Joint segmentation and registration for 4D lung CT images based on Markov random field

Abstract

The study of segmentation and registration of lung volume in medical images has been an active area with the emergence and development of 4D CT (Computed Tomography) medical imaging techniques. Precise image segmentation and registration methods are becoming more and more important in computer-aided diagnosis and treatment. Despite the significant progress which has been made in the medical image segmentation and registration, lung segmentation and registration is still a challenging task. In this paper, a joint segmentation and registration method for 4D lung CT images is proposed, which extends a general simultaneous segmentation and registration framework based on MRF (Markov Random Field) and utilizes the segmentation results of one frame as an atlas for the initialization step. Furthermore, a stochastic sampling approach is introduced for the computation of registration similarity measurement. The proposed method is evaluated on a public lung CT data set and the experimental results show its improved performance compared with the conventional methods.