Your browser doesn't support javascript.
loading
Deep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation.
Lee, Seul Bi; Hong, Youngtaek; Cho, Yeon Jin; Jeong, Dawun; Lee, Jina; Yoon, Soon Ho; Lee, Seunghyun; Choi, Young Hun; Cheon, Jung-Eun.
Affiliation
  • Lee SB; Department of Radiology, Seoul National University Hospital, Seoul, Korea.
  • Hong Y; Department of Radiology, Seoul National University College of Medicine, Seoul, Korea.
  • Cho YJ; CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul, Korea.
  • Jeong D; Department of Radiology, Seoul National University Hospital, Seoul, Korea.
  • Lee J; Department of Radiology, Seoul National University College of Medicine, Seoul, Korea. blue1010c@gmail.com.
  • Yoon SH; CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul, Korea.
  • Lee S; Brain Korea 21 PLUS Project for Medical Science, Yonsei University, Seoul, Korea.
  • Choi YH; CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul, Korea.
  • Cheon JE; Brain Korea 21 PLUS Project for Medical Science, Yonsei University, Seoul, Korea.
Korean J Radiol ; 24(4): 294-304, 2023 04.
Article in En | MEDLINE | ID: mdl-36907592
OBJECTIVE: 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. MATERIALS AND METHODS: 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. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. RESULTS: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). CONCLUSION: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.
Subject(s)
Key words

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Deep Learning Limits: Child / Humans Language: En Journal: Korean J Radiol Journal subject: RADIOLOGIA Year: 2023 Document type: Article Country of publication: Korea (South)

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Deep Learning Limits: Child / Humans Language: En Journal: Korean J Radiol Journal subject: RADIOLOGIA Year: 2023 Document type: Article Country of publication: Korea (South)