Computer-aided detection of early interstitial lung diseases using low-dose CT images

Sang Cheol Park, Jun Tan, Xingwei Wang, Dror Lederman, Joseph K. Leader, Soo Hyung Kim, Bin Zheng

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

This study aims to develop a new computer-aided detection (CAD) scheme to detect early interstitial lung disease (ILD) using low-dose computed tomography (CT) examinations. The CAD scheme classifies each pixel depicted on the segmented lung areas into positive or negative groups for ILD using a mesh-grid-based region growth method and a multi-feature-based artificial neural network (ANN). A genetic algorithm was applied to select optimal image features and the ANN structure. In testing each CT examination, only pixels selected by the mesh-grid region growth method were analyzed and classified by the ANN to improve computational efficiency. All unselected pixels were classified as negative for ILD. After classifying all pixels into the positive and negative groups, CAD computed a detection score based on the ratio of the number of positive pixels to all pixels in the segmented lung areas, which indicates the likelihood of the test case being positive for ILD. When applying to an independent testing dataset of 15 positive and 15 negative cases, the CAD scheme yielded the area under receiver operating characteristic curve (AUC = 0.884 ± 0.064) and 80.0% sensitivity at 85.7% specificity. The results demonstrated the feasibility of applying the CAD scheme to automatically detect early ILD using low-dose CT examinations.

Original languageEnglish (US)
Pages (from-to)1139-1153
Number of pages15
JournalPhysics in Medicine and Biology
Volume56
Issue number4
DOIs
StatePublished - Feb 21 2011

Fingerprint

Interstitial Lung Diseases
Tomography
Lung
Growth
ROC Curve
Area Under Curve

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

Park, S. C., Tan, J., Wang, X., Lederman, D., Leader, J. K., Kim, S. H., & Zheng, B. (2011). Computer-aided detection of early interstitial lung diseases using low-dose CT images. Physics in Medicine and Biology, 56(4), 1139-1153. https://doi.org/10.1088/0031-9155/56/4/016

Computer-aided detection of early interstitial lung diseases using low-dose CT images. / Park, Sang Cheol; Tan, Jun; Wang, Xingwei; Lederman, Dror; Leader, Joseph K.; Kim, Soo Hyung; Zheng, Bin.

In: Physics in Medicine and Biology, Vol. 56, No. 4, 21.02.2011, p. 1139-1153.

Research output: Contribution to journalArticle

Park, SC, Tan, J, Wang, X, Lederman, D, Leader, JK, Kim, SH & Zheng, B 2011, 'Computer-aided detection of early interstitial lung diseases using low-dose CT images', Physics in Medicine and Biology, vol. 56, no. 4, pp. 1139-1153. https://doi.org/10.1088/0031-9155/56/4/016
Park, Sang Cheol ; Tan, Jun ; Wang, Xingwei ; Lederman, Dror ; Leader, Joseph K. ; Kim, Soo Hyung ; Zheng, Bin. / Computer-aided detection of early interstitial lung diseases using low-dose CT images. In: Physics in Medicine and Biology. 2011 ; Vol. 56, No. 4. pp. 1139-1153.
@article{425e6ffdc855429ca2743f5f1fc83537,
title = "Computer-aided detection of early interstitial lung diseases using low-dose CT images",
abstract = "This study aims to develop a new computer-aided detection (CAD) scheme to detect early interstitial lung disease (ILD) using low-dose computed tomography (CT) examinations. The CAD scheme classifies each pixel depicted on the segmented lung areas into positive or negative groups for ILD using a mesh-grid-based region growth method and a multi-feature-based artificial neural network (ANN). A genetic algorithm was applied to select optimal image features and the ANN structure. In testing each CT examination, only pixels selected by the mesh-grid region growth method were analyzed and classified by the ANN to improve computational efficiency. All unselected pixels were classified as negative for ILD. After classifying all pixels into the positive and negative groups, CAD computed a detection score based on the ratio of the number of positive pixels to all pixels in the segmented lung areas, which indicates the likelihood of the test case being positive for ILD. When applying to an independent testing dataset of 15 positive and 15 negative cases, the CAD scheme yielded the area under receiver operating characteristic curve (AUC = 0.884 ± 0.064) and 80.0{\%} sensitivity at 85.7{\%} specificity. The results demonstrated the feasibility of applying the CAD scheme to automatically detect early ILD using low-dose CT examinations.",
author = "Park, {Sang Cheol} and Jun Tan and Xingwei Wang and Dror Lederman and Leader, {Joseph K.} and Kim, {Soo Hyung} and Bin Zheng",
year = "2011",
month = "2",
day = "21",
doi = "10.1088/0031-9155/56/4/016",
language = "English (US)",
volume = "56",
pages = "1139--1153",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "4",

}

TY - JOUR

T1 - Computer-aided detection of early interstitial lung diseases using low-dose CT images

AU - Park, Sang Cheol

AU - Tan, Jun

AU - Wang, Xingwei

AU - Lederman, Dror

AU - Leader, Joseph K.

AU - Kim, Soo Hyung

AU - Zheng, Bin

PY - 2011/2/21

Y1 - 2011/2/21

N2 - This study aims to develop a new computer-aided detection (CAD) scheme to detect early interstitial lung disease (ILD) using low-dose computed tomography (CT) examinations. The CAD scheme classifies each pixel depicted on the segmented lung areas into positive or negative groups for ILD using a mesh-grid-based region growth method and a multi-feature-based artificial neural network (ANN). A genetic algorithm was applied to select optimal image features and the ANN structure. In testing each CT examination, only pixels selected by the mesh-grid region growth method were analyzed and classified by the ANN to improve computational efficiency. All unselected pixels were classified as negative for ILD. After classifying all pixels into the positive and negative groups, CAD computed a detection score based on the ratio of the number of positive pixels to all pixels in the segmented lung areas, which indicates the likelihood of the test case being positive for ILD. When applying to an independent testing dataset of 15 positive and 15 negative cases, the CAD scheme yielded the area under receiver operating characteristic curve (AUC = 0.884 ± 0.064) and 80.0% sensitivity at 85.7% specificity. The results demonstrated the feasibility of applying the CAD scheme to automatically detect early ILD using low-dose CT examinations.

AB - This study aims to develop a new computer-aided detection (CAD) scheme to detect early interstitial lung disease (ILD) using low-dose computed tomography (CT) examinations. The CAD scheme classifies each pixel depicted on the segmented lung areas into positive or negative groups for ILD using a mesh-grid-based region growth method and a multi-feature-based artificial neural network (ANN). A genetic algorithm was applied to select optimal image features and the ANN structure. In testing each CT examination, only pixels selected by the mesh-grid region growth method were analyzed and classified by the ANN to improve computational efficiency. All unselected pixels were classified as negative for ILD. After classifying all pixels into the positive and negative groups, CAD computed a detection score based on the ratio of the number of positive pixels to all pixels in the segmented lung areas, which indicates the likelihood of the test case being positive for ILD. When applying to an independent testing dataset of 15 positive and 15 negative cases, the CAD scheme yielded the area under receiver operating characteristic curve (AUC = 0.884 ± 0.064) and 80.0% sensitivity at 85.7% specificity. The results demonstrated the feasibility of applying the CAD scheme to automatically detect early ILD using low-dose CT examinations.

UR - http://www.scopus.com/inward/record.url?scp=79551700582&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79551700582&partnerID=8YFLogxK

U2 - 10.1088/0031-9155/56/4/016

DO - 10.1088/0031-9155/56/4/016

M3 - Article

C2 - 21263171

AN - SCOPUS:79551700582

VL - 56

SP - 1139

EP - 1153

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 4

ER -