Region-based clustering for lung segmentation in low-dose CT images
Lung segmentation in thoracic computed tomography scans is essential for the development of computer-aided diagnostic methods for identifying the lung diseases. Low-dose CT scans are increasingly utilized in lung studies, but segmenting them with traditional threshold segmentation algorithms often y...
| Autor principal: | |
|---|---|
| Formato: | conferenceObject |
| Idioma: | eng |
| Publicado em: |
2010
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/10198/2631 |
| País: | Portugal |
| Oai: | oai:bibliotecadigital.ipb.pt:10198/2631 |
| Resumo: | Lung segmentation in thoracic computed tomography scans is essential for the development of computer-aided diagnostic methods for identifying the lung diseases. Low-dose CT scans are increasingly utilized in lung studies, but segmenting them with traditional threshold segmentation algorithms often yields less than satisfying results. In this paper we present a hybrid framework to lung segmentation which joints region-based information based on watershed transform with clustering techniques. The proposed method eliminates the task of finding an optimal threshold and the over-segmentation produced by watershed. We have applied our approach on several pulmonary low-dose CT images and the results reveal the robustness and accuracy of this method. |
|---|