Semantic Lung Segmentation Using Convolutional Neural Networks

  • Chest X-Ray (CXR) images as part of a non-invasive diagnosis method are commonly used in today’s medical workflow. In traditional methods, physicians usually use their experience to interpret CXR images, however, there is a large interobserver variance. Computer vision may be used as a standard for assisted diagnosis. In this study, we applied an encoder-decoder neural network architecture for automatic lung region detection. We compared a three-class approach (left lung, right lung, background) and a two-class approach (lung, background). The differentiation of left and right lungs as direct result of a semantic segmentation on basis of neural nets rather than post-processing a lung-background segmentation is done here for the first time. Our evaluation was done on the NIH Chest X-ray dataset, from which 1736 images were extracted and manually annotated. We achieved 94:9% mIoU and 92% mIoU as segmentation quality measures for the two-class-model and the three-class-model, respectively. This result is very promising for the segmentation of lung regions having the simultaneous classification of left and right lung in mind.

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Ching-Sheng Chang, Jin-Fa Lin, Ming-Ching LeeORCiD, Christoph PalmORCiDGND
DOI:https://doi.org/10.1007/978-3-658-29267-6_17
ISBN:978-3-658-29266-9
Parent Title (German):Bildverarbeitung für die Medizin 2020. Algorithmen – Systeme – Anwendungen. Proceedings des Workshops vom 15. bis 17. März 2020 in Berlin
Publisher:Springer Vieweg
Place of publication:Wiesbaden
Editor:Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus-Hermann Maier-Hein, Christoph Palm
Document Type:conference proceeding (article)
Language:English
Year of first Publication:2020
Release Date:2020/04/30
Tag:Chest X-Ray; Deep Learning; Encoder-Decoder Network
GND Keyword:Neuronales Netz; Segmentierung; Brustkorb
First Page:75
Last Page:80
Institutes:Fakultät Informatik und Mathematik
Regensburg Center of Biomedical Engineering - RCBE
Regensburg Medical Image Computing - ReMIC
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke
6 Technik, Medizin, angewandte Wissenschaften