From Local to Global: A Holistic Lung Graph Model
Lung image analysis is an essential part in the assessment of pulmonary diseases. Through visual inspection of CT scans, radiologists detect abnormal patterns in the lung parenchyma, aiming to establish a timely diagnosis and thus improving patient outcome. However, in a generalized disorder of the lungs, such as pulmonary hypertension, the changes in organ tissue can be elusive, requiring additional invasive studies to confirm the diagnosis. We present a graph model that quantifies lung texture in a holistic approach enhancing the analysis between pathologies with similar local changes. The approach extracts local state-of-the-art 3D texture descriptors from an automatically generated geometric parcellation of the lungs. The global texture distribution is encoded in a weighted graph that characterizes the correlations among neighboring organ regions. A data set of 125 patients with suspicion of having a pulmonary vascular pathology was used to evaluate our method. Three classes containing 47 pulmonary hypertension, 31 pulmonary embolism and 47 control cases were classified in a one vs. one setup. An area under the curve of up to 0.85 was obtained adding directionality to the edges of the graph architecture. The approach was able to identify diseased patients, and to distinguish pathologies with abnormal local and global blood perfusion defects.
KeywordsLung graph model Texture analysis Pulmonary perfusion
This work was partly supported by the Swiss National Science Foundation in the PH4D project (grant agreement 320030-146804).
- 2.Depeursinge, A., Al-Kadi, O.S., Mitchell, J.R.: Biomedical Texture Analysis: Fundamentals, Applications and Tools. Elsevier-MICCAI Society Book series. Elsevier, October 2017. https://www.elsevier.com/books/title/author/9780128121337
- 3.Depeursinge, A., Zrimec, T., Busayarat, S., Müller, H.: 3D lung image retrieval using localized features. In: Medical Imaging 2011: Computer-Aided Diagnosis, vol. 7963, p. 79632E. SPIE, February 2011Google Scholar
- 4.Dicente Cid, Y., Batmanghelich, K., Müller, H.: Textured graph-model of the lungs for tuberculosis type classification and drug resistance prediction: participation in ImageCLEF 2017. In: CLEF2017 Working Notes. CEUR Workshop Proceedings, CEUR-WS.org, Dublin, Ireland, 11–14 September 2017 (2017). http://ceur-ws.org
- 5.Dicente Cid, Y., Depeursinge, A., Foncubierta-Rodríguez, Platon, A., Poletti, P.A., Müller, H.: Pulmonary embolism detection using localized vessel-based features in dual energy CT. In: SPIE Medical Imaging. International Society for Optics and Photonics (2015)Google Scholar
- 6.Dicente Cid, Y., Jimenez-del-Toro, O., Depeursinge, A., Müller, H.: Efficient and fully automatic segmentation of the lungs in CT volumes. In: Goksel, O., Jimenez-del-Toro, O., Foncubierta-Rodriguez, A., Müller, H. (eds.) Proceedings of the VISCERAL Challenge at ISBI, pp. 31–35. No. 1390 in CEUR Workshop Proceedings, April 2015Google Scholar
- 7.Dicente Cid, Y., Kalinovsky, A., Liauchuk, V., Kovalev, V., Müller, H.: Overview of ImageCLEFtuberculosis 2017 - predicting tuberculosis type and drug resistances. In: CLEF 2017 Labs Working Notes. CEUR Workshop Proceedings, CEUR-WS.org, Dublin, Ireland, 11–14 September 2017 (2017). http://ceur-ws.org
- 10.Farber, H.: Pulmonary circulation: diseases and their treatment. Eur. Respir. Rev. 21(123), 78 (2012). 3rd editionGoogle Scholar
- 17.Zrimec, T., Busayarat, S., Wilson, P.: A 3D model of the human lung with lung regions characterization. In: ICIP 2004 Proceedings of the IEEE International Conference on Image Processing, vol. 2, pp. 1149–1152 (2004)Google Scholar