Accelerate treatment planning process using deep learning generated fluence maps for cervical cancer radiation therapy

Zengtai Yuan; Yuxiang Wang; Panpan Hu; Duoer Zhang; Bing Yan; Hsiao‐Ming Lu; Hongyan Zhang; Yinghui Yang

doi:10.1002/mp.15530

journal article Feb 25, 2022

Accelerate treatment planning process using deep learning generated fluence maps for cervical cancer radiation therapy

Zengtai Yuan Yuxiang Wang

Panpan Hu

Duoer Zhang Bing Yan

Hsiao‐Ming Lu Hongyan Zhang

Yinghui Yang

Medical Physics Vol. 49 No. 4 pp. 2631-2641 · Wiley

View at Publisher Save 10.1002/mp.15530

Abstract

AbstractPurposeThis study aims to develop a deep learning method that skips the time‐consuming inverse optimization process for automatic generation of machine‐deliverable intensity‐modulated radiation therapy (IMRT) plans.MethodsNinety cervical cancer clinical IMRT plans were collected to train a two‐stage convolution neural network, of which 66 plans were assigned for training, 11 for validation, and 13 for test. The neural network took patients’ computed tomography (CT) anatomy as the input and predicted the fluence map for each radiation beam. The predicted fluence maps were then imported into a treatment planning system and converted to multileaf collimators motion sequences. The automatic plan was evaluated against its corresponding clinical plan, and its machine deliverability was validated by patient‐specific IMRT quality assurance (QA).ResultsThere were no significant differences in dose parameters between automatic and clinical plans for all 13 test patients, indicating a good prediction of fluence maps and a decent quality of automatic plans. The average dice similarity coefficient of isodose volumes encompassed by 0%–100% isodose lines ranged from 0.94 to 1. In patient‐specific IMRT QA, the mean gamma passing rate of automatic plans achieved 99.5% under 3%/3 mm criteria, and 97.3% under 2%/2 mm criteria, with a low dose threshold of 10%.ConclusionsThe proposed deep learning framework can produce machine‐deliverable IMRT plans with quality similar to the clinical plans in the test set. It skips the inverse plan optimization process and provides an effective and efficient method to accelerate treatment planning process.

Topics

No keywords indexed for this article. Browse by subject →

References

33

[1]

10.1002/cncr.21324

[2]

10.1016/0167‐8140(88)90167‐3

[3]

10.1088/0031‐9155/40/9/004

[4]

10.1118/1.596958

[5]

10.1118/1.4761864

[6]

10.1118/1.4906183

[7]

10.1016/j.radonc.2014.07.009

[8]

10.1016/j.ijrobp.2010.11.030

[9]

10.1118/1.3253464

[10]

10.1016/j.ijrobp.2010.05.026

[11]

10.1118/1.4828788

[12]

10.1002/mp.13271

[13]

Nguyen D "Dose prediction with U‐net: a feasibility study for predicting dose distributions from contours using deep learning on prostate IMRT patients" Arxiv (2017)

[14]

10.1002/mp.13597

[15]

10.1088/1361‐6560/aaef74

[16]

10.1002/mp.13262

[17]

10.1002/mp.14394

[18]

10.1002/mp.13490

[19]

10.1038/s41598‐019‐52262‐x

[20]

10.1016/j.adro.2021.100672

[21]

10.1088/1361‐6560/abc12c

[22]

10.1002/mp.14770

[23]

10.1016/j.neucom.2016.12.025

[24]

Chen L‐C "Rethinking atrous convolution for semantic image segmentation" Arxiv (2017)

[25]

Choromanska A "Batch normalization: accelerating deep network training by reducing internal covariate shift" Data Min With Decis Trees (2015)

[26]

Image quality assessment: from error visibility to structural similarity

Zhou Wang, A.C. Bovik, H.R. Sheikh et al.

IEEE Transactions on Image Processing 10.1109/tip.2003.819861

[27]

Kingma DP "Adam: a method for stochastic optimization" Arxiv (2015)

[28]

Dual Attention Network for Scene Segmentation

Jun Fu, Jing Liu, Haijie Tian et al.

2019 IEEE/CVF Conference on Computer Vision and Pa... 10.1109/cvpr.2019.00326

[29]

10.1007/s00066‐011‐0015‐x

[30]

10.1016/s0360‐3016(96)00601‐3

[31]

10.1109/tmi.2018.2845918

[32]

He K "Deep residual learning for image recognition" Arxiv (2016)

[33]

Tensorflow. TensorFlow. 2018.2018.https://www.tensorflow.org/

Cited By

20

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

20

Citations

33

References

Details

Published: Feb 25, 2022
Vol/Issue: 49(4)
Pages: 2631-2641
License: View

Authors

Z

Zengtai Yuan

Department of Engineering and Applied Physics University of Science and Technology of China Anhui China

Y

Yuxiang Wang

Hefei Ion Medical Center, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine University of Science and Technology of China Anhui China

P

Panpan Hu

Department of Engineering and Applied Physics University of Science and Technology of China Anhui China; Department of Radiation Oncology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine University of Science and Technology of China Anhui China

D

Duoer Zhang

Department of Engineering and Applied Physics University of Science and Technology of China Anhui China

B

Bing Yan

Department of Radiation Oncology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine University of Science and Technology of China Anhui China

H

Hsiao‐Ming Lu

Hefei Ion Medical Center, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine University of Science and Technology of China Anhui China

H

Hongyan Zhang

Hefei Ion Medical Center, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine University of Science and Technology of China Anhui China; Department of Radiation Oncology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine University of Science and Technology of China Anhui China

Y

Yinghui Yang

Department of Engineering and Applied Physics University of Science and Technology of China Anhui China; Department of Radiation Oncology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine University of Science and Technology of China Anhui China

Funding

Fundamental Research Funds for the Central Universities Award: WK2030000037

Cite This Article

Zengtai Yuan, Yuxiang Wang, Panpan Hu, et al. (2022). Accelerate treatment planning process using deep learning generated fluence maps for cervical cancer radiation therapy. Medical Physics, 49(4), 2631-2641. https://doi.org/10.1002/mp.15530

Accelerate treatment planning process using deep learning generated fluence maps for cervical cancer radiation therapy

You May Also Like