Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloSegmentation of magnetic resonance brain images through discriminant analysis
Anno di pubblicazione2003
Formato-
Autore/iAmato, U and Larobina, M and Antoniadis, A and Alfano, B
Affiliazioni autoriAmato, U (Reprint Author), CNR, Sez Napoli, Ist Appl Calcolo Mauro Picone, Via Pietro Castellino 111, I-80132 Naples, Italy. CNR, Sez Napoli, Ist Appl Calcolo Mauro Picone, I-80132 Naples, Italy. CNR, Ist Biostrutt & Bioimmagini, I-80131 Naples, Italy. Univ Grenoble 1, Inst Informat & Math Appl Grenoble, F-38041 Grenoble, France.
Autori CNR e affiliazioni
  • UMBERTO AMATO
  • MICHELE LAROBINA
Lingua/e
  • inglese
AbstractSegmentation (tissue classification) of medical images obtained from a magnetic resonance (MR) system is a primary step in most applications of medical image post-processing. This paper describes nonparametric discriminant analysis methods to segment multispectral MR images of the brain. Starting from routinely available spin-lattice relaxation time, spin-spin relaxation time, and proton density weighted images (T(1)w, T(2)w, PDW), the proposed family of statistical methods is based on: (i) a transform of the images into components that are statistically independent from each other; (ii) a nonparametric estimate of probability density functions of each tissue starting from a training set; (iii) a classic Bayes 0-1 classification rule. Experiments based on a computer built brain phantom (brainweb) and on eight real patient data sets are shown. A comparison with parametric discriminant analysis is also reported. The capability of nonparametric discriminant analysis in improving brain tissue classification of parametric methods is demonstrated. Finally, an assessment of the role of multi spectrality in classifying brain tissues is discussed. (C) 2003 Elsevier B.V. All rights reserved.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da65
Pagine a74
Pagine totali-
RivistaJournal of neuroscience methods
Attiva dal 1979
Editore: Elsevier - Shannon ;
Paese di pubblicazione: Paesi Bassi
Lingua: inglese
ISSN: 0165-0270
Titolo chiave: Journal of neuroscience methods
Titolo proprio: Journal of neuroscience methods.
Titolo abbreviato: J. neurosci. methods
Numero volume della rivista131
Fascicolo della rivista1-2
DOI10.1016/S0165-0270(03)00237-1
Verificato da referee-
Stato della pubblicazione-
Indicizzazione (in banche dati controllate)
  • ISI Web of Science (WOS) (Codice:000187725400008)
Parole chiavemagnetic resonance imaging, brain, segmentation, discriminant analysis, principal component analysis, independent component analysis, kernel density estimation, INDEPENDENT COMPONENT ANALYSIS, ARTIFICIAL NEURAL NETWORKS, MR-IMAGES, AUTOMATED SEGMENTATION, MULTISPECTRAL ANALYSIS, CLASSIFICATION, ALGORITHM, LESIONS
Link (URL, URI)-
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • IBB — Istituto di biostrutture e bioimmagini
Moduli/Attività/Sottoprogetti CNR-
Progetti Europei-
Allegati
Segmentation of magnetic resonance brain images through discriminant analysis (documento privato )
Tipo documento: application/pdf