A deep-learning method using computed tomography scout images for estimating patient body weight
Abstract Body weight is an indispensable parameter for determination of contrast medium dose, appropriate drug dosing, or management of radiation dose. However, we cannot always determine the accurate patient body weight at the time of computed tomography (CT) scanning, especially in emergency care....
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-08-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-021-95170-9 |
id |
doaj-5494661527bf4f8593b4bd0b539078cd |
---|---|
record_format |
Article |
spelling |
doaj-5494661527bf4f8593b4bd0b539078cd2021-08-08T11:26:48ZengNature Publishing GroupScientific Reports2045-23222021-08-011111910.1038/s41598-021-95170-9A deep-learning method using computed tomography scout images for estimating patient body weightShota Ichikawa0Misaki Hamada1Hiroyuki Sugimori2Graduate School of Health Sciences, Hokkaido UniversityDepartment of Radiological Technology, Kurashiki Central HospitalFaculty of Health Sciences, Hokkaido UniversityAbstract Body weight is an indispensable parameter for determination of contrast medium dose, appropriate drug dosing, or management of radiation dose. However, we cannot always determine the accurate patient body weight at the time of computed tomography (CT) scanning, especially in emergency care. Time-efficient methods to estimate body weight with high accuracy before diagnostic CT scans currently do not exist. In this study, on the basis of 1831 chest and 519 abdominal CT scout images with the corresponding body weights, we developed and evaluated deep-learning models capable of automatically predicting body weight from CT scout images. In the model performance assessment, there were strong correlations between the actual and predicted body weights in both chest (ρ = 0.947, p < 0.001) and abdominal datasets (ρ = 0.869, p < 0.001). The mean absolute errors were 2.75 kg and 4.77 kg for the chest and abdominal datasets, respectively. Our proposed method with deep learning is useful for estimating body weights from CT scout images with clinically acceptable accuracy and potentially could be useful for determining the contrast medium dose and CT dose management in adult patients with unknown body weight.https://doi.org/10.1038/s41598-021-95170-9 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shota Ichikawa Misaki Hamada Hiroyuki Sugimori |
spellingShingle |
Shota Ichikawa Misaki Hamada Hiroyuki Sugimori A deep-learning method using computed tomography scout images for estimating patient body weight Scientific Reports |
author_facet |
Shota Ichikawa Misaki Hamada Hiroyuki Sugimori |
author_sort |
Shota Ichikawa |
title |
A deep-learning method using computed tomography scout images for estimating patient body weight |
title_short |
A deep-learning method using computed tomography scout images for estimating patient body weight |
title_full |
A deep-learning method using computed tomography scout images for estimating patient body weight |
title_fullStr |
A deep-learning method using computed tomography scout images for estimating patient body weight |
title_full_unstemmed |
A deep-learning method using computed tomography scout images for estimating patient body weight |
title_sort |
deep-learning method using computed tomography scout images for estimating patient body weight |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2021-08-01 |
description |
Abstract Body weight is an indispensable parameter for determination of contrast medium dose, appropriate drug dosing, or management of radiation dose. However, we cannot always determine the accurate patient body weight at the time of computed tomography (CT) scanning, especially in emergency care. Time-efficient methods to estimate body weight with high accuracy before diagnostic CT scans currently do not exist. In this study, on the basis of 1831 chest and 519 abdominal CT scout images with the corresponding body weights, we developed and evaluated deep-learning models capable of automatically predicting body weight from CT scout images. In the model performance assessment, there were strong correlations between the actual and predicted body weights in both chest (ρ = 0.947, p < 0.001) and abdominal datasets (ρ = 0.869, p < 0.001). The mean absolute errors were 2.75 kg and 4.77 kg for the chest and abdominal datasets, respectively. Our proposed method with deep learning is useful for estimating body weights from CT scout images with clinically acceptable accuracy and potentially could be useful for determining the contrast medium dose and CT dose management in adult patients with unknown body weight. |
url |
https://doi.org/10.1038/s41598-021-95170-9 |
work_keys_str_mv |
AT shotaichikawa adeeplearningmethodusingcomputedtomographyscoutimagesforestimatingpatientbodyweight AT misakihamada adeeplearningmethodusingcomputedtomographyscoutimagesforestimatingpatientbodyweight AT hiroyukisugimori adeeplearningmethodusingcomputedtomographyscoutimagesforestimatingpatientbodyweight AT shotaichikawa deeplearningmethodusingcomputedtomographyscoutimagesforestimatingpatientbodyweight AT misakihamada deeplearningmethodusingcomputedtomographyscoutimagesforestimatingpatientbodyweight AT hiroyukisugimori deeplearningmethodusingcomputedtomographyscoutimagesforestimatingpatientbodyweight |
_version_ |
1721215944459550720 |