13 March 2017 Region growing segmentation of ultrasound images using gradients and local statistics
Author Affiliations +
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.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Isabela M. Mercado-Aguirre, Isabela M. Mercado-Aguirre, Alberto Patiño-Vanegas, Alberto Patiño-Vanegas, Sonia H. Contreras-Ortiz, Sonia H. Contreras-Ortiz, } "Region growing segmentation of ultrasound images using gradients and local statistics", Proc. SPIE 10139, Medical Imaging 2017: Ultrasonic Imaging and Tomography, 101391E (13 March 2017); doi: 10.1117/12.2254518; https://doi.org/10.1117/12.2254518

Back to Top