Quantitative analysis of geometric-pattern features of interstitial infiltrates in digital chest radiographs: Preliminary results

Shigehiko Katsuragawa, Kunio Doi, Heber MacMahon, Laurence Monnier-Cholley, Junji Morishita, Takayuki Ishida

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

We are developing a computerized method for detection and characterization of interstitial diseases based on a quantitative analysis of geometric features of various infiltrate patterns in digital chest radiographs. In our approach, regions of interest (ROIs) with 128 × 128 matrix size (22.4 mm × 22.4 mm) are automatically selected, covering peripheral lung regions. Next, nodular and linear opacities, which are the basic components of interstitial infiltrates, are identified from two processed images obtained by use of a multiple-level thresholding technique and a line enhancement filter, respectively. Finally, the total area of nodular opacities and the total length of linear opacities in each ROI are determined as measures of geometric pattern features. We have applied this computer analysis to 72 ROIs with normal and abnormal patterns that were classified in advance by six chest radiologists. Preliminary results indicate that the distribution of measures of geometric-pattern features correlate well with radiologists' classification. These early results are encouraging, and further evaluation hopes to establish that this computerized method might prove useful to radiologists in their assessment of interstitial diseases.

Original languageEnglish
Pages (from-to)137-144
Number of pages8
JournalJournal of Digital Imaging
Volume9
Issue number3
DOIs
Publication statusPublished - 1996
Externally publishedYes

Fingerprint

Opacity
Thorax
Chemical analysis
Lung
Radiologists

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Cite this

Quantitative analysis of geometric-pattern features of interstitial infiltrates in digital chest radiographs : Preliminary results. / Katsuragawa, Shigehiko; Doi, Kunio; MacMahon, Heber; Monnier-Cholley, Laurence; Morishita, Junji; Ishida, Takayuki.

In: Journal of Digital Imaging, Vol. 9, No. 3, 1996, p. 137-144.

Research output: Contribution to journalArticle

Katsuragawa, Shigehiko ; Doi, Kunio ; MacMahon, Heber ; Monnier-Cholley, Laurence ; Morishita, Junji ; Ishida, Takayuki. / Quantitative analysis of geometric-pattern features of interstitial infiltrates in digital chest radiographs : Preliminary results. In: Journal of Digital Imaging. 1996 ; Vol. 9, No. 3. pp. 137-144.
@article{9045ba0a81264587923951ee51cdc02f,
title = "Quantitative analysis of geometric-pattern features of interstitial infiltrates in digital chest radiographs: Preliminary results",
abstract = "We are developing a computerized method for detection and characterization of interstitial diseases based on a quantitative analysis of geometric features of various infiltrate patterns in digital chest radiographs. In our approach, regions of interest (ROIs) with 128 × 128 matrix size (22.4 mm × 22.4 mm) are automatically selected, covering peripheral lung regions. Next, nodular and linear opacities, which are the basic components of interstitial infiltrates, are identified from two processed images obtained by use of a multiple-level thresholding technique and a line enhancement filter, respectively. Finally, the total area of nodular opacities and the total length of linear opacities in each ROI are determined as measures of geometric pattern features. We have applied this computer analysis to 72 ROIs with normal and abnormal patterns that were classified in advance by six chest radiologists. Preliminary results indicate that the distribution of measures of geometric-pattern features correlate well with radiologists' classification. These early results are encouraging, and further evaluation hopes to establish that this computerized method might prove useful to radiologists in their assessment of interstitial diseases.",
author = "Shigehiko Katsuragawa and Kunio Doi and Heber MacMahon and Laurence Monnier-Cholley and Junji Morishita and Takayuki Ishida",
year = "1996",
doi = "10.1007/BF03168609",
language = "English",
volume = "9",
pages = "137--144",
journal = "Journal of Digital Imaging",
issn = "0897-1889",
publisher = "Springer New York",
number = "3",

}

TY - JOUR

T1 - Quantitative analysis of geometric-pattern features of interstitial infiltrates in digital chest radiographs

T2 - Preliminary results

AU - Katsuragawa, Shigehiko

AU - Doi, Kunio

AU - MacMahon, Heber

AU - Monnier-Cholley, Laurence

AU - Morishita, Junji

AU - Ishida, Takayuki

PY - 1996

Y1 - 1996

N2 - We are developing a computerized method for detection and characterization of interstitial diseases based on a quantitative analysis of geometric features of various infiltrate patterns in digital chest radiographs. In our approach, regions of interest (ROIs) with 128 × 128 matrix size (22.4 mm × 22.4 mm) are automatically selected, covering peripheral lung regions. Next, nodular and linear opacities, which are the basic components of interstitial infiltrates, are identified from two processed images obtained by use of a multiple-level thresholding technique and a line enhancement filter, respectively. Finally, the total area of nodular opacities and the total length of linear opacities in each ROI are determined as measures of geometric pattern features. We have applied this computer analysis to 72 ROIs with normal and abnormal patterns that were classified in advance by six chest radiologists. Preliminary results indicate that the distribution of measures of geometric-pattern features correlate well with radiologists' classification. These early results are encouraging, and further evaluation hopes to establish that this computerized method might prove useful to radiologists in their assessment of interstitial diseases.

AB - We are developing a computerized method for detection and characterization of interstitial diseases based on a quantitative analysis of geometric features of various infiltrate patterns in digital chest radiographs. In our approach, regions of interest (ROIs) with 128 × 128 matrix size (22.4 mm × 22.4 mm) are automatically selected, covering peripheral lung regions. Next, nodular and linear opacities, which are the basic components of interstitial infiltrates, are identified from two processed images obtained by use of a multiple-level thresholding technique and a line enhancement filter, respectively. Finally, the total area of nodular opacities and the total length of linear opacities in each ROI are determined as measures of geometric pattern features. We have applied this computer analysis to 72 ROIs with normal and abnormal patterns that were classified in advance by six chest radiologists. Preliminary results indicate that the distribution of measures of geometric-pattern features correlate well with radiologists' classification. These early results are encouraging, and further evaluation hopes to establish that this computerized method might prove useful to radiologists in their assessment of interstitial diseases.

UR - http://www.scopus.com/inward/record.url?scp=0030201347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030201347&partnerID=8YFLogxK

U2 - 10.1007/BF03168609

DO - 10.1007/BF03168609

M3 - Article

C2 - 8854264

AN - SCOPUS:0030201347

VL - 9

SP - 137

EP - 144

JO - Journal of Digital Imaging

JF - Journal of Digital Imaging

SN - 0897-1889

IS - 3

ER -