Back to the list
Congress: ECR25
Poster Number: C-12869
Type: Poster: EPOS Radiographer (scientific)
Authorblock: S. Maruyama1, H. Saitou2; 1Maebashi, Gunma/JP, 2Itabashi, Tokyo/JP
Disclosures:
Sho Maruyama: Nothing to disclose
Hiroki Saitou: Nothing to disclose
Keywords: Computer applications, Digital radiography, Experimental investigations, Physics, Technology assessment, Quality assurance
Purpose Digital radiography (DR) is a widely used in clinical practice. The exposure dose per examination in DR is lower compared to other modalities, however, it is one of the factors contributing to integrated exposure of patients [1,2]. Therefore, reducing the exposure dose while maintaining diagnostic image quality of DR is a crucial task for technologists [3–6].The reduction of the imaging dose leads to an increase in quantum noise. Since image noise is an important factor affecting the accuracy of diagnostic...
Read more Methods and materials Imaging system and software for noise reduction The CXDI-720C (Canon Medical Systems) was used for image acquisition. The pixel size of the images was 0.125 × 0.125 mm, with a 2800 × 3408 matrix and 16-bit grayscale. X-ray exposure was performed using an X-ray system with a total filtration of 2.8 mm Al.For noise reduction processing, two methods available within this imaging system were used. One is a conventional rule-based approach (conventional noise reduction: Con-NR), and the other was a...
Read more Results NPSIF in uniform image conditionsFigures 4 and 5 show the results under ultra-low-dose conditions. The noise-reduction processing significantly improved image granularity, as demonstrated by an overall decrease in NPS values. Furthermore, evaluations based on NPSIF revealed that the noise reduction effect on uniform images was consistent across all spatial frequencies, with particularly strong improvements observed under the INR10 condition. [fig 4] [fig 5]  Figures 6 and 7 show the results under moderate-low-dose conditions. The trends of NPS and NPSIF were similar to those for the...
Read more Conclusion The INR algorithms using deep-learning demonstrated particularly notable improvements in NPS under low-dose conditions, while its effect tended to be smaller under high-dose conditions. This behavior is considered to mean that the performance of deep learning model depends on the training images, suggesting that the noise characteristics inherent in the training data define the upper limit of noise improvement. NPSIF, which quantitatively evaluates the effects of image processing for each spatial frequency, offers a more detailed and intuitive characterization of noise...
Read more References ICRP Publication 93. Ann ICRP. 34(1), 2004. ICRP Publication 135. Ann ICRP. 46(1), 2017. Samei E. et al. Radiat Prot Dosim. 2005;114:220–229. Samei E. et al. Radiology. 2008;249(3):926–937. AAPM Report No. 233. The Report of AAPM Task Group 233, 2019. ICRP Publication 154. Ann ICRP. 52(3), 2023. Yalcin A, et al. Med Phys. 2020;47(9):3935–3944. Chandra TB, et al. Measurement. 2020;153:107426. Oh S, et al. Eur Radiol. 2021;31:8937–8946. Lee W, et al. PLOS ONE. 2020;15(2):e0228609. Johnson J. Technical White Paper of Canon Medical Components. 2023. Ice J, et al. Clinical White Paper...
Read more
GALLERY