Nonlinear histogram binning for quantitative analysis of lung tissue fibrosis in high-resolution CT data

Vanessa A. Zavaletta, Brian Jack Bartholmai, Richard A. Robb

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

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.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6511
EditionPART 2
DOIs
StatePublished - 2007
EventMedical Imaging 2007: Physiology, Function, and Structure from Medical Images - San Diego, CA, United States
Duration: Feb 18 2007Feb 20 2007

Other

OtherMedical Imaging 2007: Physiology, Function, and Structure from Medical Images
CountryUnited States
CitySan Diego, CA
Period2/18/072/20/07

Fingerprint

Higher order statistics
Pulmonary diseases
Computerized tomography
Dynamic programming
Textures
Tissue
Bins
Chemical analysis
Statistics
Personnel

Keywords

  • Histogram binning
  • Lung tissue pathophysiology
  • Texture analysis

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Zavaletta, V. A., Bartholmai, B. J., & Robb, R. A. (2007). Nonlinear histogram binning for quantitative analysis of lung tissue fibrosis in high-resolution CT data. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (PART 2 ed., Vol. 6511). [65111Q] https://doi.org/10.1117/12.710220

Nonlinear histogram binning for quantitative analysis of lung tissue fibrosis in high-resolution CT data. / Zavaletta, Vanessa A.; Bartholmai, Brian Jack; Robb, Richard A.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6511 PART 2. ed. 2007. 65111Q.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zavaletta, VA, Bartholmai, BJ & Robb, RA 2007, Nonlinear histogram binning for quantitative analysis of lung tissue fibrosis in high-resolution CT data. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. PART 2 edn, vol. 6511, 65111Q, Medical Imaging 2007: Physiology, Function, and Structure from Medical Images, San Diego, CA, United States, 2/18/07. https://doi.org/10.1117/12.710220
Zavaletta VA, Bartholmai BJ, Robb RA. Nonlinear histogram binning for quantitative analysis of lung tissue fibrosis in high-resolution CT data. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. PART 2 ed. Vol. 6511. 2007. 65111Q https://doi.org/10.1117/12.710220
Zavaletta, Vanessa A. ; Bartholmai, Brian Jack ; Robb, Richard A. / Nonlinear histogram binning for quantitative analysis of lung tissue fibrosis in high-resolution CT data. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6511 PART 2. ed. 2007.
@inproceedings{7c3ed0f36f36432c8b4f24aa5a28cf79,
title = "Nonlinear histogram binning for quantitative analysis of lung tissue fibrosis in high-resolution CT data",
abstract = "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.",
keywords = "Histogram binning, Lung tissue pathophysiology, Texture analysis",
author = "Zavaletta, {Vanessa A.} and Bartholmai, {Brian Jack} and Robb, {Richard A.}",
year = "2007",
doi = "10.1117/12.710220",
language = "English (US)",
isbn = "0819466298",
volume = "6511",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
edition = "PART 2",

}

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 Jack

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

SN - 0819466298

SN - 9780819466297

VL - 6511

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -