Mandible and Skull Segmentation in Cone Bean Computed Tomography Data

• Ano de defesa: 2017
• Autor(a) principal: Linares, Oscar Alonso Cuadros
• Tipo de documento: Tese
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Biblioteca Digitais de Teses e Dissertações da USP
• Palavras-chave em Português: Agrupamento em grafos; Bone segmentation; Cone bean computed tomography; Crânio; Graph clustering; Mandible; Mandíbula; Segmentação de ossos; Skull; Super voxels; Super- voxels; Tomografia computadorizada de feixe cônico
• Link de acesso: http://www.teses.usp.br/teses/disponiveis/55/55134/tde-24072018-165943/

Cone Beam Computed Tomography (CBCT) is a medical imaging technique routinely employed for diagnosis and treatment of patients with cranio-maxillo-facial defects. CBCT 3D reconstruction and segmentation of bones such as mandible or maxilla are essential procedures in orthodontic treatments. However, CBCT images present characteristics that are not desirable for processing, including low contrast, inhomogeneity, noise, and artifacts. Besides, values assigned to voxels are relative Hounsfield Units (HU), unlike traditional Computed Tomography (CT). Such drawbacks render CBCT segmentation a difficult and time-consuming task, usually performed manually with tools designed for medical image processing. We introduce two interactive two-stage methods for 3D segmentation of CBCT data: i) we first reduce the CBCT image resolution by grouping similar voxels into super-voxels defining a graph representation; ii) next, seeds placed by users guide graph clustering algorithms, splitting the bones into mandible and skull. We have evaluated our segmentation methods intensively by comparing the results against ground truth data of the mandible and the skull, in various scenarios. Results show that our methods produce accurate segmentation and are robust to changes in parameter settings. We also compared our approach with a similar segmentation strategy and we showed that it produces more accurate segmentation of the mandible and skull. In addition, we have evaluated our proposal with CT data of patients with deformed or missing bones. We obtained more accurate segmentation in all cases. As for the efficiency of our implementation, a segmentation of a typical CBCT image of the human head takes about five minutes. Finally, we carried out a usability test with orthodontists. Results have shown that our proposal not only produces accurate segmentation, as it also delivers an effortless and intuitive user interaction.