Skip to main content Deutsch

PULMARCH

Sorry, this content is only available in German!

PULMARCH

Image PULMARCH

Funded by the Austrian Science Fund (FWF)

Project team: Christina Müller-Mang, Joachim Ofner, Karl-Heinz Nenning, Thomas Schlegl, Wolf-Dieter Vogl, Georg Langs

Summary: The differential diagnosis of idiopathic interstitial pneumonias (IIPs) with thin-section computed tomography (CT) is an important and particularly difficult task in clinical radiology. The distinction between the two most common entities, idiopathic pulmonary fibrosis (IPF) and nonspecific interstitial pneumonia (NSIP) is especially important because these two entities have substantially different prognoses and  usually require different treatment.

This project will create an automated computer-aided diagnosis (CAD) system with two main aims: 1) To differentiate between the textural expression of usual interstitial pneumonia (UIP, the histopathological counterpart of IPF) and NSIP in a fully automated fashion while providing increased sensitivity/specificity over today's differential diagnosis; 2) To allow early diagnosis by performing spatiotemporal analysis of disease progression, yielding novel insights into disease formation.

The computational framework we will develop during the project first segments the lung in the CT volume, then computes and selects relevant three-dimensional texture features, and, subsequently differentiates automatically between IPF/UIP and NSIP. The change in the lung's interstitial architectures is assessed by a classification pipeline based on three-dimensional features that represent the texture sub-types e.g., ground-glass opacities, reticular opacities, honeycombing, etc.). The diagnostic power of the system is improved by machine learning approaches, which are used for the automatic selection of the associated texture features. This leads to a classification of IPF/UIP versus NSIP based on an optimal differentiation between the texture sub-types.

Tracking the local texture changes between the first examination and all follow-up examinations will yield mathematical models that precisely describe the spatiotemporal progression of the disease, allowing the study of trends within the cohort. The resulting automatic, quantitative analysis of the spatiotemporal progression of IIPs will provide new insights into the disease course characteristics.

 

Papers

  • René Donner, Helmut Steiner, Horst Bischof, Georg Langs. Localization of 3D Anatomical Structures Using Random Forests and Discrete Optimization. in Proc. of MCV - MICCAI 2010
  • Burner, A. and Donner, R. and Mayerhoefer, M. and Kainberger, F. and Langs G.  Texture Bags: Anomaly Retrieval in Medical Images based on Local 3D-Texture Similarity.  Proc. of the MICCAI 2011 MCBR-CDS 2011, Toronto, Canada.
  • Haas, S. and Donner, R. and Burner, A. and Holzer, M. and Langs G. Superpixel-based Interest Points for Effective Bags of Visual Words Medical Image Retrieval.  Proc. of the MICCAI 2011 MCBR-CDS 2011, Toronto, Canada.
  • René Donner, Georg Langs. Fast Anatomical Structure Localization Using Top-down Image Patch Regression. In Proc. of MICCAI 2012 Workshop on Medical Computer Vision.
  • Karl-Heinz Nenning, Georg Langs. Overlapping Functional Networks in Multiple fMRI Paradigms. 2nd NIPS workshop on Machine Learning and Interpretation in Neuroimaging, Lake Tahoe, USA, 2012
  • A. Valentinitsch, JM. Patsch, J. Deutschmann, C. Schueller-Weidekamm, H. Resch, F. Kainberger, G. Langs. Automated threshold-independent cortex segmentation by 3D-texture analysis of HR-pQCT scans. in Bone 51(3):480-487, 2012 Sep;
  • A. Valentinitsch, J. M. Patsch, J. Deutschmann, C. Schueller-Weidekamm, H. Resch, F. Kainberger, and G. Langs. Automated threshold-independent cortex segmentation by 3d-texture analysis of hr-pqct scans. Bone, 51(3):480–487, 2012.
  • M. Dorfer, R. Donner, and G. Langs, “Constructing an un-biased whole body atlas from clinical imaging data by fragment bundling,” in proceedings of Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013, 2013, pp. 219–226.
  • Molinari F, Tack DM, Boiselle P, Ngo L, Mueller-Mang C, Litmanovich D, Bankier AA. Radiation dose management in thoracic CT: an international survey. Diagn Interv Radiol. 2013 May-Jun;19(3):201-9.
  • René Donner, Bjoern H. Menze, Horst Bischof, and Georg Langs. "Global localization of 3D anatomical structures by pre-filtered Hough Forests and discrete optimization." Medical image analysis 17, no. 8 (2013): 1304-1314.
  • Thomas Schlegl, Joachim Ofner, Georg Langs. Unsupervised pre-training across image domains improves lung tissue classification. In Medical Computer Vision: Algorithms for Big Data (pp. 82-93). Springer International Publishing (2014)
  • Wolf-Dieter Vogl, Helmut Prosch, Christina Müller-Mang, Ursula Schmidt-Erfurth, and Georg Langs. Longitudinal Alignment of Disease Progression in Fibrosing Interstitial Lung Disease. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2014 (pp. 97-104). Springer International Publishing (2014).
  • Mueller-Mang C. Classical patterns of interstitial lung diseases. Radiologe. 2014 Dec; 54(12):1159-69 doi: 10.1007/s00117-014-2756-x.
  • Karl-Heinz Nenning, Kathrin Kollndorfer, Veronika Schöpf, Daniela Prayer, and Georg Langs, Multi-Subject Manifold Alignment of Functional Network Structures via Joint Diagonalization, to appear in Advances in Information Processing in Medical Imaging IPMI 2015 (accepted)

Peer-reviewed abstracts and presentations ad scientific congresses

  • Karl-Heinz Nenning, Veronika Schöpf, René Donner, Gregor Kasprian, Daniela Prayer, Georg Langs. Identifying overlapping functional networks in multi-paradigm fMRI studies. European Congress of Radiology, Vienna, Austria, 2013.
  • Karl-Heinz Nenning, Rene Donner, Daniela Prayer, Georg Langs. Resting-state and stimulus induced fMRI data fusion, European Congress of Radiology, Vienna, Austria, 2014
  • Karl-Heinz Nenning, Andreas Müller, Daniela Prayer, Georg Langs, Gregor Kasprian, The Functional Language Connectome in frontal and temporal Gliomas,  European Congress of Radiology, Vienna, Austria, 2014
  • Georg Langs, René Donner, Philipp Peloschek, Franz Kainberger, Daniela Prayer, Gregor Kasprian, Ernst Schwartz, Eva Dittrich, Andreas Burner, Lukas Fischer, Alexander Valentinitsch, Thomas Schlegl, Janina Patsch. Spatio-temporal patterns in radiology: from research in machine learning, pattern recognition and radiology towards clinical application. ECR 2012 IMAGINE, European Congress of Radiology, Vienna, Austria, 2012
  • Georg Langs, René Donner, Philipp Peloschek, Franz Kainberger, Daniela Prayer, Gregor Kasprian, Ernst Schwartz, Eva Dittrich, Andreas Burner, Lukas Fischer, Alexander Valentinitsch, Janina Patsch. The convergence of machine learning, computer vision and radiology: research and clinical application. ECR 2011 IMAGINE, European Congress of Radiology, Vienna, Austria, 2011
  • E. Dittrich, T. Riklin-Raviv, G. Kasprian, P. Brugger, D. Prayer and G. Langs. Learning a spatio-temporal latent atlas for fetal brain segmentation.  Proceedings of the MICCAI 2011 Workshop on Image Analysis of Human Brain Development (IAHBD 2011), Toronto, Canada.
  • Werner Lang, René Donner. Towards efficient simultaneous multi-patient annotation of 3D imaging data. In ECR 2012
  •  J.Ofner, C.Müller-Mang, A.Burner, D.Markonis, A.Depeursinge, H.Müller, G.Langs. Com- putational Texture Analysis in Interstitial Lung Disease: Comparison of Descriptors and Classification Accuracy. European Society of Radiology 2013.
  • KH Nenning, V Schoepf, D Prayer, G Langs, Overlapping Functional Networks in Mul- tiple fMRI Paradigms, 2nd NIPS 2012 Workshop on Machine Learning and Interpretation in NeuroImaging
  • J.Ofner,A.Burner,R.Donner,A.Depeursinge,D.Markonis,C.Müller-Mang,H.Müller,G.Langs. Evaluation of Content-based, Tissue-Analysis Algorithms for Lung Pathology Detec- tion. Radiologic Society of North America 2012.
  • J.Ofner, C.Müller-Mang, A.Burner, D.Markonis, A.Depeursinge, H.Müller, G.Langs. Com- putational Texture Analysis in Interstitial Lung Disease: Comparison of Descriptors and Classification Accuracy. European Society of Radiology 2013.
  • KH Nenning, V Schoepf, D Prayer, G Langs, Overlapping Functional Networks in Mul- tiple fMRI Paradigms, 2nd NIPS 2012 Workshop on Machine Learning and Interpretation in NeuroImaging
  • KH Nenning, V Schoepf, R Donner, G Kasprian D Prayer, G Langs, Identifying over- lapping functional networks in multi-paradigm fMRI studies, European Congress of Radiology 2013.