Kyle Hasenstab1,2, Guilherme Moura Cunha3, Shintaro Ichikawa4, Soudabeh Fazeli Dehkordy3, Min Hee Lee5, Soo Jin Kim6, Alexandra Schlein3, Yesenia Covarrubias3, Claude B Sirlin3, Kathryn J Fowler3. 1. Liver Imaging Group, Department of Radiology, University of California, San Diego, La Jolla, CA, USA. kylehasenstab@gmail.com. 2. Department of Mathematics and Statistics, San Diego State University, San Diego, CA, USA. kylehasenstab@gmail.com. 3. Liver Imaging Group, Department of Radiology, University of California, San Diego, La Jolla, CA, USA. 4. Department of Radiology, University of Yamanashi, Yamanashi, Japan. 5. Soonchunhyang University Bucheon Hospital, Gyeonggi-do, South Korea. 6. National Cancer Center, Republic of Korea, Gyeonggi-do, South Korea.
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 cm2 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.
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 cm2 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.
Authors: Daniel C Sullivan; Nancy A Obuchowski; Larry G Kessler; David L Raunig; Constantine Gatsonis; Erich P Huang; Marina Kondratovich; Lisa M McShane; Anthony P Reeves; Daniel P Barboriak; Alexander R Guimaraes; Richard L Wahl Journal: Radiology Date: 2015-08-12 Impact factor: 11.105
Authors: Paul A Yushkevich; Joseph Piven; Heather Cody Hazlett; Rachel Gimpel Smith; Sean Ho; James C Gee; Guido Gerig Journal: Neuroimage Date: 2006-03-20 Impact factor: 6.556
Authors: Camilo A Campo; Diego Hernando; Tilman Schubert; Candice A Bookwalter; Andrew J Van Pay; Scott B Reeder Journal: AJR Am J Roentgenol Date: 2017-07-13 Impact factor: 3.959
Authors: Susanne Bonekamp; An Tang; Arian Mashhood; Tanya Wolfson; Christopher Changchien; Michael S Middleton; Lisa Clark; Anthony Gamst; Rohit Loomba; Claude B Sirlin Journal: J Magn Reson Imaging Date: 2014-06 Impact factor: 4.813
Authors: Michael S Middleton; Elhamy R Heba; Catherine A Hooker; Mustafa R Bashir; Kathryn J Fowler; Kumar Sandrasegaran; Elizabeth M Brunt; David E Kleiner; Edward Doo; Mark L Van Natta; Joel E Lavine; Brent A Neuschwander-Tetri; Arun Sanyal; Rohit Loomba; Claude B Sirlin Journal: Gastroenterology Date: 2017-06-15 Impact factor: 22.682
Authors: Jonathan C Hooker; Gavin Hamilton; Charlie C Park; Steven Liao; Tanya Wolfson; Soudabeh Fazeli Dehkordy; Cheng William Hong; Adrija Mamidipalli; Anthony Gamst; Rohit Loomba; Claude B Sirlin Journal: Abdom Radiol (NY) Date: 2019-02
Authors: Soudabeh Fazeli Dehkordy; Kathryn J Fowler; Adrija Mamidipalli; Tanya Wolfson; Cheng William Hong; Yesenia Covarrubias; Jonathan C Hooker; Ethan Z Sy; Alexandra N Schlein; Jennifer Y Cui; Anthony C Gamst; Gavin Hamilton; Scott B Reeder; Claude B Sirlin Journal: Eur Radiol Date: 2018-12-13 Impact factor: 5.315
Authors: Maria Reig; Martina Gambato; Nancy Kwan Man; John P Roberts; David Victor; Lorenzo A Orci; Christian Toso Journal: Transplantation Date: 2019-01 Impact factor: 4.939
Authors: Kyle A Hasenstab; Guilherme Moura Cunha; Atsushi Higaki; Shintaro Ichikawa; Kang Wang; Timo Delgado; Ryan L Brunsing; Alexandra Schlein; Leornado Kayat Bittencourt; Armin Schwartzman; Katie J Fowler; Albert Hsiao; Claude B Sirlin Journal: Eur Radiol Exp Date: 2019-10-26