K Martini1, B Baessler2, M Bogowicz3, C Blüthgen2, M Mannil2, S Tanadini-Lang3, J Schniering4, B Maurer4, T Frauenfelder2. 1. Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Rämistrase 100, 8091, Zurich, Switzerland. katharina.martini@usz.ch. 2. Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Rämistrase 100, 8091, Zurich, Switzerland. 3. Department of Radiation Oncology, University Hospital Zurich, University of Zurich, Zurich, Switzerland. 4. Center of Experimental Rheumatology, Department of Rheumatology, University Hospital Zurich, University of Zurich, Zurich, Switzerland.
Abstract
OBJECTIVE: To retrospectively evaluate if texture-based radiomics features are able to detect interstitial lung disease (ILD) and to distinguish between the different disease stages in patients with systemic sclerosis (SSc) in comparison with mere visual analysis of high-resolution computed tomography (HRCT). METHODS: Sixty patients (46 females, median age 56 years) with SSc who underwent HRCT of the thorax were retrospectively analyzed. Visual analysis was performed by two radiologists for the presence of ILD features. Gender, age, and pulmonary function (GAP) stage was calculated from clinical data (gender, age, pulmonary function test). Data augmentation was performed and the balanced dataset was split into a training (70%) and a testing dataset (30%). For selecting variables that allow classification of the GAP stage, single and multiple logistic regression models were fitted and compared by using the Akaike information criterion (AIC). Diagnostic accuracy was evaluated from the area under the curve (AUC) from receiver operating characteristic (ROC) analyses, and diagnostic sensitivity and specificity were calculated. RESULTS: Values for some radiomics features were significantly lower (p < 0.05) and those of other radiomics features were significantly higher (p = 0.001) in patients with GAP2 compared with those in patients with GAP1. The combination of two specific radiomics features in a multivariable model resulted in the lowest AIC of 10.73 with an AUC of 0.96, 84% sensitivity, and 99% specificity. Visual assessment of fibrosis was inferior in predicting individual GAP stages (AUC 0.86; 83% sensitivity; 74% specificity). CONCLUSION: The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features indicating severity of SSc-ILD on HRCT, which are not recognized by visual analysis. KEY POINTS: • Radiomics features can predict GAP stage with a sensitivity of 84% and a specificity of almost 100%. • Extent of fibrosis on HRCT and a combined model of different visual HRCT-ILD features perform worse in predicting GAP stage. • The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features on HRCT, which are not recognized by visual analysis.
OBJECTIVE: To retrospectively evaluate if texture-based radiomics features are able to detect interstitial lung disease (ILD) and to distinguish between the different disease stages in patients with systemic sclerosis (SSc) in comparison with mere visual analysis of high-resolution computed tomography (HRCT). METHODS: Sixty patients (46 females, median age 56 years) with SSc who underwent HRCT of the thorax were retrospectively analyzed. Visual analysis was performed by two radiologists for the presence of ILD features. Gender, age, and pulmonary function (GAP) stage was calculated from clinical data (gender, age, pulmonary function test). Data augmentation was performed and the balanced dataset was split into a training (70%) and a testing dataset (30%). For selecting variables that allow classification of the GAP stage, single and multiple logistic regression models were fitted and compared by using the Akaike information criterion (AIC). Diagnostic accuracy was evaluated from the area under the curve (AUC) from receiver operating characteristic (ROC) analyses, and diagnostic sensitivity and specificity were calculated. RESULTS: Values for some radiomics features were significantly lower (p < 0.05) and those of other radiomics features were significantly higher (p = 0.001) in patients with GAP2 compared with those in patients with GAP1. The combination of two specific radiomics features in a multivariable model resulted in the lowest AIC of 10.73 with an AUC of 0.96, 84% sensitivity, and 99% specificity. Visual assessment of fibrosis was inferior in predicting individual GAP stages (AUC 0.86; 83% sensitivity; 74% specificity). CONCLUSION: The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features indicating severity of SSc-ILD on HRCT, which are not recognized by visual analysis. KEY POINTS: • Radiomics features can predict GAP stage with a sensitivity of 84% and a specificity of almost 100%. • Extent of fibrosis on HRCT and a combined model of different visual HRCT-ILD features perform worse in predicting GAP stage. • The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features on HRCT, which are not recognized by visual analysis.
Authors: Yossra A Suliman; Rucsandra Dobrota; Dörte Huscher; Thi D L Nguyen-Kim; Britta Maurer; Suzana Jordan; Rudolf Speich; Thomas Frauenfelder; Oliver Distler Journal: Arthritis Rheumatol Date: 2015-12 Impact factor: 10.995
Authors: Xiaoping Wu; Grace H Kim; Margaret L Salisbury; David Barber; Brian J Bartholmai; Kevin K Brown; Craig S Conoscenti; Jan De Backer; Kevin R Flaherty; James F Gruden; Eric A Hoffman; Stephen M Humphries; Joseph Jacob; Toby M Maher; Ganesh Raghu; Luca Richeldi; Brian D Ross; Rozsa Schlenker-Herceg; Nicola Sverzellati; Athol U Wells; Fernando J Martinez; David A Lynch; Jonathan Goldin; Simon L F Walsh Journal: Am J Respir Crit Care Med Date: 2019-01-01 Impact factor: 21.405
Authors: Hyun J Kim; Matthew S Brown; Robert Elashoff; Gang Li; David W Gjertson; David A Lynch; Diane C Strollo; Eric Kleerup; Daniel Chong; Sumit K Shah; Shama Ahmad; Fereidoun Abtin; Donald P Tashkin; Jonathan G Goldin Journal: Eur Radiol Date: 2011-09-17 Impact factor: 5.315
Authors: H Schurawitzki; R Stiglbauer; W Graninger; C Herold; D Pölzleitner; O C Burghuber; D Tscholakoff Journal: Radiology Date: 1990-09 Impact factor: 11.105
Authors: S Fanti; A De Fabritiis; D Aloisi; M Dondi; M Marengo; G Compagnone; F Fallani; A Cavalli; N Monetti Journal: J Nucl Med Date: 1994-12 Impact factor: 10.057
Authors: Saeed Mirsadraee; Matthew Tse; Lucy Kershaw; Scott Semple; Nicola Schembri; Calvin Chin; John T Murchison; Nik Hirani; Edwin J R van Beek Journal: Quant Imaging Med Surg Date: 2016-02
Authors: Turkey Refaee; Benjamin Bondue; Gaetan Van Simaeys; Guangyao Wu; Chenggong Yan; Henry C Woodruff; Serge Goldman; Philippe Lambin Journal: J Pers Med Date: 2022-02-28
Authors: Anne-Noëlle Frix; François Cousin; Turkey Refaee; Fabio Bottari; Akshayaa Vaidyanathan; Colin Desir; Wim Vos; Sean Walsh; Mariaelena Occhipinti; Pierre Lovinfosse; Ralph T H Leijenaar; Roland Hustinx; Paul Meunier; Renaud Louis; Philippe Lambin; Julien Guiot Journal: J Pers Med Date: 2021-06-25