

10.1186/s13014-018-1106-y

[38]

10.1109/tpami.2019.2913372

[39]

10.1002/mp.13300

[40]

Tieleman T "Lecture 6.5‐rmsprop: divide the gradient by a running average of its recent magnitude" COURSERA: Neural Networks Mach Learn (2012)

[41]

10.1016/j.ijrobp.2017.03.049

[42]

10.1118/1.4824433

[43]

10.1093/jrr/rrx100

[44]

10.1118/1.3512801

[45]

10.1088/0031-9155/52/16/018

[46]

10.1016/j.radonc.2008.07.002

[47]

10.1002/mp.13271

[48]

10.1088/1361-6560/ab039b

Cited By

9

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

Coen Hurkmans, Jean-Emmanuel Bibault · 2024

Radiotherapy and Oncology

Metrics

9

Citations

48

References

Details

Published: Oct 17, 2022
Vol/Issue: 49(12)
Pages: 7779-7790
License: View

Authors

C

Changfei Gong

Radiation Oncology Department 1st Affiliated Hospital of Nanchang Medical University Nanchang China; Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China

K

Kecheng Zhu

Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China

C

Chengyin Lin

Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China

C

Ce Han

Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China

Z

Zhongjie Lu

Radiation Oncology Department 1st Affiliated Hospital of Medical School of Zhejiang University Zhejiang China

Y

Yuanhua Chen

Radiation Oncology Department 1st Affiliated Hospital of Medical School of Zhejiang University Zhejiang China

C

Changhui Yu

Radiation Oncology Department Taizhou Hospital of Zhejiang Province Taizhou China

L

Liqiao Hou

Radiation Oncology Department Taizhou Hospital of Zhejiang Province Taizhou China

Y

Yongqiang Zhou

Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China

J

Jinling Yi

Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China

Y

Yao Ai

Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China

X

Xiaojun Xiang

Radiation Oncology Department 1st Affiliated Hospital of Nanchang Medical University Nanchang China

C

Congying Xie

Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China; Radiation Oncology Department 2nd Affiliated Hospital of Wenzhou Medical University Wenzhou China

X

Xiance Jin

Radiotherapy Center 1st Affiliated Hospital of Wenzhou Medical University Wenzhou China; School of Basic Medical Science Wenzhou Medical University Wenzhou China

Funding

Wenzhou Municipal Science and Technology Bureau Award: Y2020917

Cite This Article

Changfei Gong, Kecheng Zhu, Chengyin Lin, et al. (2022). Efficient dose–volume histogram–based pretreatment patient‐specific quality assurance methodology with combined deep learning and machine learning models for volumetric modulated arc radiotherapy. Medical Physics, 49(12), 7779-7790. https://doi.org/10.1002/mp.16010

Efficient dose–volume histogram–based pretreatment patient‐specific quality assurance methodology with combined deep learning and machine learning models for volumetric modulated arc radiotherapy

You May Also Like