TY - JOUR
T1 - Texture-based identification and characterization of interstitial pneumonia patterns in lung multidetector CT
AU - Korfiatis, Panayiotis D.
AU - Karahaliou, Anna N.
AU - Kazantzi, Alexandra D.
AU - Kalogeropoulou, Cristina
AU - Costaridou, Lena I.
N1 - Funding Information:
Manuscript received June 30, 2009; revised October 12, 2009. First published November 10, 2009; current version published June 3, 2010. This work was supported in part by the Caratheodory Programe (C.180) of the University of Patras.
PY - 2010/5
Y1 - 2010/5
N2 - Identification and characterization of diffuse parenchyma lung disease (DPLD) patterns challenges computer-aided schemes in computed tomography (CT) lung analysis. In this study, an automated scheme for volumetric quantification of interstitial pneumonia (IP) patterns, a subset of DPLD, is presented, utilizing a multidetector CT (MDCT) dataset. Initially, lung-field segmentation is achieved by 3-D automated gray-level thresholding combined with an edge-highlighting wavelet preprocessing step, followed by a texture-based border refinement step. The vessel tree volume is identified and removed from lung field, resulting in lung parenchyma (LP) volume. Following, identification and characterization of IP patterns is formulated as a three-class pattern classification of LP into normal, ground glass, and reticular patterns, by means of k-nearest neighbor voxel classification, exploiting 3-D cooccurrence features. Performance of the proposed scheme in indentifying and characterizing ground glass and reticular patterns was evaluated by means of volume overlap (ground glass: 0.734 ± 0.057, reticular: 0.815 ± 0.037), true-positive fraction (ground glass: 0.638 ± 0.055, reticular: 0.942 ± 0.023) and false-positive fraction (ground glass: 0.361 ± 0.027, reticular: 0.147 ± 0.032) on five MDCT scans.
AB - Identification and characterization of diffuse parenchyma lung disease (DPLD) patterns challenges computer-aided schemes in computed tomography (CT) lung analysis. In this study, an automated scheme for volumetric quantification of interstitial pneumonia (IP) patterns, a subset of DPLD, is presented, utilizing a multidetector CT (MDCT) dataset. Initially, lung-field segmentation is achieved by 3-D automated gray-level thresholding combined with an edge-highlighting wavelet preprocessing step, followed by a texture-based border refinement step. The vessel tree volume is identified and removed from lung field, resulting in lung parenchyma (LP) volume. Following, identification and characterization of IP patterns is formulated as a three-class pattern classification of LP into normal, ground glass, and reticular patterns, by means of k-nearest neighbor voxel classification, exploiting 3-D cooccurrence features. Performance of the proposed scheme in indentifying and characterizing ground glass and reticular patterns was evaluated by means of volume overlap (ground glass: 0.734 ± 0.057, reticular: 0.815 ± 0.037), true-positive fraction (ground glass: 0.638 ± 0.055, reticular: 0.942 ± 0.023) and false-positive fraction (ground glass: 0.361 ± 0.027, reticular: 0.147 ± 0.032) on five MDCT scans.
KW - Image segmentation
KW - Image texture analysis
KW - Respiratory system
UR - http://www.scopus.com/inward/record.url?scp=77953173086&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77953173086&partnerID=8YFLogxK
U2 - 10.1109/TITB.2009.2036166
DO - 10.1109/TITB.2009.2036166
M3 - Article
C2 - 19906596
AN - SCOPUS:77953173086
SN - 1089-7771
VL - 14
SP - 675
EP - 680
JO - IEEE Transactions on Information Technology in Biomedicine
JF - IEEE Transactions on Information Technology in Biomedicine
IS - 3
M1 - 5325905
ER -