Graph cut based co-segmentation of lung tumor in PET-CT images

Wei Ju; Dehui Xiang; Bin Zhang; Xinjian Chen

doi:10.1117/12.2081858

Translator Disclaimer

20 March 2015 Graph cut based co-segmentation of lung tumor in PET-CT images

Wei Ju; Dehui Xiang; Bin Zhang; Xinjian Chen

Author Affiliations +

Proceedings Volume 9413, Medical Imaging 2015: Image Processing; 94133K (2015) https://doi.org/10.1117/12.2081858
Event: SPIE Medical Imaging, 2015, Orlando, Florida, United States

Abstract

Accurate segmentation of pulmonary tumor is important for clinicians to make appropriate diagnosis and treatment. Positron Emission Tomography (PET) and Computed Tomography (CT) are two commonly used imaging technologies for image-guided radiation therapy. In this study, we present a graph-based method to integrate the two modalities to segment the tumor simultaneously on PET and CT images. The co-segmentation problem is formulated as an energy minimization problem. Two weighted sub-graphs are constructed for PET and CT. The characteristic information of the two modalities is encoded on the edges of the graph. A context cost is enforced by adding context arcs to achieve consistent results between the two modalities. An optimal solution can be achieved by solving a maximum flow problem. The proposed segmentation method was validated on 18 sets of PET-CT images from different patients with non-small cell lung cancer (NSCLC). The quantitative results show significant improvement of our method with a mean DSC value 0.82.

Citation Download Citation

Wei Ju, Dehui Xiang, Bin Zhang, and Xinjian Chen "Graph cut based co-segmentation of lung tumor in PET-CT images", Proc. SPIE 9413, Medical Imaging 2015: Image Processing, 94133K (20 March 2015); https://doi.org/10.1117/12.2081858

ACCESS THE FULL ARTICLE