Title :
Fast-learning neural classifier for chest radiograph
Author :
Soliz, P. ; Coons, T. ; Coultas, D. ; James, D.
Author_Institution :
Kestrel Corp., Albuquerque, NM, USA
Abstract :
To reduce inter- and intra-reader variability in diagnosing chest radiographs, a neural network-based system was developed and tested. The results of an experiment with 65 digitized chest radiographs, demonstrated high degree of sensitivity and specificity in classifying these X-rays. The use of a computer-assisted chest radiograph reader eliminated the inconsistencies in the human readers
Keywords :
diagnostic radiography; image classification; medical image processing; neural nets; computer-assisted chest radiograph reader; fast-learning neural classifier; human reader inconsistencies elimination; interreader variability; intrareader variability; medical diagnostic imaging; sensitivity; specificity; Diagnostic radiography; Entropy; Fractals; Humans; Image recognition; Neural networks; Proposals; Sensitivity and specificity; System testing; X-rays;
Conference_Titel :
[Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-5674-8
DOI :
10.1109/IEMBS.1999.804305
