Open AccessImproved chest disease detection with scanning equalization radiography
Author(s) -
JC Wandtke,
D B Plewes
Publication year - 1985
Publication title -
american journal of roentgenology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.294
H-Index - 196
eISSN - 1546-3141
pISSN - 0361-803X
DOI - 10.2214/ajr.145.5.979
Subject(s) - medicine , false positive paradox , radiography , true positive rate , radiology , equalization (audio) , nuclear medicine , artificial intelligence , algorithm , decoding methods , computer science
The efficacy of chest disease detection with scanning equalization radiography (SER) was evaluated in a clinical study of 95 patients: 51 normals and 44 with abnormal chest radiographs. A conventional and an SER image of each patient were interpreted independently by four radiologists. The increased numbers of true positives (3%) and true negatives (9%) when the SER images were interpreted were statistically significant. There was also a reduced number of false positives (7%) with SER. This improved disease detection was noted by each of the radiologists and led to more frequent agreement (11%) of the correct interpretation among the radiologists.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom