Modeling Interaction for Segmentation of Neighboring Structures

• Published in: IEEE transactions on information technology in biomedicine Vol. 13; no. 2; pp. 252 - 262
• Main Authors: Pingkun Yan, Kassim, A.A., Weijia Shen, Shah, M.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2009
• Subjects: Algorithms; Amygdala - anatomy & histology; Anatomical structure; Biomedical imaging; Computer aided diagnosis; Computer science; Computer Simulation; Data mining; Diagnostic Imaging - methods; Energy minimization; Hippocampus - anatomy & histology; Humans; Image Processing, Computer-Assisted - methods; Image segmentation; interaction model; Lateral Ventricles - anatomy & histology; Level set; Medical diagnostic imaging; Models, Biological; neighboring structures; Robustness; segmentation; Shape; shape prior
• ISSN: 1089-7771; 1558-0032
• DOI: 10.1109/TITB.2008.2010492

This paper presents a new method for segmenting medical images by modeling interaction between neighboring structures. Compared to previously reported methods, the proposed approach enables simultaneous segmentation of multiple neighboring structures for improved robustness. During the segmentation process, the object contour evolution and shape prior estimates are influenced by the interactions between neighboring shapes consisting of attraction, repulsion, and competition. Instead of estimating the a priori shape of each structure independently, an interactive maximum a posteriori shape estimation method is used for estimating the shape priors by considering shape prior distribution, neighboring shapes, and image features. Energy functionals are then formulated to model the interaction and segmentation. With the proposed method, neighboring structures with similar intensities and/or textures, and blurred boundaries can be extracted simultaneously. Experimental results obtained on both synthetic data and medical images demonstrate that the introduced interaction between neighboring structures improves segmentation performance compared with other existing approaches.