• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.59.2022.tde-27022023-074122
Document
Author
Full name
André Riccieri Albinati Silva Vitor
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
Ribeirão Preto, 2023
Supervisor
Committee
Cardoso, George Cunha (President)
Paula, Jayter Silva de
Pereira, Thiago Martini
Title in Portuguese
Mapas de melanina e oxiemoglobina para auxiliar redes neurais na classificação de imagens de retina
Keywords in Portuguese
Fundo de olho
Melanina
Oxiemoglobina
Redes neurais convolucionais
Abstract in Portuguese
A maioria das doenças oculares podem ser prevenidas e tratadas de maneira eficaz se detectadas precocemente. As redes neurais podem acelerar os processos de triagem das patologias oculares ao identificar previamente a presença de alguma doença. Uma vez que várias doenças estão relacionadas com o nível de oxigenação dos olhos, esta pode ser uma característica importante a ser analisada, visando o diagnóstico e tratamento. Neste trabalho utilizamos os mapas de densidade de oxiemoglobina e melanina em imagens de retinografia combinados de duas formas: 3 canais (tons de cinza, melanina e oxiemoglobina) ou 5 canais (vermelho, verde, azul, melanina e oxiemoglobina) e testamos essas combinações em 3 redes neurais convolucionais sendo uma delas um modelo pré-treinado.
Title in English
Melanin and oxyhemoglobin maps to improve neural networks in eye fundus images classification
Keywords in English
Convolutional neural networks
Eye fundus
Melanin
Oxyhemoglobin
Abstract in English
Several eye diseases can be prevented and treated effectively if detected early. Neural networks can speed up the processes of screening for eye diseases by identifying the presence of some disease in advance. Since several diseases are related to the oxygenation level of the eyes, this can be an important feature to be analyzed. In this work we use oxyhemoglobin and melanin density maps as new channels in convolutional neural networks and compare the results with pre-trained models.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2023-03-23
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.