Jeanny Pan1, Johannes Hofmanninger1, Karl-Heinz Nenning1, Florian Prayer2, Sebastian Röhrich2, Nicola Sverzellati3, Venerino Poletti4,5, Sara Tomassetti4, Michael Weber1, Helmut Prosch6, Georg Langs1. 1. Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Spitalgasse 23, 1090, Vienna, Austria. 2. Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria. 3. Unit "Scienze Radiologiche", Department of Medicine and Surgery (DiMeC), University of Parma, Parma, Italy. 4. Department of Thoracic Diseases, Morgagni-Pierantoni Hospital, Forlì, Italy. 5. Department of Respiratory Diseases and Allergy, Aarhus University Hospital, Aarhus, Denmark. 6. Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria. helmut.prosch@meduniwien.ac.at.
Abstract
OBJECTIVES: To identify and evaluate predictive lung imaging markers and their pathways of change during progression of idiopathic pulmonary fibrosis (IPF) from sequential data of an IPF cohort. To test if these imaging markers predict outcome. METHODS: We studied radiological disease progression in 76 patients with IPF, including overall 190 computed tomography (CT) examinations of the chest. An algorithm identified candidates for imaging patterns marking progression by computationally clustering visual CT features. A classification algorithm selected clusters associated with radiological disease progression by testing their value for recognizing the temporal sequence of examinations. This resulted in radiological disease progression signatures, and pathways of lung tissue change accompanying progression observed across the cohort. Finally, we tested if the dynamics of marker patterns predict outcome, and performed an external validation study on a cohort from a different center. RESULTS: Progression marker patterns were identified and exhibited high stability in a repeatability experiment with 20 random sub-cohorts of the overall cohort. The 4 top-ranked progression markers were consistently selected as most informative for progression across all random sub-cohorts. After spatial image registration, local tracking of lung pattern transitions revealed a network of tissue transition pathways from healthy to a sequence of disease tissues. The progression markers were predictive for outcome, and the model achieved comparable results on a replication cohort. CONCLUSIONS: Unsupervised learning can identify radiological disease progression markers that predict outcome. Local tracking of pattern transitions reveals pathways of radiological disease progression from healthy lung tissue through a sequence of diseased tissue types. KEY POINTS: • Unsupervised learning can identify radiological disease progression markers that predict outcome in patients with idiopathic pulmonary fibrosis. • Local tracking of pattern transitions reveals pathways of radiological disease progression from healthy lung tissue through a sequence of diseased tissue types. • The progression markers achieved comparable results on a replication cohort.
OBJECTIVES: To identify and evaluate predictive lung imaging markers and their pathways of change during progression of idiopathic pulmonary fibrosis (IPF) from sequential data of an IPF cohort. To test if these imaging markers predict outcome. METHODS: We studied radiological disease progression in 76 patients with IPF, including overall 190 computed tomography (CT) examinations of the chest. An algorithm identified candidates for imaging patterns marking progression by computationally clustering visual CT features. A classification algorithm selected clusters associated with radiological disease progression by testing their value for recognizing the temporal sequence of examinations. This resulted in radiological disease progression signatures, and pathways of lung tissue change accompanying progression observed across the cohort. Finally, we tested if the dynamics of marker patterns predict outcome, and performed an external validation study on a cohort from a different center. RESULTS: Progression marker patterns were identified and exhibited high stability in a repeatability experiment with 20 random sub-cohorts of the overall cohort. The 4 top-ranked progression markers were consistently selected as most informative for progression across all random sub-cohorts. After spatial image registration, local tracking of lung pattern transitions revealed a network of tissue transition pathways from healthy to a sequence of disease tissues. The progression markers were predictive for outcome, and the model achieved comparable results on a replication cohort. CONCLUSIONS: Unsupervised learning can identify radiological disease progression markers that predict outcome. Local tracking of pattern transitions reveals pathways of radiological disease progression from healthy lung tissue through a sequence of diseased tissue types. KEY POINTS: • Unsupervised learning can identify radiological disease progression markers that predict outcome in patients with idiopathic pulmonary fibrosis. • Local tracking of pattern transitions reveals pathways of radiological disease progression from healthy lung tissue through a sequence of diseased tissue types. • The progression markers achieved comparable results on a replication cohort.
Authors: David M Hansell; Alexander A Bankier; Heber MacMahon; Theresa C McLoud; Nestor L Müller; Jacques Remy Journal: Radiology Date: 2008-01-14 Impact factor: 11.105
Authors: Audrunas Gruslys; Julio Acosta-Cabronero; Peter J Nestor; Guy B Williams; Richard E Ansorge Journal: IEEE Trans Med Imaging Date: 2014-06-23 Impact factor: 10.048
Authors: C M Sköld; E Bendstrup; M Myllärniemi; G Gudmundsson; T Sjåheim; O Hilberg; A Altraja; R Kaarteenaho; G Ferrara Journal: J Intern Med Date: 2016-11-13 Impact factor: 8.989
Authors: Brian J Bartholmai; Sushravya Raghunath; Ronald A Karwoski; Teng Moua; Srinivasan Rajagopalan; Fabien Maldonado; Paul A Decker; Richard A Robb Journal: J Thorac Imaging Date: 2013-09 Impact factor: 3.000
Authors: Evans R Fernández Pérez; Craig E Daniels; Darrell R Schroeder; Jennifer St Sauver; Thomas E Hartman; Brian J Bartholmai; Eunhee S Yi; Jay H Ryu Journal: Chest Date: 2009-09-11 Impact factor: 9.410
Authors: Ganesh Raghu; Martine Remy-Jardin; Jeffrey L Myers; Luca Richeldi; Christopher J Ryerson; David J Lederer; Juergen Behr; Vincent Cottin; Sonye K Danoff; Ferran Morell; Kevin R Flaherty; Athol Wells; Fernando J Martinez; Arata Azuma; Thomas J Bice; Demosthenes Bouros; Kevin K Brown; Harold R Collard; Abhijit Duggal; Liam Galvin; Yoshikazu Inoue; R Gisli Jenkins; Takeshi Johkoh; Ella A Kazerooni; Masanori Kitaichi; Shandra L Knight; George Mansour; Andrew G Nicholson; Sudhakar N J Pipavath; Ivette Buendía-Roldán; Moisés Selman; William D Travis; Simon Walsh; Kevin C Wilson Journal: Am J Respir Crit Care Med Date: 2018-09-01 Impact factor: 21.405