Conference proceeding
Smoothing lung segmentation surfaces in 3D x-ray CT images using anatomic guidance
Proceedings of SPIE, Vol.5370(1), pp.1066-1075
Medical Imaging 2004: Image Processing
05/12/2004
DOI: 10.1117/12.536891
Abstract
Several methods for automatic lung segmentation in volumetric computed tomography (CT)
images have been proposed. Most methods distinguish the lung parenchyma from the surrounding
anatomy based on the difference in CT attenuation values. This can lead to an irregular and inconsistent
lung boundary for the regions near the mediastinum. This paper
presents a fully automatic method for the 3D smoothing of the lung boundary using information
from the segmented human airway tree. First, using the segmented airway tree we define a
bounding box around the mediastinum for each lung, within which all operations are performed.
We then define all generations of the airway tree distal to the right and left mainstem bronchi
to be part of the respective lungs, and exclude all other segments. Finally, we perform a fast
morphological closing with an ellipsoidal kernel to smooth the surface of the lung. This
method has been tested by processing the segmented lungs from eight normal datasets. The mean
value of the magnitude of curvature of the contours of mediastinal transverse slices, averaged
over all the datasets, is 0.0450 before smoothing and 0.0167 post smoothing. The accuracy
of the lung contours after smoothing is assessed by comparing the automatic results to manually
traced smooth lung borders by a human analyst. Averaged over all volumes, the root mean square
difference between human and computer borders is 0.8691 mm after smoothing, compared to 1.3012 mm
before. The mean similarity index, which is an area overlap measure based on the kappa statistic, is
0.9958 (SD 0.0032).
Details
- Title: Subtitle
- Smoothing lung segmentation surfaces in 3D x-ray CT images using anatomic guidance
- Creators
- Soumik Ukil - University of IowaJoseph M Reinhardt - University of Iowa
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of SPIE, Vol.5370(1), pp.1066-1075
- Conference
- Medical Imaging 2004: Image Processing
- DOI
- 10.1117/12.536891
- ISSN
- 0277-786X
- Language
- English
- Date published
- 05/12/2004
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology
- Record Identifier
- 9984196974402771
Metrics
5 Record Views