TY - JOUR
T1 - Computerized analysis of interstitial infiltrates on chest radiographs
T2 - A new scheme based on geometric pattern features and fourier analysis
AU - Monnier-Cholley, Laurence
AU - MacMahon, Heber
AU - Katsuragawa, Shigehiko
AU - Morishita, Junji
AU - Doi, Kunio
N1 - Copyright:
Copyright 2015 Elsevier B.V., All rights reserved.
PY - 1995/6
Y1 - 1995/6
N2 - Rationale and Objectives.: Detection of interstitial infiltrates on chest radiographs is difficult and subjective. Therefore, we developed a computerized method to provide quantitative analysis of lung texture to increase diagnostic accuracy. Methods.: Two hundred chest radiographs-100 healthy and 100 abnormal with interstitial infiltrates-were digitized using a laser scanner. They were analyzed by an automated computerized scheme that uses a combination of two methods for detection of interstitial infiltrates: a lung texture analysis based on the Fourier transform and a geometric pattern feature analysis based on filtering techniques. Results.: The overall sensitivity and specificity of the computerized scheme were 92% and 90%, respectively. The scheme achieved a sensitivity of 80% in subtle cases (n = 15) and 88% in cases with localized interstitial disease (n = 26), whereas the specificity remained unchanged. There was good correlation between the computer output and the radiologists' severity rating. Conclusion.: This enhanced computerized scheme exhibits high sensitivity and specificity with a large database.
AB - Rationale and Objectives.: Detection of interstitial infiltrates on chest radiographs is difficult and subjective. Therefore, we developed a computerized method to provide quantitative analysis of lung texture to increase diagnostic accuracy. Methods.: Two hundred chest radiographs-100 healthy and 100 abnormal with interstitial infiltrates-were digitized using a laser scanner. They were analyzed by an automated computerized scheme that uses a combination of two methods for detection of interstitial infiltrates: a lung texture analysis based on the Fourier transform and a geometric pattern feature analysis based on filtering techniques. Results.: The overall sensitivity and specificity of the computerized scheme were 92% and 90%, respectively. The scheme achieved a sensitivity of 80% in subtle cases (n = 15) and 88% in cases with localized interstitial disease (n = 26), whereas the specificity remained unchanged. There was good correlation between the computer output and the radiologists' severity rating. Conclusion.: This enhanced computerized scheme exhibits high sensitivity and specificity with a large database.
UR - http://www.scopus.com/inward/record.url?scp=0029311387&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029311387&partnerID=8YFLogxK
U2 - 10.1016/S1076-6332(05)80399-X
DO - 10.1016/S1076-6332(05)80399-X
M3 - Article
C2 - 9419591
AN - SCOPUS:0029311387
VL - 2
SP - 455
EP - 462
JO - Academic Radiology
JF - Academic Radiology
SN - 1076-6332
IS - 6
ER -