CNN color-coded difference maps accurately display longitudinal changes in liver MRI-PDFF
- Authors
- Hasenstab, Kyle; Cunha, Guilherme Moura; Ichikawa, Shintaro; Dehkordy, Soudabeh Fazeli; Lee, Min Hee; Kim, Soo Jin; Schlein, Alexandra; Covarrubias, Yesenia; Sirlin, Claude B.; Fowler, Kathryn J.
- Issue Date
- Jul-2021
- Publisher
- Springer Verlag
- Keywords
- Liver; Magnetic resonance imaging; Neural networks, computer; Image interpretation, computer-assisted
- Citation
- European Radiology, v.31, no.7, pp 5041 - 5049
- Pages
- 9
- Journal Title
- European Radiology
- Volume
- 31
- Number
- 7
- Start Page
- 5041
- End Page
- 5049
- URI
- https://scholarworks.bwise.kr/sch/handle/2021.sw.sch/18752
- DOI
- 10.1007/s00330-020-07649-0
- ISSN
- 0938-7994
1432-1084
- Abstract
- Objectives To assess the feasibility of a CNN-based liver registration algorithm to generate difference maps for visual display of spatiotemporal changes in liver PDFF, without needing manual annotations. Methods This retrospective exploratory study included 25 patients with suspected or confirmed NAFLD, who underwent PDFF-MRI at two time points at our institution. PDFF difference maps were generated by applying a CNN-based liver registration algorithm, then subtracting follow-up from baseline PDFF maps. The difference maps were post-processed by smoothing (5 cm(2) round kernel) and applying a categorical color scale. Two fellowship-trained abdominal radiologists and one radiology resident independently reviewed difference maps to visually determine segmental PDFF change. Their visual assessment was compared with manual ROI-based measurements of each Couinaud segment and whole liver PDFF using intraclass correlation (ICC) and Bland-Altman analysis. Inter-reader agreement for visual assessment was calculated (ICC). Results The mean patient age was 49 years (12 males). Baseline and follow-up PDFF ranged from 2.0 to 35.3% and 3.5 to 32.0%, respectively. PDFF changes ranged from - 20.4 to 14.1%. ICCs against the manual reference exceeded 0.95 for each reader, except for segment 2 (2 readers ICC = 0.86-0.91) and segment 4a (reader 3 ICC = 0.94). Bland-Altman limits of agreement were within 5% across all three readers. Inter-reader agreement for visually assessed PDFF change (whole liver and segmental) was excellent (ICCs > 0.96), except for segment 2 (ICC = 0.93). Conclusions Visual assessment of liver segmental PDFF changes using a CNN-generated difference map strongly agreed with manual estimates performed by an expert reader and yielded high inter-reader agreement. Key Points Visual assessment of longitudinal changes in quantitative liver MRI can be performed using a CNN-generated difference map and yields strong agreement with manual estimates performed by expert readers.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Medicine > Department of Radiology > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.