Literature DB >> 1579432

[Assessment of the severity of interstitial lung diseases in chest radiographs using a computer-aided analysis system. A comparison with X-ray CT].

S Kido1.   

Abstract

A new computer-aided system to assess the severity of interstitial lung diseases in chest radiographs using proposed parameters, radiographic indices, was developed. The radiographic index is the normalized percent area of shadows in a ROI selected in the lung fields of chest radiographs. In the right lungs of 82 patients, 164 ROIs were processed by computerized methods such as filtering, binarization, determination and subtraction of linear shadows. In subtraction method, the image processed with determination of linear shadows is subtracted from the image filtered by 4-directional Laplacian-Gaussian filters. Then, the radiographic indices, Dbin (binarization), Dlin (linear shadow determination) and Dsub (subtraction), were obtained for the corresponding images. The combined radiographic index "Dcom" was calculated from "Dlin" and "Dsub". Values of these indices of the ROIs were compared with the grade (0-4) of the severity of interstitial involvement evaluated by CT. The results were obtained as follows: 1) Dbin, Dlin and Dcom provided good correlation with the severity throughout 5 grades, while Dsub did not. 2) As a parameter for detection of interstitial lung diseases, Dcom was significantly superior to the other indices (p less than .05). 3) As a parameter for assessment of severity of the diseases, Dlin showed the best performance and Dcom was the second best. Dlin and Dcom were superior to Dbin, and Dsub was inferior to Dbin. These results indicate that a new system is useful for assessment of the severity of interstitial lung diseases in chest radiographs.

Entities:  

Mesh:

Year:  1992        PMID: 1579432

Source DB:  PubMed          Journal:  Nihon Igaku Hoshasen Gakkai Zasshi        ISSN: 0048-0428


  1 in total

1.  Application of clinico-radiologic-pathologic diagnosis of diffuse parenchymal lung diseases in children in China.

Authors:  Dan Xu; Zhimin Chen; Huizhong Chen; Rongyan Huang; Shunying Zhao; Xiuyun Liu; Chunju Zhou; Yun Peng; Xinyu Yuan; Jizhen Zou; Hailing Zhang; Deyu Zhao; Enmei Liu; Yuejie Zheng; Lili Zhong; Min Lu; Jirong Lu; Guangmin Nong
Journal:  PLoS One       Date:  2015-01-08       Impact factor: 3.240

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.