biostudies-literatureLee SBNational Research Foundation of Korea294-304https://www.ebi.ac.uk/biostudies/studies/S-EPMC10067697biostudies-literatureUnknown24(4)<h4>Objective</h4>We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods.<h4>Materials and methods</h4>We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. AKorean journal of radiologyDeep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation.PMC10067697NRF-2020R1F1A1077320Lee SCheon JEYoon SHHong YChoi YHCho YJJeong DLee JLee SBfalseDeep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation.<h4>Objective</h4>We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods.<h4>Materials and methods</h4>We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A2023-01-01T00:00:00Z2023 Apr2025-04-04T10:42:05.085Z2025-04-04T10:42:05.085ZS-EPMC100676973690759210.3348/kjr.2022.0588