Multiplicative gradient based edge detection method for medical ultrasound image" />
Multiplicative gradient based edge detection method for medical ultrasound image" />
Multiplicative gradient based edge detection method for medical ultrasound image" />
基于乘性梯度的医学超声图像边缘检测算法
Multiplicative gradient based edge detection method for medical ultrasound image
GONG Xiao-hong1, ZHENG Yin-fei1, QIN Jia-le2, ZHOU Hao1
1.Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou 310027, China; 2. Department of Ultrasound, Women’s Hospital, School of Medicine, Zhejiang University, Hangzhou 310006, China
An accurate and fast edge detection method for medical ultrasound images was proposed based on a modified multiplicative gradient (MG) operator and the traditional Canny. The dimension of the template of the MG operator was increased to improve the performance in weak edge detecting. The results of Canny and MG operators were combined to improve the accuracy of the edge detection. The proposed method was evaluated based on simulated and in vivo ultrasound images. Experimental results showed that the accuracy of the proposed method was more than 75% for different speckle noise level. The results of the edge detection can be obtained in real-time by using the proposed method.
［1］ CRONAN J J. Ultrasound: is there a future in diagnostic imaging？ ［J］. Journal of the American College of Radiology, 2006, 3(9): 645-646.
［2］ MOREAU J F. Re: “ultrasound: is there a future in diagnostic imaging？” ［J］. Journal of the American College of Radiology, 2007, 4(1): 78-79.
［3］ YU Yong-jian, SCOTT T. Edge detection in ultrasound imagery using the instantaneous coefficient of variation ［J］. IEEE Transaction on Image Processing, 2004, 13(12): 1640-1655.
［4］ CHEN Zhi-gang, CUI Yue-li, CHEN Ai-hua. An multi-scale edge detection approach ［C］ ∥ 2012 International Conference on Solid State Devices and Materials Science. Macao: ［s.n.］, 2012: 1616-1620.
［5］ NES P G. Fast multi-scale edge-detection in medical ultrasound signals ［J］. Signal Processing, 2012, 92(10): 2394-2408.
［6］ LOPEZ-MOLINA C, BAETS B, BUSTINCE H, et al. Multiscale edge detection based on Gaussian smoothing and edge tracking ［J］. Knowledge-Based Systems, 2013, 44(12): 101-111.
［7］ VERMA O P, HANMANDLU M, SULTANIA A K, et al. A novel fuzzy system for edge detection in noisy image using bacterial foraging ［J］. Multidimensional Systems and Signal Processing, 2011, 24(1): 181-198.
［8］ TALAI Z, TALAI A. A fast edge detection using fuzzy rules ［C］ ∥ Proceedings of the Communications, Computing and Control Applications. Hammamet: IEEE, 2011: 15.
［9］ RAY K. Unsupervised edge detection and noise detection from a single image ［J］. Pattern Recognition, 2013, 46(8): 2067-2077.
HE Wen-hao, YUAN Kui, ZOU Wei. Self-adaptive threshold edge detection and its implementation in hardware ［J］. Systems Engineering and Electronics, 2009, 31(1): 233-237.
［12］ LI W, WANG C, WANG Q, et al. An edge detection method based on optimized BP neural network ［C］∥ International Symposium on Information Science and Engineering. Shanghai: IEEE, 2008: 40-44.
［13］ MORA M, CRDOVA-LEPE F, DEL-VALLE R. A non-Newtonian gradient for contour detection in images with multiplicative noise ［J］. Pattern Recognition Letters, 2012, 33(10): 1245-1256.
［14］ CRDOVA-LEPE F. From quotient operation toward a proportional calculus ［J］. Internetional Journal of Mathematics, Game Theory and Algebra, 2009, 18(6): 527-536.
［15］ CRDOVA-LEPE F. The multiplicative derivative as a measure of elasticity in economics ［J］. Theaeteto Atheniensi Mathematica (TEMAT), 2004, 2(3) online.
［16］ CANNY J. A computational approach to edge detection ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679-698.
［17］ JOSHI S R, KOJU R. Study and comparison of edge detection algorithms ［C］ ∥ 2012 3rd Asian Himalayas International Conference on Internet. Kathmandu: IEEE, 2012: 15.
［18］ LOPEZ-MOLINA C, DE BAETS B, BUSTINCE H. Quantitative error measures for edge detection ［J］. Pattern Recognition, 2013, 46(4): 1125-1139.
