TY - JOUR
T1 - Automated lobe-based airway labeling
AU - Gu, Suicheng
AU - Wang, Zhimin
AU - Siegfried, Jill M.
AU - Wilson, David
AU - Bigbee, William L.
AU - Pu, Jiantao
PY - 2012
Y1 - 2012
N2 - Regional quantitative analysis of airway morphological abnormalities is of great interest in lung disease investigation. Considering that pulmonary lobes are relatively independent functional unit, we develop and test a novel and efficient computerized scheme in this study to automatically and robustly classify the airways into different categories in terms of pulmonary lobe. Given an airway tree, which could be obtained using any available airway segmentation scheme, the developed approach consists of four basic steps: (1) airway skeletonization or centerline extraction, (2) individual airway branch identification, (3) initial rule-based airway classification/labeling, and (4) self-correction of labeling errors. In order to assess the performance of this approach, we applied it to a dataset consisting of 300 chest CT examinations in a batch manner and asked an image analyst to subjectively examine the labeled results. Our preliminary experiment showed that the labeling accuracy for the right upper lobe, the right middle lobe, the right lower lobe, the left upper lobe, and the left lower lobe is 100, 99.3, 99.3, 100, and 100, respectively. Among these, only two cases are incorrectly labeled due to the failures in airway detection. It takes around 2 minutes to label an airway tree using this algorithm.
AB - Regional quantitative analysis of airway morphological abnormalities is of great interest in lung disease investigation. Considering that pulmonary lobes are relatively independent functional unit, we develop and test a novel and efficient computerized scheme in this study to automatically and robustly classify the airways into different categories in terms of pulmonary lobe. Given an airway tree, which could be obtained using any available airway segmentation scheme, the developed approach consists of four basic steps: (1) airway skeletonization or centerline extraction, (2) individual airway branch identification, (3) initial rule-based airway classification/labeling, and (4) self-correction of labeling errors. In order to assess the performance of this approach, we applied it to a dataset consisting of 300 chest CT examinations in a batch manner and asked an image analyst to subjectively examine the labeled results. Our preliminary experiment showed that the labeling accuracy for the right upper lobe, the right middle lobe, the right lower lobe, the left upper lobe, and the left lower lobe is 100, 99.3, 99.3, 100, and 100, respectively. Among these, only two cases are incorrectly labeled due to the failures in airway detection. It takes around 2 minutes to label an airway tree using this algorithm.
UR - http://www.scopus.com/inward/record.url?scp=84867868159&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867868159&partnerID=8YFLogxK
U2 - 10.1155/2012/382806
DO - 10.1155/2012/382806
M3 - Article
C2 - 23093951
AN - SCOPUS:84867868159
SN - 1687-4188
VL - 2012
JO - International Journal of Biomedical Imaging
JF - International Journal of Biomedical Imaging
M1 - 382806
ER -