Prediction of body weight from chest radiographs using deep learning with a convolutional neural network

Ichikawa, Shota; Itadani, Hideki; Sugimori, Hiroyuki

doi:10.1007/s12194-023-00697-3

Cited by 6 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

“…Body weight estimation from medical images using deep learning has been performed on the chest and abdominal CT scout images, 20 chest radiographs, 21 and head CT scout images. 22 Previous studies using chest and abdominal CT scout images and chest radiographs showed high accuracy with MAEs <5 kg, 20,21 which was superior in accuracy to that in the present study using axial CT images. Although it is not an easy comparison because of differences in the subjects and size of the training data, the possible reason for these findings is that CT scout images and chest radiographs have x-ray attenuation information over a certain range in the direction of the body's z axis, whereas axial CT images have information only over an extremely narrow cross-sectional range.…”

Section: Discussionmentioning

confidence: 99%

“…As noted in previous studies, 20,21 estimating body weight from scout images or chest radiographs rather than axial images is advantageous because radiologists and radiological technologists can obtain the patient's body weight before the CT scan, allowing them to determine the contrast medium dose without a noncontrast CT and to provide the body weight to the CT scanner during patient registration. However, estimation from scout images using deep learning is sensitive to off-center patient positioning, which is a common procedural error.…”

Section: Discussionmentioning

confidence: 99%

“…Supervised learning based on the Visual Geometry Group 16 (VGG16) architecture 24 was performed using axial CT images as input data and the corresponding body weight as reference data, since this network has been successful in accurately estimating body weight from medical images. 20,21 According to the previously proposed method, 21 the final layers of the original VGG16 model were replaced as follows: (1) a linear layer with an output size of 512, (2) a rectified linear unit function, (3) dropout (dropout rate, 0.4), and (4) a linear layer with an output size of 1. All images fed into the network were normalized using ImageNet scene statistics (mean = [0.485, 0.456, 0.406], standard deviation = [0.229, 0.224, 0.225]).…”

Section: Deep Learning-based Modelmentioning

confidence: 99%

“…The first approach was to apply the linear regression model using the total cross-sectional body area measured by threshold-based techniques as an input variable. Motivated by the recent prominent results of deep learning in estimating body weight from medical images, [20][21][22] the second approach was to estimate body weight directly from axial CT images using deep learning techniques. The purpose of this study was 2-fold: to evaluate the correlation between the estimated body weight from the 2 easy-to-perform methods and the actual body weight at different slice levels and to determine the best reference site for a single-slice CT analysis for estimating body weight.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Estimating Body Weight From Measurements From Different Single-Slice Computed Tomography Levels: An Evaluation of Total Cross-Sectional Body Area Measurements and Deep Learning

Ichikawa,

Sugimori

2024

J Comput Assist Tomogr

Self Cite

View full text Add to dashboard Cite

Objective This study aimed to evaluate the correlation between the estimated body weight obtained from 2 easy-to-perform methods and the actual body weight at different computed tomography (CT) levels and determine the best reference site for estimating body weight. Methods A total of 862 patients from a public database of whole-body positron emission tomography/CT studies were retrospectively analyzed. Two methods for estimating body weight at 10 single-slice CT levels were evaluated: a linear regression model using total cross-sectional body area and a deep learning–based model. The accuracy of body weight estimation was evaluated using the mean absolute error (MAE), root mean square error (RMSE), and Spearman rank correlation coefficient (ρ). Results In the linear regression models, the estimated body weight at the T5 level correlated best with the actual body weight (MAE, 5.39 kg; RMSE, 7.01 kg; ρ = 0.912). The deep learning–based models showed the best accuracy at the L5 level (MAE, 6.72 kg; RMSE, 8.82 kg; ρ = 0.865). Conclusions Although both methods were feasible for estimating body weight at different single-slice CT levels, the linear regression model using total cross-sectional body area at the T5 level as an input variable was the most favorable method for single-slice CT analysis for estimating body weight.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Deep Learning-based Modelmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Estimating Body Weight From Measurements From Different Single-Slice Computed Tomography Levels: An Evaluation of Total Cross-Sectional Body Area Measurements and Deep Learning

Ichikawa,

Sugimori

2024

J Comput Assist Tomogr

Self Cite

View full text Add to dashboard Cite

show abstract

Machine learning‐based estimation of patient body weight from radiation dose metrics in computed tomography

Ichikawa,

Sawane

2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

PurposeCurrently, precise patient body weight (BW) at the time of diagnostic imaging cannot always be used for radiation dose management. Various methods have been explored to address this issue, including the application of deep learning to medical imaging and BW estimation using scan parameters. This study develops and evaluates machine learning‐based BW prediction models using 11 features related to radiation dose obtained from computed tomography (CT) scans.MethodsA dataset was obtained from 3996 patients who underwent positron emission tomography CT scans, and training and test sets were established. Dose metrics and descriptive data were automatically calculated from the CT images or obtained from Digital Imaging and Communications in Medicine metadata. Seven machine‐learning models and three simple regression models were employed to predict BW using features such as effective diameter (ED), water equivalent diameter (WED), and mean milliampere‐seconds. The mean absolute error (MAE) and correlation coefficient between the estimated BW and the actual BW obtained from each BW prediction model were calculated.ResultsOur results found that the highest accuracy was obtained using a light gradient‐boosting machine model, which had an MAE of 1.99 kg and a strong positive correlation between estimated and actual BW (ρ = 0.972). The model demonstrated significant predictive power, with 73% of patients falling within a ±5% error range. WED emerged as the most relevant dose metric for BW estimation, followed by ED and sex.ConclusionsThe proposed machine‐learning approach is superior to existing methods, with high accuracy and applicability to radiation dose management. The model's reliance on universal dose metrics that are accessible through radiation dose management software enhances its practicality. In conclusion, this study presents a robust approach for BW estimation based on CT imaging that can potentially improve radiation dose management practices in clinical settings.

show abstract

Deep learning-based computed tomography assessment for lung function prediction in chronic obstructive pulmonary disease

Shimizu,

Sugimori,

Tanabe

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning models based on medical imaging enable numerical functional predictions in combination with regression methods. In this study, we evaluate the prediction performance of a deep learning-based model for the raw value and percent predicted forced expiratory volume in one second (FEV1) in patients with chronic obstructive pulmonary disease (COPD). To this end, ResNet50-based regression prediction models were constructed for FEV1 and %FEV1 based on 200 CT scans. 10-fold cross-validation was performed to yield ten models in aggregate. The prediction model for %FEV1 was externally validated using 20 data points. Two hundred internal CT datasets were assessed using commercial software, producing a regression model predicting airway [%WA] and parenchymal indices [%LAV]. The average Root Mean Squared Error(RMSE) value of the 10 predictive models was 627.65 for FEV1 as per internal validation and 15.34 for %FEV1. The externally validated RMSE for %FEV1 was 11.52, whereas that for %FEV1 was 23.18. The predictive model for %FEV1 yielded significant positive correlations corresponding to both internal and external validation. The proposed models exhibited better prediction accuracy for %FEV1 than for FEV1. Further studies are required to improve the accuracy further and determine the validity of longitudinal applications.

show abstract

Prediction of body weight from chest radiographs using deep learning with a convolutional neural network

Cited by 6 publications

References 21 publications

Estimating Body Weight From Measurements From Different Single-Slice Computed Tomography Levels: An Evaluation of Total Cross-Sectional Body Area Measurements and Deep Learning

Estimating Body Weight From Measurements From Different Single-Slice Computed Tomography Levels: An Evaluation of Total Cross-Sectional Body Area Measurements and Deep Learning

Machine learning‐based estimation of patient body weight from radiation dose metrics in computed tomography

Deep learning-based computed tomography assessment for lung function prediction in chronic obstructive pulmonary disease

Contact Info

Product

Resources

About