TY - JOUR
T1 - Radiation dose reduction using deep learning-based image reconstruction for a low-dose chest computed tomography protocol
T2 - a phantom study
AU - Jung, Yunsub
AU - Hur, Jin
AU - Han, Kyunghwa
AU - Imai, Yasuhiro
AU - Hong, Yoo Jin
AU - Im, Dong Jin
AU - Lee, Kye Ho
AU - Desnoyers, Melissa
AU - Thomsen, Brian
AU - Shigemasa, Risa
AU - Um, Kyounga
AU - Jang, Kyungeun
N1 - 2023 Quantitative Imaging in Medicine and Surgery. All rights reserved.
PY - 2023/3
Y1 - 2023/3
N2 - Background: The aim of this study was to compare the dose reduction potential and image quality of deep learning-based image reconstruction (DLIR) with those of filtered back-projection (FBP) and iterative reconstruction (IR) and to determine the clinically usable dose of DLIR for low-dose chest computed tomography (LDCT) scans. Methods: Multi-slice computed tomography (CT) scans of a chest phantom were performed with various tube voltages and tube currents, and the images were reconstructed using seven methods to control the amount of noise reduction: FBP, three stages of IR, and three stages of DLIR. For subjective image analysis, four radiologists compared 48 image data sets with reference images and rated on a 5-point scale. For quantitative image analysis, the signal to noise ratio (SNR), contrast to noise ratio (CNR), nodule volume, and nodule diameter were measured. Results: In the subjective analysis, DLIR-Low (0.46 mGy), DLIR-Medium (0.31 mGy), and DLIR-High (0.18 mGy) images showed similar quality to the FBP (2.47 mGy) image. Under the same dose conditions, the SNR and CNR were higher with DLIR-High than with FBP and all the IR methods (all P<0.05). The nodule volume and size with DLIR-High were significantly closer to the real volume than with FBP and all the IR methods (all P<0.001). Conclusions: DLIR can improve the image quality of LDCT compared to FBP and IR. In addition, the appropriate effective dose for LDCT would be 0.24 mGy with DLIR-High.
AB - Background: The aim of this study was to compare the dose reduction potential and image quality of deep learning-based image reconstruction (DLIR) with those of filtered back-projection (FBP) and iterative reconstruction (IR) and to determine the clinically usable dose of DLIR for low-dose chest computed tomography (LDCT) scans. Methods: Multi-slice computed tomography (CT) scans of a chest phantom were performed with various tube voltages and tube currents, and the images were reconstructed using seven methods to control the amount of noise reduction: FBP, three stages of IR, and three stages of DLIR. For subjective image analysis, four radiologists compared 48 image data sets with reference images and rated on a 5-point scale. For quantitative image analysis, the signal to noise ratio (SNR), contrast to noise ratio (CNR), nodule volume, and nodule diameter were measured. Results: In the subjective analysis, DLIR-Low (0.46 mGy), DLIR-Medium (0.31 mGy), and DLIR-High (0.18 mGy) images showed similar quality to the FBP (2.47 mGy) image. Under the same dose conditions, the SNR and CNR were higher with DLIR-High than with FBP and all the IR methods (all P<0.05). The nodule volume and size with DLIR-High were significantly closer to the real volume than with FBP and all the IR methods (all P<0.001). Conclusions: DLIR can improve the image quality of LDCT compared to FBP and IR. In addition, the appropriate effective dose for LDCT would be 0.24 mGy with DLIR-High.
KW - chest phantom
KW - deep learning-based image reconstruction (DLIR)
KW - Low-dose chest computed tomography (LDCT)
UR - http://www.scopus.com/inward/record.url?scp=85149026661&partnerID=8YFLogxK
U2 - 10.21037/qims-22-618
DO - 10.21037/qims-22-618
M3 - Journal article
C2 - 36915339
AN - SCOPUS:85149026661
SN - 2223-4292
VL - 13
SP - 1937
EP - 1947
JO - Quantitative Imaging in Medicine and Surgery
JF - Quantitative Imaging in Medicine and Surgery
IS - 3
ER -