TY - JOUR
T1 - Automated breast tumor detection and segmentation with a novel computational framework of whole ultrasound images
AU - Liu, Lei
AU - Li, Kai
AU - Qin, Wenjian
AU - Wen, Tiexiang
AU - Li, Ling
AU - Wu, Jia
AU - Gu, Jia
N1 - Funding Information:
Funding information This work is partially supported by grants from the National Natural Science Foundation of China (NSFC: 61401451, 61501444, 61472411), Guangdong Province Science and Technology Plan Projects (Grant No. 2015B020233004), and Shenzhen Technology Research Project (Grant No. JSGG20160429192140681, JCYJ20160429174611494).
Publisher Copyright:
© 2017, International Federation for Medical and Biological Engineering.
PY - 2018/2/1
Y1 - 2018/2/1
N2 - Due to the low contrast and ambiguous boundaries of the tumors in breast ultrasound (BUS) images, it is still a challenging task to automatically segment the breast tumors from the ultrasound. In this paper, we proposed a novel computational framework that can detect and segment breast lesions fully automatic in the whole ultrasound images. This framework includes several key components: pre-processing, contour initialization, and tumor segmentation. In the pre-processing step, we applied non-local low-rank (NLLR) filter to reduce the speckle noise. In contour initialization step, we cascaded a two-step Otsu-based adaptive thresholding (OBAT) algorithm with morphologic operations to effectively locate the tumor regions and initialize the tumor contours. Finally, given the initial tumor contours, the improved Chan-Vese model based on the ratio of exponentially weighted averages (CV-ROEWA) method was utilized. This pipeline was tested on a set of 61 breast ultrasound (BUS) images with diagnosed tumors. The experimental results in clinical ultrasound images prove the high accuracy and robustness of the proposed framework, indicating its potential applications in clinical practice. [Figure not available: see fulltext.]
AB - Due to the low contrast and ambiguous boundaries of the tumors in breast ultrasound (BUS) images, it is still a challenging task to automatically segment the breast tumors from the ultrasound. In this paper, we proposed a novel computational framework that can detect and segment breast lesions fully automatic in the whole ultrasound images. This framework includes several key components: pre-processing, contour initialization, and tumor segmentation. In the pre-processing step, we applied non-local low-rank (NLLR) filter to reduce the speckle noise. In contour initialization step, we cascaded a two-step Otsu-based adaptive thresholding (OBAT) algorithm with morphologic operations to effectively locate the tumor regions and initialize the tumor contours. Finally, given the initial tumor contours, the improved Chan-Vese model based on the ratio of exponentially weighted averages (CV-ROEWA) method was utilized. This pipeline was tested on a set of 61 breast ultrasound (BUS) images with diagnosed tumors. The experimental results in clinical ultrasound images prove the high accuracy and robustness of the proposed framework, indicating its potential applications in clinical practice. [Figure not available: see fulltext.]
KW - Automatic segmentation
KW - Breast
KW - Contour initialization
KW - Level set segmentation
KW - Speckle reduction
KW - Ultrasound image
UR - http://www.scopus.com/inward/record.url?scp=85039763983&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85039763983&partnerID=8YFLogxK
U2 - 10.1007/s11517-017-1770-3
DO - 10.1007/s11517-017-1770-3
M3 - Review article
C2 - 29292471
AN - SCOPUS:85039763983
SN - 0140-0118
VL - 56
SP - 183
EP - 199
JO - Medical and Biological Engineering and Computing
JF - Medical and Biological Engineering and Computing
IS - 2
ER -