Multi-stage learning for robust lung segmentation in challenging CT volumes

Authors:
Michal Sofka;Jens Wetzl;Neil Birkbeck;Jingdan Zhang;Timo Kohlberger;Jens Kaftan;Jérôme Declerck;S. Kevin Zhou
Affiliations:
Image Analytics and Informatics, Siemens Corporate Research, Princeton, NJ;Image Analytics and Informatics, Siemens Corporate Research, Princeton, NJ;Image Analytics and Informatics, Siemens Corporate Research, Princeton, NJ;Image Analytics and Informatics, Siemens Corporate Research, Princeton, NJ;Image Analytics and Informatics, Siemens Corporate Research, Princeton, NJ;Molecular Imaging, Siemens Healthcare, Oxford, UK;Molecular Imaging, Siemens Healthcare, Oxford, UK;Image Analytics and Informatics, Siemens Corporate Research, Princeton, NJ
Venue:
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III
Year:
2011

Citing 3
Cited 1

Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Template registration with missing parts: application to the segmentation of m. tuberculosis infected lungs

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Interactive lung segmentation in ct scans with severe abnormalities

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro

Thoracic abnormality detection with data adaptive structure estimation

MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Simple algorithms for segmenting healthy lung parenchyma in CT are unable to deal with high density tissue common in pulmonary diseases. To overcome this problem, we propose a multi-stage learningbased approach that combines anatomical information to predict an initialization of a statistical shape model of the lungs. The initialization first detects the carina of the trachea, and uses this to detect a set of automatically selected stable landmarks on regions near the lung (e.g., ribs, spine). These landmarks are used to align the shape model, which is then refined through boundary detection to obtain fine-grained segmentation. Robustness is obtained through hierarchical use of discriminative classifiers that are trained on a range of manually annotated data of diseased and healthy lungs. We demonstrate fast detection (35s per volume on average) and segmentation of 2 mm accuracy on challenging data.