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. 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.

An artificial intelligence system for predicting body weight from chest radiographs

“…This approach showed a strong correlation (r = 0.969) between the measured and predicted body weights, but it is limited to polytrauma patients who undergo whole-body CT scans. Recently, body-weight prediction using deep learning from chest CT scout images showed an MAE of 2.75 kg and a strong correlation (ρ = 0.947) between the actual and predicted body weights; however, the overweight cases tended to be underestimated because of the limited number of training sets [9].…”

“…The arti cial intelligence (AI)-based approach has shown many encouraging results in medical imaging analysis. Particularly, a convolutional neural network (CNN) can achieve excellent predictions [9][10][11][12]. The use of CNN to predict body weight from chest and abdominal CT scout images has also been shown [9].…”

“…Particularly, a convolutional neural network (CNN) can achieve excellent predictions [9][10][11][12]. The use of CNN to predict body weight from chest and abdominal CT scout images has also been shown [9].…”

X-ray Dissectography Improves Lung Nodule Detection

“…Before performing a typical CT scan, 2D scout views, also konwn as topograms or planning radiographs, are initially obtained for prescribing CT slices and modulating x-ray tube current for dose reduction. Radiologists have found that planning radiogaphs carry significant diagnostic information (1)(2)(3)(4), although they have limited information compared to radiography and CT. These X-ray imaging modes have their strengths and weaknesses.…”

Design and Development of Smart Weight Measurement, Lateral Turning and Transfer Bedding for Unconscious Patients in Pandemics

“…Bodyweight fluctuations are important indications for a range of medical disorders, and in some cases, such as congestive heart failure, they are key determinants of intensive care measures [ 1 ]. Many doctors and medical professionals require patient weight for various diagnostic procedures and prescription of medication or diet [ 2 ]. Bodyweight, as well as weight change, is particularly important for critically sick patients hospitalized in intensive care units (ICUs), since it is a direct measure of fluid balance effectiveness and general health.…”