Sundaresh Ram1,2, Benjamin A Hoff1, Alexander J Bell1, Stefanie Galban1, Aleksa B Fortuna1, Oliver Weinheimer3,4, Mark O Wielpütz3,4, Terry E Robinson5, Beverley Newman6, Dharshan Vummidi1, Aamer Chughtai1, Ella A Kazerooni1,7, Timothy D Johnson8, MeiLan K Han7, Charles R Hatt1,9, Craig J Galban1,2. 1. Department of Radiology, Michigan Medicine, University of Michigan, Ann Arbor, Michigan, United States of America. 2. Department of Biomedical Engineering, Michigan Medicine, University of Michigan, Ann Arbor, Michigan, United States of America. 3. Department of Diagnostic and Interventional Radiology, University Hospital of Heidelberg, Heidelberg, Germany. 4. Translational Lung Research Center, Heidelberg (TLRC), German Lung Research Center (DZL), Heidelberg, Germany. 5. Department of Pediatrics, Center of Excellence in Pulmonary Biology, Stanford University School of Medicine, Stanford, California, United States of America. 6. Department of Pediatric Radiology, Lucile Packard Children's Hospital at Stanford, Stanford, California, United States of America. 7. Department of Internal Medicine, Michigan Medicine, University of Michigan, Ann Arbor, Michigan, United States of America. 8. Department of Biostatistics, University of Michigan, School of Public Health, Ann Arbor, Michigan, United States of America. 9. Imbio LLC, Minneapolis, Minnesota, United States of America.
Abstract
BACKGROUND: Radiologic evidence of air trapping (AT) on expiratory computed tomography (CT) scans is associated with early pulmonary dysfunction in patients with cystic fibrosis (CF). However, standard techniques for quantitative assessment of AT are highly variable, resulting in limited efficacy for monitoring disease progression. OBJECTIVE: To investigate the effectiveness of a convolutional neural network (CNN) model for quantifying and monitoring AT, and to compare it with other quantitative AT measures obtained from threshold-based techniques. MATERIALS AND METHODS: Paired volumetric whole lung inspiratory and expiratory CT scans were obtained at four time points (0, 3, 12 and 24 months) on 36 subjects with mild CF lung disease. A densely connected CNN (DN) was trained using AT segmentation maps generated from a personalized threshold-based method (PTM). Quantitative AT (QAT) values, presented as the relative volume of AT over the lungs, from the DN approach were compared to QAT values from the PTM method. Radiographic assessment, spirometric measures, and clinical scores were correlated to the DN QAT values using a linear mixed effects model. RESULTS: QAT values from the DN were found to increase from 8.65% ± 1.38% to 21.38% ± 1.82%, respectively, over a two-year period. Comparison of CNN model results to intensity-based measures demonstrated a systematic drop in the Dice coefficient over time (decreased from 0.86 ± 0.03 to 0.45 ± 0.04). The trends observed in DN QAT values were consistent with clinical scores for AT, bronchiectasis, and mucus plugging. In addition, the DN approach was found to be less susceptible to variations in expiratory deflation levels than the threshold-based approach. CONCLUSION: The CNN model effectively delineated AT on expiratory CT scans, which provides an automated and objective approach for assessing and monitoring AT in CF patients.
BACKGROUND: Radiologic evidence of air trapping (AT) on expiratory computed tomography (CT) scans is associated with early pulmonary dysfunction in patients with cystic fibrosis (CF). However, standard techniques for quantitative assessment of AT are highly variable, resulting in limited efficacy for monitoring disease progression. OBJECTIVE: To investigate the effectiveness of a convolutional neural network (CNN) model for quantifying and monitoring AT, and to compare it with other quantitative AT measures obtained from threshold-based techniques. MATERIALS AND METHODS: Paired volumetric whole lung inspiratory and expiratory CT scans were obtained at four time points (0, 3, 12 and 24 months) on 36 subjects with mild CF lung disease. A densely connected CNN (DN) was trained using AT segmentation maps generated from a personalized threshold-based method (PTM). Quantitative AT (QAT) values, presented as the relative volume of AT over the lungs, from the DN approach were compared to QAT values from the PTM method. Radiographic assessment, spirometric measures, and clinical scores were correlated to the DN QAT values using a linear mixed effects model. RESULTS: QAT values from the DN were found to increase from 8.65% ± 1.38% to 21.38% ± 1.82%, respectively, over a two-year period. Comparison of CNN model results to intensity-based measures demonstrated a systematic drop in the Dice coefficient over time (decreased from 0.86 ± 0.03 to 0.45 ± 0.04). The trends observed in DN QAT values were consistent with clinical scores for AT, bronchiectasis, and mucus plugging. In addition, the DN approach was found to be less susceptible to variations in expiratory deflation levels than the threshold-based approach. CONCLUSION: The CNN model effectively delineated AT on expiratory CT scans, which provides an automated and objective approach for assessing and monitoring AT in CF patients.
Authors: T E Robinson; A N Leung; R B Moss; F G Blankenberg; H al-Dabbagh; W H Northway Journal: AJR Am J Roentgenol Date: 1999-06 Impact factor: 3.959
Authors: Stefan Klein; Marius Staring; Keelin Murphy; Max A Viergever; Josien P W Pluim Journal: IEEE Trans Med Imaging Date: 2009-11-17 Impact factor: 10.048
Authors: Wassim W Labaki; Carlos H Martinez; Fernando J Martinez; Craig J Galbán; Brian D Ross; George R Washko; R Graham Barr; Elizabeth A Regan; Harvey O Coxson; Eric A Hoffman; John D Newell; Douglas Curran-Everett; James C Hogg; James D Crapo; David A Lynch; Ella A Kazerooni; MeiLan K Han Journal: Am J Respir Crit Care Med Date: 2017-12-01 Impact factor: 21.405
Authors: Elizabeth A Belloli; Irina Degtiar; Xin Wang; Gregory A Yanik; Linda J Stuckey; Stijn E Verleden; Ella A Kazerooni; Brian D Ross; Susan Murray; Craig J Galbán; Vibha N Lama Journal: Am J Respir Crit Care Med Date: 2017-04-01 Impact factor: 21.405
Authors: Oliver Weinheimer; Benjamin A Hoff; Aleksa B Fortuna; Antonio Fernández-Baldera; Philip Konietzke; Mark O Wielpütz; Terry E Robinson; Craig J Galbán Journal: Acad Radiol Date: 2018-12-10 Impact factor: 3.173
Authors: Ilse M Boudewijn; Dirkje S Postma; Eef D Telenga; Nick H T Ten Hacken; Wim Timens; Matthijs Oudkerk; Brian D Ross; Craig J Galbán; Maarten van den Berge Journal: Eur Respir J Date: 2015-06-25 Impact factor: 16.671
Authors: Terry E Robinson; Frederick R Long; Pavi Raman; Paramita Saha; M J Emond; Joseph M Reinhardt; Raghav Raman; Alan S Brody Journal: Acad Radiol Date: 2009-05-24 Impact factor: 3.173
Authors: Tara A Retson; Kyle A Hasenstab; Seth J Kligerman; Kathleen E Jacobs; Andrew C Yen; Sharon S Brouha; Lewis D Hahn; Albert Hsiao Journal: Radiol Artif Intell Date: 2021-11-10