Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/53097
Título: | Kidney segmentation in 3D CT images using B-Spline Explicit Active Surfaces |
Autor(es): | Torres, Helena R. Oliveira, Bruno Queiros, Sandro Morais, Pedro Fonseca, Jaime C. D'hooge, Jan Rodrigues, Nuno F. Vilaca, Joao L. |
Palavras-chave: | B-Spline Explicit Active Surfaces Computed Tomography Kidney segmentation Surface analysis Volumetric analysis |
Data: | 2016 |
Editora: | IEEE |
Revista: | IEEE International Conference on Serious Games and Applications for Health |
Resumo(s): | In this manuscript, we propose to adapt the B-Spline Explicit Active Surfaces (BEAS) framework for semi-automatic kidney segmentation in computed tomography (CT) images. To study the best energy functional for kidney CT extraction, three different localized region-based energies were implemented within the BEAS framework, namely localized Chan-Vese, localized Yezzi, and signed localized Yezzi energies. Moreover, a novel gradient-based regularization term is proposed. The method was applied on 18 kidneys from 9 CT datasets, with different image properties. Several energy combinations were contrasted using surface-based comparison against ground truth meshes, assessing their accuracy and robustness against surface initialization. Overall, the hybrid energy functional combining the localized signed Yezzi energy with gradient-based regularization simultaneously showed the highest accuracy and the lowest sensitivity to the initialization. Volumetric analysis demonstrated the feasibility of the method from a clinical point of view, with similar reproducibility to manual observers. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/53097 |
ISBN: | 978-150902209-0 |
DOI: | 10.1109/SeGAH.2016.7586276 |
ISSN: | 2330-5649 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | DEI - Artigos em atas de congressos internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
07586276.pdf | 1,83 MB | Adobe PDF | Ver/Abrir |