Title :
Automatic Mass Segmentation Based on Adaptive Pyramid and Sublevel Set Analysis
Author :
Ma, Fei ; Bajger, Mariusz ; Bottema, Murk J.
Author_Institution :
Flinders Univ., Adelaide, SA, Australia
Abstract :
A method based on sublevel sets is presented for refining segmentation of screening mammograms. Initial segmentation is provided by an adaptive pyramid (AP) scheme which is viewed as seeding of the final segmentation by sublevel sets. Performance is tested with and without prior anisotropic smoothing and is compared to refinement based on component merging. The combination of anisotropic smoothing, AP segmentation and sublevel refinement is found to outperform other combinations.
Keywords :
image segmentation; mammography; medical image processing; set theory; adaptive pyramid analysis; anisotropic smoothing; automatic mass segmentation; component merging; screening mammograms; sublevel refinement; sublevel set analysis; Anisotropic magnetoresistance; Breast; Computer applications; Digital images; Image segmentation; Level set; Mammography; Shape; Smoothing methods; Testing; inclusion tree; mammogram; segmentation; sublevel set;
Conference_Titel :
Digital Image Computing: Techniques and Applications, 2009. DICTA '09.
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4244-5297-2
Electronic_ISBN :
978-0-7695-3866-2
DOI :
10.1109/DICTA.2009.47
