×

Breast ultrasound image segmentation based on particle swarm optimization and the characteristics of breast tissue. (English) Zbl 1221.92059

Summary: Breast cancer occurs in over 8% of women during their lifetime, and is the leading cause of death among women. Sonography is superior to mammography because it has the ability to detect focal abnormalities in the dense breasts and has no side-effects. We propose a novel automatic segmentation algorithm based on the characteristics of breast tissue and eliminating particle swarm optimization (EPSO) clustering analysis. The characteristics of mammary gland in breast ultrasound (BUS) images are analyzed and utilized, and a method based on step-down threshold technique is employed to locate the mammary gland area. The EPSO clustering algorithm utilizes the idea of “survival of the superior and weeding out the inferior”. The experimental results demonstrate that the proposed approach can segment BUS image with high accuracy and low computational time. The EPSO clustering method reduces the computational time by 32.75% compared with the standard PSO clustering algorithm. The proposed approach would find wide applications in automatic lesion classification and computer aided diagnosis (CAD) systems of breast cancer.

MSC:

92C55 Biomedical imaging and signal processing
92C50 Medical applications (general)
90C59 Approximation methods and heuristics in mathematical programming
68U10 Computing methodologies for image processing
92-08 Computational methods for problems pertaining to biology
90C90 Applications of mathematical programming
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] DOI: 10.1016/j.ultrasmedbio.2008.09.007 · doi:10.1016/j.ultrasmedbio.2008.09.007
[2] DOI: 10.1016/S0031-3203(03)00192-4 · Zbl 1058.68621 · doi:10.1016/S0031-3203(03)00192-4
[3] DOI: 10.1385/MB:29:3:233 · doi:10.1385/MB:29:3:233
[4] DOI: 10.3322/canjclin.55.1.10 · doi:10.3322/canjclin.55.1.10
[5] Hider P., The Early Detection and Diagnosis of Breast Cancer: A Literature Review: an Update (1999)
[6] Kaul K., Hospital Physician 9 pp 49–
[7] DOI: 10.1186/bcr429 · doi:10.1186/bcr429
[8] DOI: 10.1097/00005792-199911000-00006 · doi:10.1097/00005792-199911000-00006
[9] DOI: 10.1016/S1076-6332(03)00723-2 · doi:10.1016/S1076-6332(03)00723-2
[10] DOI: 10.1148/radiology.180.3.1871302 · doi:10.1148/radiology.180.3.1871302
[11] DOI: 10.1016/0929-8266(95)00087-9 · doi:10.1016/0929-8266(95)00087-9
[12] DOI: 10.1148/radiology.177.2.2217759 · doi:10.1148/radiology.177.2.2217759
[13] Sohn C., Breast Ultrasound (1998)
[14] DOI: 10.1118/1.1386426 · doi:10.1118/1.1386426
[15] DOI: 10.1118/1.1429239 · doi:10.1118/1.1429239
[16] DOI: 10.1118/1.1485995 · doi:10.1118/1.1485995
[17] DOI: 10.1016/S0929-8266(98)00062-7 · doi:10.1016/S0929-8266(98)00062-7
[18] DOI: 10.1177/016173469501700403 · doi:10.1177/016173469501700403
[19] DOI: 10.1016/S0301-5629(03)00992-X · doi:10.1016/S0301-5629(03)00992-X
[20] DOI: 10.1016/S0301-5629(03)00059-0 · doi:10.1016/S0301-5629(03)00059-0
[21] DOI: 10.1148/radiology.213.2.r99nv13407 · doi:10.1148/radiology.213.2.r99nv13407
[22] Otsu N., IEEE Transactions on Systems, Man, and Cybernetics 9 pp 62– · doi:10.1109/TSMC.1979.4310076
[23] DOI: 10.1016/S0301-5629(99)00140-4 · doi:10.1016/S0301-5629(99)00140-4
[24] DOI: 10.1109/TITB.2003.816560 · Zbl 05455819 · doi:10.1109/TITB.2003.816560
[25] DOI: 10.1016/j.ultrasmedbio.2003.12.001 · doi:10.1016/j.ultrasmedbio.2003.12.001
[26] DOI: 10.1109/TMI.2002.808364 · doi:10.1109/TMI.2002.808364
[27] DOI: 10.1109/TMI.2006.877092 · doi:10.1109/TMI.2006.877092
[28] DOI: 10.1109/83.841949 · doi:10.1109/83.841949
[29] Wu C. M., IEEE Transactions on Medical Imaging 11 pp 141–
[30] DOI: 10.1016/j.ultrasmedbio.2005.10.007 · doi:10.1016/j.ultrasmedbio.2005.10.007
[31] Sohn C., Breast Ultrasound: A Systematic Approach to Technique and Image Interpretation (1999)
[32] Anderberg M. R., Cluster Analysis for Applications (1973) · Zbl 0299.62029
[33] Forgey E., Biometrics 21 pp 768–
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.