Virtual bacterium colony in 3D image segmentation

• Published in: Computerized medical imaging and graphics Vol. 65; pp. 152 - 166
• Main Author: Badura, Pawel
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.04.2018; Elsevier Science Ltd
• Subjects: Algorithms; Artificial Intelligence; Bacteria - growth & development; Colonies; Computed tomography; Computer graphics; Computer-aided diagnosis; Data mining; Data processing; Image processing; Image segmentation; Imaging, Three-Dimensional; Intelligence; Internal Medicine; Medical diagnosis; Medical imaging; Multiagent systems; Optimization; Other; Social behavior; Swarm intelligence; Ultrasound; Virtual Reality; Image segmentation; Multiagent systems; Swarm intelligence; Artificial intelligence; Computer-aided diagnosis
• ISSN: 0895-6111; 1879-0771; 1879-0771
• DOI: 10.1016/j.compmedimag.2017.04.004

•A novel virtual bacterium colony technique (BCS) is proposed for 3D image segmentation.•Multiple stimuli involving social behaviour and memory mechanisms control the swarm motion.•Virtual bacteria employ stigmergy to communicate and make decisions.•Evaluation is based on synthetic data, computed tomography studies, and ultrasound images. Several heuristic, biologically inspired strategies have been discovered in recent decades, including swarm intelligence algorithms. So far, their application to volumetric imaging data mining is, however, limited. This paper presents a new flexible swarm intelligence optimization technique for segmentation of various structures in three- or two-dimensional images. The agents of a self-organizing colony explore their host, use stigmergy to communicate themselves, and mark regions of interest leading to the object extraction. Detailed specification of the bacterium colony segmentation (BCS) technique in terms of both individual and social behaviour is described in this paper. The method is illustrated and evaluated using several experiments involving synthetic data, computed tomography studies, and ultrasonography images. The obtained results and observations are discussed in terms of parameter settings and potential application of the method in various segmentation tasks.