Por favor, use este identificador para citar o enlazar este ítem: http://redi.ufasta.edu.ar:8082/jspui/handle/123456789/1212
Título : Magnetic resonance volumetric techniques: a new segmentation method based on interval type-2 fuzzy logic and clinical applications
metadata.dc.creator: Comas, Diego
Meschino, Gustavo
Costantino, Sebastián
Pastore, Juan
Capiel, Carlos
Ballarín, Virginia
Palabras clave : Informática y Salud
metadata.dc.date: 2016
Editorial : Universidad FASTA. Facultad de Ingeniería
Descripción : Fil: Comas, Diego. Universidad FASTA. Facultad de Ingeniería; Argentina.
Fil: Meschino, Gustavo. Universidad FASTA. Facultad de Ingeniería; Argentina.
Fil: Costantino, Sebastián. Universidad FASTA. Facultad de Ingeniería; Argentina.
Fil: Pastore, Juan. Universidad FASTA. Facultad de Ingeniería; Argentina.
Fil: Capiel, Carlos. Universidad FASTA. Facultad de Ingeniería; Argentina.
Fil: Ballarín, Virginia. Universidad FASTA. Facultad de Ingeniería; Argentina.
The analysis of structural changes in the brain through magnetic resonance imaging (MRI) provides useful information for diagnosis and clinical treatment of patients with some pathologies, like Alzheimer disease and dementia. While complexity achieved by the MRI equipment is high, quantification of structures and tissues has not been entirely solved. This paper presents a method for segmentation of magnetic resonance images of the brain, based on a classification method using interval type-2 fuzzy logic called Type-2 Label-based Fuzzy Predicate Classification (T2-LFPC) which enables computing volumes occupied for the different tissues into the intracranial cavity. In the first stage, a random partition of observations is performed. Data contained in data subsets are analyzed, applying clustering to the observations corresponding to each class in order to discover groups of data with similar properties. Then, interval type-2 membership functions and fuzzy predicates are defined. In the final stage, optimization of parameters regarding the classification system is done. A comparison against various known classification methods was performed. A method of measuring the progressive atrophy and possible changes compared to a therapeutic effect should be essentially automatic and therefore independent of the radiologist. Results show that the performance of the proposed method is highly acceptable as a contribution for this goal. Advantages of this approach are presented throughout this paper.
URI : http://redi.ufasta.edu.ar:8082/jspui/handle/123456789/1212
Aparece en las colecciones: Facultad de Ingeniería - G.I - Informática y Salud

Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
Paper Tandil 2016-Informática y Salud.pdf593,15 kBAdobe PDFVisualizar/Abrir


Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.