• 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
10.11606/D.18.2019.tde-04042019-103624
Document
Author
Full name
Lucas Exposto Soares
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2019
Supervisor
Committee
Vieira, Marcelo Andrade da Costa (President)
Batista Neto, João do Espírito Santo
Silva, Fernanda Paula Yamamoto
Title in Portuguese
Aplicação de técnicas de processamento de imagens para auxílio na detecção de fraturas radiculares verticais em radiografias periapicais digitais
Keywords in Portuguese
Fraturas radiculares verticais
Processamento digital de imagens
Radiografia periapical digital
Abstract in Portuguese
Fraturas radiculares verticais (FRV) são fraturas longitudinais que acontecem na raiz dos dentes. O diagnóstico clínico da FRV é um desafio, já que os pacientes não apresentam sinais e sintomas patognomônicos. Embora apresente limitações, a radiografia periapical deve ser o primeiro exame a ser realizado, pois possui menor custo e dose de radiação do que os exames tomográficos. O objetivo deste trabalho foi avaliar a contribuição de novas técnicas de processamento de imagens para o realce da FRV em radiografias periapicais digitais, visando facilitar sua detecção pelos odontologistas. O método de pré-processamento de imagem proposto foi composto de quatro etapas: ajuste geométrico+ negativo, filtragem de ruído, realce de contraste adaptativo e correção Gamma. Trinta radiografias periapicais digitais de dentes (fraturados ou não) tratados endodonticamente e com pino metálico instalado foram adquiridas. Resultados objetivos mostraram que o método desenvolvido aumentou o valor médio da razão contraste-ruído em 173% em comparação com o método de processamento tradicional fornecido pelo fabricante do equipamento. Testes subjetivos foram realizados com dez especialistas (radiologistas e endodontistas), que classificaram as imagens segundo a presença ou ausência de fratura. Os resultados indicaram que o método proposto melhorou a taxa de detecção de FRV pelos especialistas em 14%, em comparação com o método comercial, mas a especificidade foi reduzida. Dessa forma, a proposta deste trabalho pode ser utilizada como uma ferramenta complementar ao método de processamento tradicional, de modo a aumentar a sensibilidade do exame sem comprometer sua especificidade.
Title in English
Application of image processing techniques to assist detection of vertical root fractures in digital periapical radiographs
Keywords in English
Digital image processing
Digital periapical radiography
Vertical root fractures
Abstract in English
Vertical root fractures (VRF) are longitudinal fractures that occur at the root of the teeth. The clinical diagnosis of VRF is a challenge, since the patients have no pathognomonic signs and symptoms. Although it presents limitations, periapical radiography should be the first examination to be performed, because it has a lower cost and radiation dose than tomographic exams. The aim of this work was to evaluate the contribution of new image processing techniques for the enhancement of VRF in digital periapical radiographs, in order to facilitate its detection by dentists. The proposed image preprocessing method was composed of four steps: geometric adjustment+negative, noise filtering, adaptive contrast enhancement and Gamma correction. Thirty digital radiographs of teeth (fractured or not) treated endodontically and with installed metal pin were acquired. Objective results showed that the method developed increased the mean value of the contrast-to-noise ratio by 173% compared to the traditional processing method provided by the equipment manufacturer. Subjective tests were performed with ten examiners (radiologists and endodontists), who classified the images according to the presence or absence of fracture. The results indicated that the proposed method improved the detection rate of VRF by the examiners by 14% compared to the commercial method, but the specificity was reduced. Therefore, the proposal of this work can be used as a complementary tool to the traditional processing method, in order to increase the sensitivity of the test without compromising its specificity.
 
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
2019-04-08
 
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 © 2001-2021. All rights reserved.