Unsupervised machine learning identifies predictive progression markers of IPF.
Idiopathic pulmonary fibrosis
Tomography, X-ray computed
Unsupervised machine learning
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
Feb 2023
Feb 2023
Historique:
received:
03
11
2021
accepted:
08
06
2022
revised:
06
05
2022
pubmed:
7
9
2022
medline:
3
2
2023
entrez:
6
9
2022
Statut:
ppublish
Résumé
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. 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. 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. 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. • 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.
Identifiants
pubmed: 36066734
doi: 10.1007/s00330-022-09101-x
pii: 10.1007/s00330-022-09101-x
pmc: PMC9889455
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
925-935Subventions
Organisme : Austrian Science Fund
ID : P 35189, P 34198
Organisme : Vienna Science and Technology Fund
ID : LS20-065
Informations de copyright
© 2022. The Author(s).
Références
Corrin B, Nicholson AG (2011) Pathology of the lungs E-book: expert consult: Online and Print., 3rd ed. Elsevier Health Sciences
Sgalla G, Biffi A, Richeldi L (2016) Idiopathic pulmonary fibrosis: diagnosis, epidemiology and natural history: IPF: diagnosis, epidemiology, course. Respirology 21:427–437. https://doi.org/10.1111/resp.12683
doi: 10.1111/resp.12683
Sköld CM, Bendstrup E, Myllärniemi M et al (2017) Treatment of idiopathic pulmonary fibrosis: a position paper from a Nordic expert group. J Intern Med 281:149–166. https://doi.org/10.1111/joim.12571
doi: 10.1111/joim.12571
Hutchinson J, Fogarty A, Hubbard R, McKeever T (2015) Global incidence and mortality of idiopathic pulmonary fibrosis: a systematic review. Eur Respir J 46:795–806. https://doi.org/10.1183/09031936.00185114
doi: 10.1183/09031936.00185114
Fernández Pérez ER, Daniels CE, St. Sauver J et al (2010) Incidence, prevalence, and clinical course of idiopathic pulmonary fibrosis. Chest 137:129–137. https://doi.org/10.1378/chest.09-1002
doi: 10.1378/chest.09-1002
Martinez FJ, Collard HR, Pardo A et al (2017) Idiopathic pulmonary fibrosis. Nat Rev Dis Primer 3:17074. https://doi.org/10.1038/nrdp.2017.74
doi: 10.1038/nrdp.2017.74
Raghu G, Remy-Jardin M, Myers JL et al (2018) Diagnosis of idiopathic pulmonary fibrosis. An official ATS/ERS/JRS/ALAT clinical practice guideline. Am J Respir Crit Care Med 198:e44–e68. https://doi.org/10.1164/rccm.201807-1255ST
doi: 10.1164/rccm.201807-1255ST
Turner-Warwick M, Burrows B, Johnson A (1980) Cryptogenic fibrosing alveolitis: clinical features and their influence on survival. Thorax 35:171–180. https://doi.org/10.1136/thx.35.3.171
doi: 10.1136/thx.35.3.171
Bartholmai BJ, Raghunath S, Karwoski RA et al (2013) Quantitative computed tomography imaging of interstitial lung diseases. J Thorac Imaging 28:298–307. https://doi.org/10.1097/RTI.0b013e3182a21969
doi: 10.1097/RTI.0b013e3182a21969
Flaherty KR, Andrei A-C, King TE et al (2008) Idiopathic interstitial pneumonia: do community and academic physicians agree on diagnosis? Yearb Pulm Dis 2008:186–187. https://doi.org/10.1016/S8756-3452(08)70642-X
doi: 10.1016/S8756-3452(08)70642-X
Hansell DM, Bankier AA, MacMahon H et al (2008) Fleischner Society: Glossary of terms for thoracic imaging. Radiology 246:697–722. https://doi.org/10.1148/radiol.2462070712
doi: 10.1148/radiol.2462070712
Mäkelä K, Hodgson U, Piilonen A et al (2018) Analysis of the histologic features associated with interobserver variation in idiopathic pulmonary fibrosis. Am J Surg Pathol:1. https://doi.org/10.1097/PAS.0000000000001031
Walsh SLF, Calandriello L, Sverzellati N et al (2016) Interobserver agreement for the ATS/ERS/JRS/ALAT criteria for a UIP pattern on CT. Thorax 71:45–51. https://doi.org/10.1136/thoraxjnl-2015-207252
doi: 10.1136/thoraxjnl-2015-207252
Vogl W-D, Prosch H, Müller-Mang C et al (2014) Longitudinal alignment of disease progression in fibrosing interstitial lung disease. In: Golland P, Hata N, Barillot C et al (eds) Medical image computing and computer-assisted intervention – MICCAI 2014. Springer International Publishing, Cham, pp 97–104
doi: 10.1007/978-3-319-10470-6_13
Hofmanninger J, Krenn M, Holzer M et al (2016) Unsupervised identification of clinically relevant clusters in routine imaging data. In: Ourselin S, Joskowicz L, Sabuncu MR et al (eds) Medical image computing and computer-assisted intervention – MICCAI 2016. Springer International Publishing, Cham, pp 192–200
doi: 10.1007/978-3-319-46720-7_23
Goksel O, Foncubierta-Rodrıguez A, Muller H, et al (2015) Overview of the VISCERAL Challenge at ISBI. 6
Gruslys A, Acosta-Cabronero J, Nestor PJ et al (2014) A new fast accurate nonlinear medical image registration program including surface preserving regularization. IEEE Trans Med Imaging 33:2118–2127. https://doi.org/10.1109/TMI.2014.2332370
doi: 10.1109/TMI.2014.2332370
Avants BB, Yushkevich P, Pluta J et al (2010) The optimal template effect in hippocampus studies of diseased populations. Neuroimage 49:2457–2466. https://doi.org/10.1016/j.neuroimage.2009.09.062
Holzer M, Donner R (2014) Over-segmentation of 3D medical image volumes based on monogenic cues. Krtiny, Czech Republic, p 8
Li F-F, Perona P (2005) A Bayesian hierarchical model for learning natural scene categories. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). IEEE, San Diego, CA, USA, pp 524–531
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3:610–621. https://doi.org/10.1109/TSMC.1973.4309314
doi: 10.1109/TSMC.1973.4309314
Jaccard P (1912) The distribution of the flora in the Alpine zone. New Phytol 11:37–50. https://doi.org/10.1111/j.1469-8137.1912.tb05611.x
doi: 10.1111/j.1469-8137.1912.tb05611.x
Yu QY, Tang XX (2022) Irreversibility of pulmonary fibrosis. Aging Dis 13:73. https://doi.org/10.14336/AD.2021.0730
doi: 10.14336/AD.2021.0730
Kolahian S, Fernandez IE, Eickelberg O, Hartl D (2016) Immune mechanisms in pulmonary fibrosis. Am J Respir Cell Mol Biol 55:309–322. https://doi.org/10.1165/rcmb.2016-0121TR
doi: 10.1165/rcmb.2016-0121TR
Breiman L (2001) Random forests. In: Machine learning, 5th ed. Kluwer Academic Publishers, pp 5–32
Menze BH, Kelm BM, Masuch R et al (2009) A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics 10:213. https://doi.org/10.1186/1471-2105-10-213
doi: 10.1186/1471-2105-10-213
Wu X, Kim GH, Salisbury ML et al (2019) Computed tomographic biomarkers in idiopathic pulmonary fibrosis. The Future of Quantitative Analysis. Am J Respir Crit Care Med 199:12–21. https://doi.org/10.1164/rccm.201803-0444PP
doi: 10.1164/rccm.201803-0444PP
Chung JH, Adegunsoye A, Cannon B et al (2021) Differentiation of idiopathic pulmonary fibrosis from connective tissue disease-related interstitial lung disease using quantitative imaging. J Clin Med 10:2663. https://doi.org/10.3390/jcm10122663
doi: 10.3390/jcm10122663
Salisbury ML, Lynch DA, van Beek EJR et al (2017) Idiopathic pulmonary fibrosis: the association between the adaptive multiple features method and fibrosis outcomes. Am J Respir Crit Care Med 195:921–929. https://doi.org/10.1164/rccm.201607-1385OC
doi: 10.1164/rccm.201607-1385OC
Gogali A, Wells AU (2012) Diagnostic approach to interstitial lung disease. Curr Respir Care Rep 1:199–207. https://doi.org/10.1007/s13665-012-0029-6
doi: 10.1007/s13665-012-0029-6
Jonigk D, Stark H, Braubach P et al (2019) Morphological and molecular motifs of fibrosing pulmonary injury patterns. J Pathol Clin Res 5:256–271. https://doi.org/10.1002/cjp2.141
doi: 10.1002/cjp2.141
Widell J, Lidén M (2020) Interobserver variability in high-resolution CT of the lungs. Eur J Radiol Open 7:100228. https://doi.org/10.1016/j.ejro.2020.100228
doi: 10.1016/j.ejro.2020.100228
Hansell DM, Goldin JG, King TE et al (2015) CT staging and monitoring of fibrotic interstitial lung diseases in clinical practice and treatment trials: a Position Paper from the Fleischner society. Lancet Respir Med 3:483–496. https://doi.org/10.1016/S2213-2600(15)00096-X
doi: 10.1016/S2213-2600(15)00096-X
Maldonado F, Moua T, Rajagopalan S et al (2014) Automated quantification of radiological patterns predicts survival in idiopathic pulmonary fibrosis. Eur Respir J 43:204–212. https://doi.org/10.1183/09031936.00071812
doi: 10.1183/09031936.00071812
Jacob J, Bartholmai BJ, Rajagopalan S et al (2016) Evaluation of computer-based computer tomography stratification against outcome models in connective tissue disease-related interstitial lung disease: a patient outcome study. BMC Med:14. https://doi.org/10.1186/s12916-016-0739-7