Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Localization of epileptogenic zones in F-18FDG brain PET of patients with temporal lobe epilepsy using artificial neural network
Autore:
Lee, JS; Lee, DS; Kim, SK; Lee, SK; Chung, JK; Lee, MC; Park, KS;
Indirizzi:
Seoul Natl Univ, Coll Med, Dept Nucl Med, Seoul 110799, South Korea Seoul Natl Univ Seoul South Korea 110799 Med, Seoul 110799, South Korea Seoul Natl Univ, Interdisciplinary Program Med & Biol Engn Major, Seoul, South Korea Seoul Natl Univ Seoul South Korea & Biol Engn Major, Seoul, South Korea Seoul Natl Univ, Coll Med, Dept Neurol, Seoul, South Korea Seoul Natl Univ Seoul South Korea Med, Dept Neurol, Seoul, South Korea Seoul Natl Univ, Coll Med, Dept Biomed Engn, Seoul 110799, South Korea Seoul Natl Univ Seoul South Korea 110799 Engn, Seoul 110799, South Korea
Titolo Testata:
IEEE TRANSACTIONS ON MEDICAL IMAGING
fascicolo: 4, volume: 19, anno: 2000,
pagine: 347 - 355
SICI:
0278-0062(200004)19:4<347:LOEZIF>2.0.ZU;2-E
Fonte:
ISI
Lingua:
ENG
Soggetto:
ALZHEIMERS-DISEASE SUBJECTS; IMAGES; SPECT; CLASSIFICATION; NORMALIZATION; REGISTRATION; MRI;
Keywords:
artificial neural network; brain PET; epilepsy; spatial normalization;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Clinical Medicine
Engineering, Computing & Technology
Citazioni:
18
Recensione:
Indirizzi per estratti:
Indirizzo: Lee, DS Seoul Natl Univ, Coll Med, Dept Nucl Med, Seoul 110799, South Korea Seoul Natl Univ Seoul South Korea 110799 oul 110799, South Korea
Citazione:
J.S. Lee et al., "Localization of epileptogenic zones in F-18FDG brain PET of patients with temporal lobe epilepsy using artificial neural network", IEEE MED IM, 19(4), 2000, pp. 347-355

Abstract

For an objective interpretation of cerebral metabolic pattern to find epileptogenic zones in patients with temporal lobe epilepsy (TLE), we developeda computer-aided classifier using an artificial neural network (ANN). We studied 261 epilepsy patients diagnosed as no abnormal findings (NA, n = 64), left TLE (n. = 116), or right TLE (n = 81) on interictal brain F-18-flurodeoxyglucose positron emission tomography (FDG PET) by the consensus of twoexpert physicians. Seventeen asymmetry indexes between the mean counts of the 34 mirrored regions were extracted from the spatially normalized imagesand used as input parameters. The three diagnoses of NA, left TLE, and right TLE were used as outputs of the ANN, The structure of the ANN was optimized with variable error goals and the number of hidden units. On the criteria of agreement of diagnoses with those of expert viewers, the best classifier was chosen, which yielded a maximum average agreement of 85% for the test set when we used an error goal of 20 (sum of squared error) and ten hidden units. We could devise an ANN that performed as well in diagnosing left or right TLE on FDG PET as human experts and could be used as a clinical decision support tool.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 01/04/20 alle ore 11:46:40