A novel efficient method based on the ultrasound radio frequency (RF) signals is proposed to distinguish the breast tumors grades. First, we utilize the multi-scale geometric characteristic of Shearlet transformation to extract the multi-scale and multi-directional features of ultrasound RF signal, and then reduce the high-dimensional Shearlet features by multi-scale directional binary pattern which can effectively preserve the sufficient discriminated information. At last, we draw on the feature difference between different grades of breast tumors to design a cascade binary tree SVM classifier which not only overcome the problem of sample quantity disequilibrium but also conform to the subjective diagnosis rule of sonographer. Extensive experiments on 928 breast ultrasound RF signals collected from the hospital demonstrate the effectiveness of the new proposed method and its precision, sensitivity, specificity, PPV, NPV and MCC are 89.29%, 75.62%, 94.54%, 97%, 98.3% and 81.01%, respectively.
The grade classification algorithm of breast tumor based on ultrasound RF signals
First published at:Jan 01, 2019
1 Zhou S C, Zeng W, Fan Y W, et al. Discussing of using breast grades in ultrasound[J]. Chinese Journal of Ultrasound in Medicine, 2008, 24(6): 19-23.
2 Hou X Y, Gao Y, Huang X L, et al. Application value of breast image report data system for ultrasonography in mamary gland[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2011, 8(6): 1227-1233. DOI:10.3877/cma.j.issn.1672-6448.2011.06.008
侯新燕, 高宇, 黄晓玲, 等.乳腺影像报告数据系统在乳腺超声中的应用价值[J].中华医学超声杂志(电子版), 2011, 8(6): 1227-1233. DOI:10.3877/cma.j.issn.1672-6448.2011.06.008
3 Suzuki K. A review of computer-aided diagnosis in thoracic and colonic imaging[J]. Quantitative Imaging in Medicine and Surgery, 2012, 2(3): 163-176.
4 He J T, Chen M H, Jia W Y, et al. Segmentation of diabetic macular edema in Oct retinal images[J]. Opto-Electronic Engineering, 2018, 45(7): 170605. DOI:10.12086/oee.2018.170605
5 Lv W, Zhai Q W, Chu J H, et al. Automated detection of diabetic retinopathy exudates in color fundus images[J]. Opto-Electronic Engineering, 2016, 43(12): 183-192, 199. DOI:10.3969/j.issn.1003-501X.2016.12.028
吕卫, 翟庆伟, 褚晶辉, 等.彩色眼底图像糖网渗出物的自动检测[J].光电工程, 2016, 43(12): 183-192, 199. DOI:10.3969/j.issn.1003-501X.2016.12.028
6 Wang X W, Li L H, Liu W, et al. An interactive system for computer-aided diagnosis of breast masses[J]. Journal of Digital Imaging, 2012, 25(5): 570-579. DOI:10.1007/s10278-012-9451-0
7 Jen C C, Yu S S. Automatic detection of abnormal mammograms in mammographic images[J]. Expert Systems with Applications, 2015, 42(6): 3048-3055. DOI:10.1016/j.eswa.2014.11.061
8 Sharma S, Khanna P. Computer-aided diagnosis of malignant mammograms using Zernike moments and SVM[J]. Journal of Digital Imaging, 2015, 28(1): 77-90. DOI:10.1007/s10278-014-9719-7
9 Tan W C, Wang J H, Cai H M, et al. The performance of computer-aided diagnosis for DCIS based on classification of clustered microcalcifications[J]. Journal of Clinical Radiology, 2016, 35(9): 1352-1356.
10 Moon W K, Lo C M, Huang C S, et al. Computer-aided diagnosis based on speckle patterns in ultrasound images[J]. Ultrasound in Medicine & Biology, 2012, 38(7): 1251-1261.
11 Alam S K, Feleppa E J, Rondeau M, et al. Computer-Aided diagnosis of solid breast lesions using an ultrasonic multi-feature analysis procedure[J]. Bangladesh Journal of Medical Physics, 2013, 4(1): 1-10.
12 Huang Q H, Yang F B, Liu L Z, et al. Automatic segmentation of breast lesions for interaction in ultrasonic computer-aided diagnosis[J]. Information Sciences, 2015, 314: 293-310. DOI:10.1016/j.ins.2014.08.021
13 Cheng J Z, Ni D, Chou Y H, et al. Computer-Aided diagnosis with deep learning architecture: Applications to breast lesions in us images and pulmonary nodules in CT scans[J]. Scientific Reports, 2016, 6: 24454. DOI:10.1038/srep24454
14 Masotti L, Biagi E, Granchi S, et al. Tissue differentiation based on radiofrequency echographic signal local spectral content[C]//Proceedings of the IEEE Symposium on Ultrasonics, 2003, 1: 1030-1033.
15 Moradi M, Mahdavi S S, Nir G, et al. Ultrasound RF time series for tissue typing: first in vivo clinical results[J]. Proceedings of SPIE, 2013, 8670: 86701I. DOI:10.1117/12.2007672
16 Moradi M, Abolmaesumi P, Mousavi P. Tissue typing using ultrasound RF time series: experiments with animal tissue samples[J]. Medical Physics, 2010, 37(8): 4401-4413. DOI:10.1118/1.3457710
17 Liu Z D, Luo Y, Lin J L, et al. Quantizing and grading of fatty liver based on ultrasonic RF signals[J]. Journal of Sichuan University (Engineering Science Edition), 2011, 43(S1): 160-164.
18 Zhuang S L, Zhou J H, Wang J W, et al. Differential diagnosis of breast lesions with RF time-series signal based on ultrasonic radio-frequency flow[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2016, 13(5): 393-397. DOI:10.3877/cma.j.issn.1672-6448.2016.05.014
庄淑莲, 周建华, 王建伟, 等.基于超声射频流的RF时间序列信号在乳腺病变良恶性鉴别中的价值[J].中华医学超声杂志(电子版), 2016, 13(5): 393-397. DOI:10.3877/cma.j.issn.1672-6448.2016.05.014
19 Yan Y, Fang G, Cai R Q, et al. Ultrasound radio-frequency characteristic signal processing for breast lump recognition[J]. China Medical Equipment, 2016, 13(9): 20-22. DOI:10.3969/J.ISSN.1672-8270.2016.09.006
严郁, 方舸, 蔡润秋, 等.基于乳腺肿块的超声射频信号特征算法识别[J].中国医学装备, 2016, 13(9): 20-22. DOI:10.3969/J.ISSN.1672-8270.2016.09.006
20 Uniyal N, Eskandari H, Abolmaesumi P, et al. Ultrasound RF time series for classification of breast lesions[J]. IEEE Transactions on Medical Imaging, 2015, 34(2): 652-661. DOI:10.1109/TMI.2014.2365030
21 Guo K H, Labate D. Optimally sparse multidimensional representation using shearlets[J]. SIAM Journal on Mathematical Analysis, 2007, 39(1): 298-318. DOI:10.1137/060649781
22 Gao G R, Xu L P, Feng D Z. Multi-focus image fusion based on non-subsampled shearlet transform[J]. IET Image Processing, 2013, 7(6): 633-639. DOI:10.1049/iet-ipr.2012.0558
23 Chang L H. Fusion method based on shearlet transform and sparse representation[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2017, 56(4): 16-19.
24 Zhou F, Jia Z H, Yang J, et al. Medical image enhancement method based on improved Gamma correction in shearlet domain[J]. Journal of Optoelectronics·Laser, 2017, 28(5): 566-572.
25 Xu C, Chen X, Ji Q Y. Shearlet domian image denoising via sparse coding[J]. Laser Journal, 2017, 38(10): 96-100.
26 Easley G R, Labate D, Colonna F. Shearlet-based total variation diffusion for denoising[J]. IEEE Transactions on Image Processing, 2009, 18(2): 260-268. DOI:10.1109/TIP.2008.2008070
27 Vagharshakyan S, Bregovic R, Gotchev A. Light field reconstruction using Shearlet transform[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(1): 133-147. DOI:10.1109/TPAMI.2017.2653101
28 Xu Z L, Deng C Z, Zhang Y S. Shearlet sparsity regularized image reconstruction based on nonlocal self-similarity[J]. Journal of University of Electronic Science and Technology of China, 2016, 45(1): 43-47, 101.
29 Zhou S C, Shi J, Zhu J, et al. Shearlet-based texture feature extraction for classification of breast tumor in ultrasound image[J]. Biomedical Signal Processing and Control, 2013, 8(6): 688-696. DOI:10.1016/j.bspc.2013.06.011
Supported by National Natural Science Foundation of China (61703201), NSF of Jiangsu Province (BK20170765), and NIT fund for Young Scholar (CKJB201602)
Get Citation: Tong Ying, Yan Yu. The grade classification algorithm of breast tumor based on ultrasound RF signals[J]. Opto-Electronic Engineering, 2019, 46(1): 180368.