ETD

Archivio digitale delle tesi discusse presso l'Università di Pisa

Tesi etd-05302011-155516


Tipo di tesi
Tesi di laurea specialistica
Autore
SALVETTI, FEDERICA
URN
etd-05302011-155516
Titolo
Design and comparison of Hidden Markov Models for pattern recognition of cerebral White Matter Lesions on MRI.
Dipartimento
INGEGNERIA
Corso di studi
INGEGNERIA DELLE TELECOMUNICAZIONI
Relatori
relatore Corsini, Giovanni
relatore Pham, Tuan
relatore Prof. Diani, Marco
Parole chiave
  • Hidden Markov Model
  • White Matter Lesions
  • MRI
  • pattern recognition
Data inizio appello
27/06/2011
Consultabilità
Parziale
Data di rilascio
27/06/2051
Riassunto
The research conducted in the present thesis proposes a computational neuroscience framework aiming to analyze the similarity/dissimilarity of white matter lesions (WML) patterns on FLAIR MRI, where WMLs appear hyperintense.
The study uses the concepts of Hidden Markov Model, fractals and phylogeny, which is used to discover the pattern of relationships of organisms.
The outcome of the proposed stochastic model is a tree where patients are grouped based on the relationship of their WMH patterns in term of size, shape and spatial distribution.
File