Neural network and conventional classifiers for fluorescence-guided laser angioplasty

The ability of the back-propagation and K-nearest-neighbors techniques to classify arterial fluorescence spectra is investigated. Both methods are competitive with other classification schemes. The best validation set accuracy on the aortic data was obtained by the 1-nearest-neighbor method (98% cor...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on biomedical engineering 1991-03, Vol.38 (3), p.246-252
Main Authors: Gindi, G.R., Darken, C.J., O'Brien, K.M., Stetz, M.L., Deckelbaum, L.I.
Format: Article
Language:English
Subjects:
Angioplasty
Angioplasty, Laser
Arteriosclerosis - classification
Arteriosclerosis - surgery
Artificial Intelligence
Biological and medical sciences
Computed tomography
Diagnosis, Computer-Assisted
Diseases
Fluorescence
Humans
Laser ablation
Laser surgery
Medical sciences
Neural networks
Optical imaging
Pattern Recognition, Automated
Surgery (general aspects). Transplantations, organ and tissue grafts. Graft diseases
Testing
Ultrasonic imaging
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The ability of the back-propagation and K-nearest-neighbors techniques to classify arterial fluorescence spectra is investigated. Both methods are competitive with other classification schemes. The best validation set accuracy on the aortic data was obtained by the 1-nearest-neighbor method (98% correct overall on the test exemplars). The 22-8-1 and 22-8-4-1 networks performed second best, misclassifying only one more exemplar, at 96%. All performances on the coronary data were much poorer. The relative performance of variations on both techniques is used to make inferences about the geometry of the classification task.< >
ISSN:0018-9294
1558-2531
DOI:10.1109/10.133205