Deep-dose

a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry

Min Sun Lee, Donghwi Hwang, Joong Hyun Kim, Jae Sung Lee

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Personalized dosimetry with high accuracy is crucial owing to the growing interests in personalized medicine. The direct Monte Carlo simulation is considered as a state-of-art voxel-based dosimetry technique; however, it incurs an excessive computational cost and time. To overcome the limitations of the direct Monte Carlo approach, we propose using a deep convolutional neural network (CNN) for the voxel dose prediction. PET and CT image patches were used as inputs for the CNN with the given ground truth from direct Monte Carlo. The predicted voxel dose rate maps from the CNN were compared with the ground truth and dose rate maps generated voxel S-value (VSV) kernel convolution method, which is one of the common voxel-based dosimetry techniques. The CNN-based dose rate map agreed well with the ground truth with voxel dose rate errors of 2.54% ± 2.09%. The VSV kernel approach showed a voxel error of 9.97% ± 1.79%. In the whole-body dosimetry study, the average organ absorbed dose errors were 1.07%, 9.43%, and 34.22% for the CNN, VSV, and OLINDA/EXM dosimetry software, respectively. The proposed CNN-based dosimetry method showed improvements compared to the conventional dosimetry approaches and showed results comparable with that of the direct Monte Carlo simulation with significantly lower calculation time.

Original languageEnglish
Article number10308
JournalScientific Reports
Volume9
Issue number1
DOIs
StatePublished - 1 Dec 2019

Fingerprint

Precision Medicine
Software
Costs and Cost Analysis

Cite this

@article{d429c325f08049b0a631e00fa399e767,
title = "Deep-dose: a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry",
abstract = "Personalized dosimetry with high accuracy is crucial owing to the growing interests in personalized medicine. The direct Monte Carlo simulation is considered as a state-of-art voxel-based dosimetry technique; however, it incurs an excessive computational cost and time. To overcome the limitations of the direct Monte Carlo approach, we propose using a deep convolutional neural network (CNN) for the voxel dose prediction. PET and CT image patches were used as inputs for the CNN with the given ground truth from direct Monte Carlo. The predicted voxel dose rate maps from the CNN were compared with the ground truth and dose rate maps generated voxel S-value (VSV) kernel convolution method, which is one of the common voxel-based dosimetry techniques. The CNN-based dose rate map agreed well with the ground truth with voxel dose rate errors of 2.54{\%} ± 2.09{\%}. The VSV kernel approach showed a voxel error of 9.97{\%} ± 1.79{\%}. In the whole-body dosimetry study, the average organ absorbed dose errors were 1.07{\%}, 9.43{\%}, and 34.22{\%} for the CNN, VSV, and OLINDA/EXM dosimetry software, respectively. The proposed CNN-based dosimetry method showed improvements compared to the conventional dosimetry approaches and showed results comparable with that of the direct Monte Carlo simulation with significantly lower calculation time.",
author = "Lee, {Min Sun} and Donghwi Hwang and Kim, {Joong Hyun} and Lee, {Jae Sung}",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-46620-y",
language = "English",
volume = "9",
journal = "Scientific reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

Deep-dose : a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry. / Lee, Min Sun; Hwang, Donghwi; Kim, Joong Hyun; Lee, Jae Sung.

In: Scientific Reports, Vol. 9, No. 1, 10308, 01.12.2019.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Deep-dose

T2 - a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry

AU - Lee, Min Sun

AU - Hwang, Donghwi

AU - Kim, Joong Hyun

AU - Lee, Jae Sung

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Personalized dosimetry with high accuracy is crucial owing to the growing interests in personalized medicine. The direct Monte Carlo simulation is considered as a state-of-art voxel-based dosimetry technique; however, it incurs an excessive computational cost and time. To overcome the limitations of the direct Monte Carlo approach, we propose using a deep convolutional neural network (CNN) for the voxel dose prediction. PET and CT image patches were used as inputs for the CNN with the given ground truth from direct Monte Carlo. The predicted voxel dose rate maps from the CNN were compared with the ground truth and dose rate maps generated voxel S-value (VSV) kernel convolution method, which is one of the common voxel-based dosimetry techniques. The CNN-based dose rate map agreed well with the ground truth with voxel dose rate errors of 2.54% ± 2.09%. The VSV kernel approach showed a voxel error of 9.97% ± 1.79%. In the whole-body dosimetry study, the average organ absorbed dose errors were 1.07%, 9.43%, and 34.22% for the CNN, VSV, and OLINDA/EXM dosimetry software, respectively. The proposed CNN-based dosimetry method showed improvements compared to the conventional dosimetry approaches and showed results comparable with that of the direct Monte Carlo simulation with significantly lower calculation time.

AB - Personalized dosimetry with high accuracy is crucial owing to the growing interests in personalized medicine. The direct Monte Carlo simulation is considered as a state-of-art voxel-based dosimetry technique; however, it incurs an excessive computational cost and time. To overcome the limitations of the direct Monte Carlo approach, we propose using a deep convolutional neural network (CNN) for the voxel dose prediction. PET and CT image patches were used as inputs for the CNN with the given ground truth from direct Monte Carlo. The predicted voxel dose rate maps from the CNN were compared with the ground truth and dose rate maps generated voxel S-value (VSV) kernel convolution method, which is one of the common voxel-based dosimetry techniques. The CNN-based dose rate map agreed well with the ground truth with voxel dose rate errors of 2.54% ± 2.09%. The VSV kernel approach showed a voxel error of 9.97% ± 1.79%. In the whole-body dosimetry study, the average organ absorbed dose errors were 1.07%, 9.43%, and 34.22% for the CNN, VSV, and OLINDA/EXM dosimetry software, respectively. The proposed CNN-based dosimetry method showed improvements compared to the conventional dosimetry approaches and showed results comparable with that of the direct Monte Carlo simulation with significantly lower calculation time.

UR - http://www.scopus.com/inward/record.url?scp=85069454824&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-46620-y

DO - 10.1038/s41598-019-46620-y

M3 - Article

VL - 9

JO - Scientific reports

JF - Scientific reports

SN - 2045-2322

IS - 1

M1 - 10308

ER -