Pediatric Pulmonary Disease and Sleep Medicine Research Center

Tehrān, Iran

Pediatric Pulmonary Disease and Sleep Medicine Research Center

Tehrān, Iran
SEARCH FILTERS
Time filter
Source Type

Naseri Samaghcheh Z.,K. N. Toosi University of Technology | Abdoli F.,K. N. Toosi University of Technology | Abrishami Moghaddam H.,K. N. Toosi University of Technology | Modaresi M.,Childrens Medical Center | And 2 more authors.
Signal, Image and Video Processing | Year: 2017

A new framework for model-based lung tissue segmentation in three-dimensional thoracic CT images is proposed. In the first stage, a parametric model for lung segmenting surface is created using shape representation based on level sets method. This model is constituted by the sum of a mean distance function and a number of weighted eigenshapes. Consequently, unlike the other model-based segmentation methods, there is no need to specify any marker point in this model. In the second stage, the segmenting surface is varied so as to be matched with the binarized input image. For this purpose, a region-based energy function is minimized with respect to the parameters including the weights of eigenshapes and coefficients of a three-dimensional similarity transform. Finally, the resulted segmenting surface is post-processed in order to improve its fitness with the lung borders of the input image. The experimental results demonstrated the outperformance of the proposed framework over its model-based counterparts in model matching stage. Moreover, it performed slightly better in terms of final segmentation results. © 2017 Springer-Verlag London Ltd.

Loading Pediatric Pulmonary Disease and Sleep Medicine Research Center collaborators
Loading Pediatric Pulmonary Disease and Sleep Medicine Research Center collaborators