Region growing segmentation of ultrasound images using gradients and local statistics

This paper describes a region growing segmentation algorithm for medical ultrasound images. The algorithm starts with anisotropic diffusion filtering to reduce speckle noise without blurring the edges. Then, region growing is performed starting from a seed point, using a merging criterion that compares intensity gradients to the noise level inside the region. Finally, the boundaries are smoothed using morphological closing. The algorithm was evaluated with two simulated images and eleven phantom images and converged in 10 of them with accurate region delimitation. Preliminary results show that the proposed method can be used for ultrasound image segmentation and does not require previous knowledge of the anatomy of the structures. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

• Fecha de publicación: 2017
• Institución: Universidad Tecnológica de Bolívar
• Repositorio: Repositorio Institucional UTB
• Idioma: eng
• OAI Identifier: oai:repositorio.utb.edu.co:20.500.12585/8952
• Acceso en línea: https://hdl.handle.net/20.500.12585/8952
• Palabra clave: Anisotropic diffusion filtering; Medical ultrasound; Region growing segmentation; Anisotropy; Imaging systems; Medical imaging; Optical anisotropy; Tomography; Ultrasonic imaging; Anisotropic diffusion filtering; Intensity gradients; Medical ultrasound; Medical ultrasound images; Morphological closing; Region growing; Segmentation algorithms; Ultrasound image segmentation; Image segmentation
• Rights: restrictedAccess
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/