Hyun J Kim1, Matthew S Brown2, Daniel Chong2, David W Gjertson3, Peiyun Lu2, Hak J Kim4, Heidi Coy2, Jonathan G Goldin2. 1. Center for Computer Vision and Imaging Biomarkers; Department of Radiological Science, David Geffen School of Medicine, UCLA, Los Angeles, California; Department of Biostatistics, Fielding School of Public Health, UCLA, Los Angeles, CA 90024. Electronic address: gracekim@mednet.ucla.edu. 2. Center for Computer Vision and Imaging Biomarkers; Department of Radiological Science, David Geffen School of Medicine, UCLA, Los Angeles, California. 3. Department of Radiological Science, David Geffen School of Medicine, UCLA, Los Angeles, California; Department of Biostatistics, Fielding School of Public Health, UCLA, Los Angeles, CA 90024; Department of Pathology, David Geffen School of Medicine, UCLA, Los Angeles, California. 4. Department of Radiological Science, David Geffen School of Medicine, UCLA, Los Angeles, California.
Abstract
RATIONALE AND OBJECTIVES: Median survival of patients with idiopathic pulmonary fibrosis (IPF) is 2-5 years. Sensitive imaging metrics can play a role in detecting early changes in therapeutic development. The aim of the present study was to compare known computed tomography (CT) histogram kurtosis and a classifier-based quantitative score to assess baseline severity and change over time in patients with IPF. MATERIALS AND METHODS: A total of 57 patients with at least baseline and paired follow-up scans were selected from an imaging database of standardized CT scans obtained from patients with IPF. CT histogram measurement of kurtosis and quantitative lung fibrosis (QLF) and quantitative interstitial lung disease (QILD) scores from a classification algorithm were calculated. Spearman rank correlations were used to assess associations between baseline severity and changes for all CT-derived measures compared to forced vital capacity (FVC) and carbon monoxide diffusion capacity (DLCO) (percent predicted). RESULTS: At baseline, mean (±SD) of kurtosis was 2.43 (±1.83). Mean (±SD) values of QLF and QILD scores were 20.7% (±13.4) and 43.3% (±20.0), respectively. All baseline histogram indices and QLF and QILD scores were correlated well with baseline FVC and DLCO. When assessing associations with changes in FVC and DLCO over time, only QLF score was statistically significant (ρ = -0.57; P < .0001 for FVC and ρ = -0.34; P = .025 for DLCO), whereas kurtosis was not. CONCLUSIONS: Classifier-model-derived scores (QLF and QILD), based on a set of texture features, are associated with baseline disease extent and are also a sensitive measure of change over time. A QLF score can be used for measuring the extent of disease severity and longitudinal changes.
RATIONALE AND OBJECTIVES: Median survival of patients with idiopathic pulmonary fibrosis (IPF) is 2-5 years. Sensitive imaging metrics can play a role in detecting early changes in therapeutic development. The aim of the present study was to compare known computed tomography (CT) histogram kurtosis and a classifier-based quantitative score to assess baseline severity and change over time in patients with IPF. MATERIALS AND METHODS: A total of 57 patients with at least baseline and paired follow-up scans were selected from an imaging database of standardized CT scans obtained from patients with IPF. CT histogram measurement of kurtosis and quantitative lung fibrosis (QLF) and quantitative interstitial lung disease (QILD) scores from a classification algorithm were calculated. Spearman rank correlations were used to assess associations between baseline severity and changes for all CT-derived measures compared to forced vital capacity (FVC) and carbon monoxide diffusion capacity (DLCO) (percent predicted). RESULTS: At baseline, mean (±SD) of kurtosis was 2.43 (±1.83). Mean (±SD) values of QLF and QILD scores were 20.7% (±13.4) and 43.3% (±20.0), respectively. All baseline histogram indices and QLF and QILD scores were correlated well with baseline FVC and DLCO. When assessing associations with changes in FVC and DLCO over time, only QLF score was statistically significant (ρ = -0.57; P < .0001 for FVC and ρ = -0.34; P = .025 for DLCO), whereas kurtosis was not. CONCLUSIONS: Classifier-model-derived scores (QLF and QILD), based on a set of texture features, are associated with baseline disease extent and are also a sensitive measure of change over time. A QLF score can be used for measuring the extent of disease severity and longitudinal changes.
Authors: Susan K Mathai; Stephen Humphries; Jonathan A Kropski; Timothy S Blackwell; Julia Powers; Avram D Walts; Cheryl Markin; Julia Woodward; Jonathan H Chung; Kevin K Brown; Mark P Steele; James E Loyd; Marvin I Schwarz; Tasha Fingerlin; Ivana V Yang; David A Lynch; David A Schwartz Journal: Thorax Date: 2019-09-26 Impact factor: 9.139
Authors: Samuel Y Ash; Rola Harmouche; James C Ross; Alejandro A Diaz; Gary M Hunninghake; Rachel K Putman; Jorge Onieva; Fernando J Martinez; Augustine M Choi; David A Lynch; Hiroto Hatabu; Ivan O Rosas; Raul San Jose Estepar; George R Washko Journal: Acad Radiol Date: 2016-12-15 Impact factor: 3.173
Authors: Margaret L Salisbury; David A Lynch; Edwin J R van Beek; Ella A Kazerooni; Junfeng Guo; Meng Xia; Susan Murray; Kevin J Anstrom; Eric Yow; Fernando J Martinez; Eric A Hoffman; Kevin R Flaherty Journal: Am J Respir Crit Care Med Date: 2017-04-01 Impact factor: 21.405
Authors: Jennifer M Wang; Scott H Robertson; Ziyi Wang; Mu He; Rohan S Virgincar; Geoffry M Schrank; Rose Marie Smigla; Thomas G O'Riordan; John Sundy; Lukas Ebner; Craig R Rackley; Page McAdams; Bastiaan Driehuys Journal: Thorax Date: 2017-08-31 Impact factor: 9.139
Authors: Grace Hyun J Kim; Stephan S Weigt; John A Belperio; Matthew S Brown; Yu Shi; Joshua H Lai; Jonathan G Goldin Journal: Eur Radiol Date: 2019-08-26 Impact factor: 5.315