Lung four dimensional computed tomography (4D-CT) is of great value in tumor target localization and precise cancer radiotherapy. However, it is hard to segment tumors in 4D-CT data manually, since the data may contain a great number of slices with tumor. Meanwhile, auto-segmentation does not certainly guarantee the accuracy due to the complexity of images. Therefore, a new automatic segmentation technique based on Graph Cuts with star shape prior was proposed to increase automation and guarantee the accuracy of segmentation in our laboratory. Firstly, an object seed was selected in the image of initial phase and an initial target block was formed centering the selected seed. Then, the full search block-matching algorithm was adopted to obtain the most similar target block in the next phase and compute the motion field between them, and so on. Afterwards, the center seeds of each phase were obtained according to the motion fields, which would be set to the center point of star shape prior. Finally, tumors could be automatically segmented with Graph Cuts algorithm and star shape prior. Both qualitative and quantitative evaluation results showed that our approach could not only guarantee the accuracy of segmentation but also increase automation, compared with the traditional Graph Cuts algorithm.
The segmentation of the intracoronary optical coherence tomography (OCT) images is the basis of the plaque recognition, and it is important to the following plaque feature analysis, vulnerable plaque recognition and further coronary disease aided diagnosis. This paper proposes an algorithm about multi region plaque segmentation based on kernel graph cuts model that realizes accurate segmentation of fibrous, calcium and lipid pool plaques in coronary OCT image, while boundary information has been well reserved. We segmented 20 coronary images with typical plaques in our experiment, and compared the plaque regions segmented by this algorithm to the plaque regions obtained by doctor's manual segmentation. The results showed that our algorithm is accurate to segment the plaque regions. This work has demonstrated that it can be used for reducing doctors' working time on segmenting plaque significantly, reduce subjectivity and differences between different doctors, assist clinician's diagnosis and treatment of coronary artery disease.