Bayesian reconstruction algorithms for low-dose computed tomography are not yet suitable in clinical context
Standard
Bayesian reconstruction algorithms for low-dose computed tomography are not yet suitable in clinical context. / Kniep, Inga; Mieling, Robin; Gerling, Moritz; Schlaefer, Alexander; Heinemann, Axel; Ondruschka, Benjamin.
In: J IMAGING, Vol. 9, No. 9, 170, 23.08.2023.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Bayesian reconstruction algorithms for low-dose computed tomography are not yet suitable in clinical context
AU - Kniep, Inga
AU - Mieling, Robin
AU - Gerling, Moritz
AU - Schlaefer, Alexander
AU - Heinemann, Axel
AU - Ondruschka, Benjamin
PY - 2023/8/23
Y1 - 2023/8/23
N2 - Computed tomography (CT) is a widely used examination technique that usually requires a compromise between image quality and radiation exposure. Reconstruction algorithms aim to reduce radiation exposure while maintaining comparable image quality. Recently, unsupervised deep learning methods have been proposed for this purpose. In this study, a promising sparse-view reconstruction method (posterior temperature optimized Bayesian inverse model; POTOBIM) is tested for its clinical applicability. For this study, 17 whole-body CTs of deceased were performed. In addition to POTOBIM, reconstruction was performed using filtered back projection (FBP). An evaluation was conducted by simulating sinograms and comparing the reconstruction with the original CT slice for each case. A quantitative analysis was performed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). The quality was assessed visually using a modified Ludewig’s scale. In the qualitative evaluation, POTOBIM was rated worse than the reference images in most cases. A partially equivalent image quality could only be achieved with 80 projections per rotation. Quantitatively, POTOBIM does not seem to benefit from more than 60 projections. Although deep learning methods seem suitable to produce better image quality, the investigated algorithm (POTOBIM) is not yet suitable for clinical routine.
AB - Computed tomography (CT) is a widely used examination technique that usually requires a compromise between image quality and radiation exposure. Reconstruction algorithms aim to reduce radiation exposure while maintaining comparable image quality. Recently, unsupervised deep learning methods have been proposed for this purpose. In this study, a promising sparse-view reconstruction method (posterior temperature optimized Bayesian inverse model; POTOBIM) is tested for its clinical applicability. For this study, 17 whole-body CTs of deceased were performed. In addition to POTOBIM, reconstruction was performed using filtered back projection (FBP). An evaluation was conducted by simulating sinograms and comparing the reconstruction with the original CT slice for each case. A quantitative analysis was performed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). The quality was assessed visually using a modified Ludewig’s scale. In the qualitative evaluation, POTOBIM was rated worse than the reference images in most cases. A partially equivalent image quality could only be achieved with 80 projections per rotation. Quantitatively, POTOBIM does not seem to benefit from more than 60 projections. Although deep learning methods seem suitable to produce better image quality, the investigated algorithm (POTOBIM) is not yet suitable for clinical routine.
U2 - 10.3390/jimaging9090170
DO - 10.3390/jimaging9090170
M3 - SCORING: Journal article
VL - 9
JO - J IMAGING
JF - J IMAGING
SN - 2313-433X
IS - 9
M1 - 170
ER -