A study to determine the feasibility of computer diagnosis of the pneumoconioses.
-
1974/01/01
-
By Kruger RP
Details
-
Personal Author:
-
Description:The feasibility of possible automated mass diagnostic screening of pneumoconiosis radiography was investigated. Two distinct textural feature extraction methods involving digital and coherent optical approaches were studied. The performance of the two automated diagnostic systems is detailed. Analogous results are presented for diagnosis obtained from experienced radiologists analyzing the same films given to the automated systems. Normal/Abnormal classification accuracy for the optical system was 90.8 percent. Comparable percentages for the physicians ranged from 83.0 percent to 97.9 percent. (It is noted that the physician who accuracy was 97.9 percent is a radiologist with extensive experience at diagnosing pneumoconiosis.) Likewise, the missed abnormal testing rate for the optical system was 2.9 percent. Comparable rates for the physicians ranged from 1.0 percent to 6.9 percent. The digital system also compared well with the physician results, though it is important to note that only a subset of films was available for digital processing. (Contract No. 099-72-0030) [Description provided by NIOSH]
-
Content Notes:in NTRL, no PDF
-
Subjects:
-
Keywords:
-
Document Type:
-
Funding:
-
Genre:
-
Place as Subject:
-
CIO:
-
Topic:
-
Location:
-
Pages in Document:1-86
-
NIOSHTIC Number:nn:00068883
-
Citation:NIOSH 1974 Jan; :1-86
-
Federal Fiscal Year:1974
-
NORA Priority Area:
-
Performing Organization:University of Southern California, Los Angeles, California
-
Peer Reviewed:False
-
Source Full Name:National Institute for Occupational Safety and Health
-
Collection(s):
-
Main Document Checksum:urn:sha-512:7dc847c09aedf140bc731323e8446b4703641ae07d6ad9e7b7238120dab30b8f7dcaa9b938d34d035f87873a0fe7fec262d5d13dcaf290925445e82b6de3b57d
-
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