A novel active contour model for medical image segmentation (original) (raw)

2010, Journal of Shanghai Jiaotong University (Science)

A novel segmentation method for medical image with intensity inhomogeneity is introduced. In the proposed active contour model, both region and gradient information are taken into consideration. The former, i.e., region-based fitting energy, draws upon the region information and guarantees the accurate extraction of inhomogeneous image's local information. The latter, i.e., an edge indicator, weights the length penalizing term to consider the gradient constrain. Moreover, signed distance penalizing term is also added to ensure accurate computation and avoid the time-consuming re-initialization of evolving level set function. Experiments for synthetic and real images demonstrate the feasibility and superiority of the proposed model.

Sign up for access to the world's latest research.

checkGet notified about relevant papers

checkSave papers to use in your research

checkJoin the discussion with peers

checkTrack your impact