A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning

Dan Nguyen, Troy Long, Xun Jia, Weiguo Lu, Xuejun Gu, Zohaib Iqbal, Steve B Jiang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at the cost of increased treatment plan complexity and planning time. The accurate prediction of dose distributions would alleviate this issue by guiding clinical plan optimization to save time and maintain high quality plans. We have modified a convolutional deep network model, U-net (originally designed for segmentation purposes), for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR). We show that, as an example, we are able to accurately predict the dose of intensity-modulated radiation therapy (IMRT) for prostate cancer patients, where the average Dice similarity coefficient is 0.91 when comparing the predicted vs. true isodose volumes between 0% and 100% of the prescription dose. The average value of the absolute differences in [max, mean] dose is found to be under 5% of the prescription dose, specifically for each structure is [1.80%, 1.03%](PTV), [1.94%, 4.22%](Bladder), [1.80%, 0.48%](Body), [3.87%, 1.79%](L Femoral Head), [5.07%, 2.55%](R Femoral Head), and [1.26%, 1.62%](Rectum) of the prescription dose. We thus managed to map a desired radiation dose distribution from a patient’s PTV and OAR contours. As an additional advantage, relatively little data was used in the techniques and models described in this paper.

Original languageEnglish (US)
Article number1076
JournalScientific Reports
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Feasibility Studies
Prostatic Neoplasms
Anatomy
Radiotherapy
Learning
Organs at Risk
Prescriptions
Thigh
Rectum
Health Care Costs
Urinary Bladder
Radiation
Neoplasms
Therapeutics

ASJC Scopus subject areas

  • General

Cite this

@article{c5ed8f79016a479da3f4092874230c9c,
title = "A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning",
abstract = "With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at the cost of increased treatment plan complexity and planning time. The accurate prediction of dose distributions would alleviate this issue by guiding clinical plan optimization to save time and maintain high quality plans. We have modified a convolutional deep network model, U-net (originally designed for segmentation purposes), for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR). We show that, as an example, we are able to accurately predict the dose of intensity-modulated radiation therapy (IMRT) for prostate cancer patients, where the average Dice similarity coefficient is 0.91 when comparing the predicted vs. true isodose volumes between 0{\%} and 100{\%} of the prescription dose. The average value of the absolute differences in [max, mean] dose is found to be under 5{\%} of the prescription dose, specifically for each structure is [1.80{\%}, 1.03{\%}](PTV), [1.94{\%}, 4.22{\%}](Bladder), [1.80{\%}, 0.48{\%}](Body), [3.87{\%}, 1.79{\%}](L Femoral Head), [5.07{\%}, 2.55{\%}](R Femoral Head), and [1.26{\%}, 1.62{\%}](Rectum) of the prescription dose. We thus managed to map a desired radiation dose distribution from a patient’s PTV and OAR contours. As an additional advantage, relatively little data was used in the techniques and models described in this paper.",
author = "Dan Nguyen and Troy Long and Xun Jia and Weiguo Lu and Xuejun Gu and Zohaib Iqbal and Jiang, {Steve B}",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-018-37741-x",
language = "English (US)",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning

AU - Nguyen, Dan

AU - Long, Troy

AU - Jia, Xun

AU - Lu, Weiguo

AU - Gu, Xuejun

AU - Iqbal, Zohaib

AU - Jiang, Steve B

PY - 2019/12/1

Y1 - 2019/12/1

N2 - With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at the cost of increased treatment plan complexity and planning time. The accurate prediction of dose distributions would alleviate this issue by guiding clinical plan optimization to save time and maintain high quality plans. We have modified a convolutional deep network model, U-net (originally designed for segmentation purposes), for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR). We show that, as an example, we are able to accurately predict the dose of intensity-modulated radiation therapy (IMRT) for prostate cancer patients, where the average Dice similarity coefficient is 0.91 when comparing the predicted vs. true isodose volumes between 0% and 100% of the prescription dose. The average value of the absolute differences in [max, mean] dose is found to be under 5% of the prescription dose, specifically for each structure is [1.80%, 1.03%](PTV), [1.94%, 4.22%](Bladder), [1.80%, 0.48%](Body), [3.87%, 1.79%](L Femoral Head), [5.07%, 2.55%](R Femoral Head), and [1.26%, 1.62%](Rectum) of the prescription dose. We thus managed to map a desired radiation dose distribution from a patient’s PTV and OAR contours. As an additional advantage, relatively little data was used in the techniques and models described in this paper.

AB - With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at the cost of increased treatment plan complexity and planning time. The accurate prediction of dose distributions would alleviate this issue by guiding clinical plan optimization to save time and maintain high quality plans. We have modified a convolutional deep network model, U-net (originally designed for segmentation purposes), for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR). We show that, as an example, we are able to accurately predict the dose of intensity-modulated radiation therapy (IMRT) for prostate cancer patients, where the average Dice similarity coefficient is 0.91 when comparing the predicted vs. true isodose volumes between 0% and 100% of the prescription dose. The average value of the absolute differences in [max, mean] dose is found to be under 5% of the prescription dose, specifically for each structure is [1.80%, 1.03%](PTV), [1.94%, 4.22%](Bladder), [1.80%, 0.48%](Body), [3.87%, 1.79%](L Femoral Head), [5.07%, 2.55%](R Femoral Head), and [1.26%, 1.62%](Rectum) of the prescription dose. We thus managed to map a desired radiation dose distribution from a patient’s PTV and OAR contours. As an additional advantage, relatively little data was used in the techniques and models described in this paper.

UR - http://www.scopus.com/inward/record.url?scp=85060933244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060933244&partnerID=8YFLogxK

U2 - 10.1038/s41598-018-37741-x

DO - 10.1038/s41598-018-37741-x

M3 - Article

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 1076

ER -