An algorithm for the detection of small rounded pneumoconiosis opacities in chest x-rays and its application to automatic diagnosis.
Public Domain
-
1990/09/01
-
Details
-
Personal Author:
-
Description:A new method was presented to identify small rounded opacities of pneumoconiosis and to classify the grade of their density. The new method was based on the processing of local density patterns. The method was used in the processing of 11 International Labor Office 1980 standard films whose opacity shapes were rounded. Pneumoconiosis opacities identified by an expert reader and those detected by the proposed method were compared. The number of pneumoconiosis opacities identified by an expert reader and that detected by the proposed method were 120 and 109, respectively. Among them, 66 opacities coincided with each other. The proposed method was not sensitive to the changes of film quality, which was superior to texture analytic approaches. The correct classification rate by the proposed method was demonstrated to be comparable to them. However, many false opacities were detected as pneumoconiosis opacities; therefore, the authors conclude that further improvement of the method is needed.
-
Subjects:
-
Keywords:
-
Publisher:
-
Document Type:
-
Genre:
-
Place as Subject:
-
CIO:
-
Topic:
-
Location:
-
Pages in Document:492-494
-
NIOSHTIC Number:nn:00198449
-
Citation:Proceedings of the VIIth International Pneumoconioses Conference, August 23-26, 1988, Pittsburgh, Pennsylvania, USA. Atlanta, GA: U.S. Department of Health and Human Services, Public Health Service, Centers for Disease Control, National Institute for Occupational Safety and Health, DHHS (NIOSH) Publication No. 90-108, 1990 Sep; (Part I):492-494
-
Federal Fiscal Year:1990
-
Peer Reviewed:False
-
Part Number:I
-
Source Full Name:Proceedings of the VIIth International Pneumoconioses Conference, August 23-26, 1988, Pittsburgh, Pennsylvania, USA
-
Collection(s):
-
Main Document Checksum:urn:sha-512:bfdc447b17e0112f7922916415f14970bb7d0502cb7042e33fe35991e0029e9e7736d9eb2f9e4b1e0926513049179f283a0415cdac370718497cc109264f7d95
-
Download URL:
-
File Type:
ON THIS PAGE
CDC STACKS serves as an archival repository of CDC-published products including
scientific findings,
journal articles, guidelines, recommendations, or other public health information authored or
co-authored by CDC or funded partners.
As a repository, CDC STACKS retains documents in their original published format to ensure public access to scientific information.
As a repository, CDC STACKS retains documents in their original published format to ensure public access to scientific information.
You May Also Like