TY - GEN
T1 - Nonlinear histogram binning for quantitative analysis of lung tissue fibrosis in high-resolution CT data
AU - Zavaletta, Vanessa A.
AU - Bartholmai, Brian J.
AU - Robb, Richard A.
PY - 2007
Y1 - 2007
N2 - Diffuse lung diseases, such as idiopathic pulmonary fibrosis (IPF), can be characterized and quantified by analysis of volumetric high resolution CT scans of the lungs. These data sets typically have dimensions of 512 × 512 x 400. It is too subjective and labor intensive for a radiologist to analyze each slice and quantify regional abnormalities manually. Thus, computer aided techniques are necessary, particularly texture analysis techniques which classify various lung tissue types. Second and higher order statistics which relate the spatial variation of the intensity values are good discriminatory features for various textures. The intensity values in lung CT scans range between [-1024, 1024]. Calculation of second order statistics on this range is too computationally intensive so the data is typically binned between 16 or 32 gray levels. There are more effective ways of binning the gray level range to improve classification. An optimal and very efficient way to nonlinearly bin the histogram is to use a dynamic programming algorithm. The objective of this paper is to show that nonlinear binning using dynamic programming is computationally efficient and improves the discriminatory power of the second and higher order statistics for more accurate quantification of diffuse lung disease.
AB - Diffuse lung diseases, such as idiopathic pulmonary fibrosis (IPF), can be characterized and quantified by analysis of volumetric high resolution CT scans of the lungs. These data sets typically have dimensions of 512 × 512 x 400. It is too subjective and labor intensive for a radiologist to analyze each slice and quantify regional abnormalities manually. Thus, computer aided techniques are necessary, particularly texture analysis techniques which classify various lung tissue types. Second and higher order statistics which relate the spatial variation of the intensity values are good discriminatory features for various textures. The intensity values in lung CT scans range between [-1024, 1024]. Calculation of second order statistics on this range is too computationally intensive so the data is typically binned between 16 or 32 gray levels. There are more effective ways of binning the gray level range to improve classification. An optimal and very efficient way to nonlinearly bin the histogram is to use a dynamic programming algorithm. The objective of this paper is to show that nonlinear binning using dynamic programming is computationally efficient and improves the discriminatory power of the second and higher order statistics for more accurate quantification of diffuse lung disease.
KW - Histogram binning
KW - Lung tissue pathophysiology
KW - Texture analysis
UR - http://www.scopus.com/inward/record.url?scp=35148830871&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=35148830871&partnerID=8YFLogxK
U2 - 10.1117/12.710220
DO - 10.1117/12.710220
M3 - Conference contribution
AN - SCOPUS:35148830871
SN - 0819466298
SN - 9780819466297
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2007
T2 - Medical Imaging 2007: Physiology, Function, and Structure from Medical Images
Y2 - 18 February 2007 through 20 February 2007
ER -