3D segmentation of the head for assessing bone changes in odontology

• Grant number: 15/12771-7
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate
• Start date: October 05, 2015
• End date: September 04, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: João Do Espirito Santo Batista Neto
• Grantee: Oscar Alonso Cuadros Linares
• Supervisor: Bernd Hamann
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Institution abroad: University of California, Davis (UC Davis), United States
• Associated to the scholarship: 12/24036-1 - 3D segmentation of the head for assessing bone changes applied to Odontology., BP.DR

Abstract

This research project proposal is a requirement for a Research Internship Scholarship (BEPE) application, to be conducted at the University of California, Davis (UC Davis), USA, from September 1, 2015 to August 1, 2016. The work will be supervised by Prof. Bernd Hamann, from the Institute of Data Analysis and Visualization (IDAV). Computed Tomography plays a key role in Orthodontia, allowing, for example, investigations of changes in skull bones, following treatment with mandibular repositioning device. Such a study is performed by researchers from the Faculty of Odontology at UNESP in Araraquara (FOAR- UNESP), and consists of using tools to generate 3D segmentations of bony structures. However, these tools are labor intensive, time consuming and the segmentation of important structures are, often, not accurate enough to allow reliable measures. The current doctoral research aims to define an interactive 3D segmentation process of tomographies of the human skull to extract bones, such as, the mandible and the maxilla. The segmentation will be performed in two stages: a) construction of a probabilistic atlas of the human skull, which will provide a priori anatomical information and b) segmentation of a weighted graph built with the prior information provided by the atlas, in this graph, their vertices will be groups of similar voxels called Supervoxels. In addition, user interaction will be provided so that errors in segmentation can be corrected, by adding or removing supervoxels of different segments. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

LINARES, OSCAR CUADROS; BIANCHI, JONAS; RAVELI, DIRCEU; BATISTA NETO, JOAO; HAMANN, BERND. Mandible and skull segmentation in cone beam computed tomography using super-voxels and graph clustering. VISUAL COMPUTER, v. 35, n. 10, p. 1461-1474, OCT 2019. (12/24036-1, 15/12771-7)