Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Differentiation of intracardiac tumors and thrombi by echocardiographic tissue characterization: Comparison of an artificial neural network and humanobservers
Autore:
Gerber, TC; Foley, DA; Zheng, Y; Behrenbeck, T; Tajik, AJ; Seward, JB;
Indirizzi:
Mayo Clin & Mayo Fdn, Div Cardiovasc Dis & Internal Med, Rochester, MN 55905 USA Mayo Clin & Mayo Fdn Rochester MN USA 55905 Med, Rochester, MN 55905 USA
Titolo Testata:
ECHOCARDIOGRAPHY-A JOURNAL OF CARDIOVASCULAR ULTRASOUND AND ALLIED TECHNIQUES
fascicolo: 2, volume: 17, anno: 2000,
pagine: 115 - 126
SICI:
0742-2822(200002)17:2<115:DOITAT>2.0.ZU;2-T
Fonte:
ISI
Lingua:
ENG
Soggetto:
TWO-DIMENSIONAL ECHOCARDIOGRAMS; DIFFUSE LIVER-DISEASE; LEFT-VENTRICULAR THROMBI; TEXTURE ANALYSIS; PATTERN-RECOGNITION; IMAGE TEXTURE; DIAGNOSTIC ULTRASOUND; ATRIAL MYXOMAS; CLASSIFICATION; ULTRASONOGRAPHY;
Keywords:
intracardiac masses; neural networks; pattern recognition; transesophageal ultrasound; ultrasonic tissue characterization;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Clinical Medicine
Citazioni:
64
Recensione:
Indirizzi per estratti:
Indirizzo: Foley, DA Mayo Clin & Mayo Fdn, Div Cardiovasc Dis & Internal Med, 200 1stSt SW, Rochester, MN 55905 USA Mayo Clin & Mayo Fdn 200 1st St SW Rochester MN USA 55905 05 USA
Citazione:
T.C. Gerber et al., "Differentiation of intracardiac tumors and thrombi by echocardiographic tissue characterization: Comparison of an artificial neural network and humanobservers", ECHOCARDIOG, 17(2), 2000, pp. 115-126

Abstract

The feasibility of classifying ultrasound images of intracardiac tumors and thrombi with a neural network-based algorithm was compared with the performance of experienced echocardiographers. The neural network used statistical descriptors of the apparent echocardiographic texture of the masses, andthe blinded echocardiographers were given photographic prints of enlarged regions of interest without clinical data. The network classified 66% of the images correctly and the echocardiographers, 83%. The network and echocardiographers agreed in 88% of the images. Human observers usually base theirclassification of intracardiac masses on clinical data. The echocardiographic texture of tumors is quantitatively different from that of thrombi. This difference can be recognized by a neural network and potentially be useful in assisting with the diagnosis when clinical clues are insufficient.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 29/09/20 alle ore 12:35:27