Study on the feasibility of automatic recognition technology based on depth learning for classification of benign and malignant breast nodules in ultrasound images

doi:10.3877/cma.j.issn.1672-6448.2018.10.010

Chinese Journal of Medical Ultrasound (Electronic Edition) ›› 2018, Vol. 15 ›› Issue (10): 779-782. doi: 10.3877/cma.j.issn.1672-6448.2018.10.010

Special Issue: ；；

• Superficial Parts Ultrasound • Previous Articles Next Articles

Study on the feasibility of automatic recognition technology based on depth learning for classification of benign and malignant breast nodules in ultrasound images

Yunyun Bu¹, Shuqiang Lu², Hao Pang²

Received:2018-07-01 Online:2018-10-01 Published:2018-10-01

Abstract

Yunyun Bu, Shuqiang Lu, Hao Pang. Study on the feasibility of automatic recognition technology based on depth learning for classification of benign and malignant breast nodules in ultrasound images[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2018, 15(10): 779-782.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://chaosheng.cma-cmc.com.cn/EN/10.3877/cma.j.issn.1672-6448.2018.10.010

https://chaosheng.cma-cmc.com.cn/EN/Y2018/V15/I10/779

Figures/Tables 5

References 15

1	Chen W, Zheng R, Baade PD, et al. Cancer statistics in China, 2015 [J]. CA Cancer J Clin, 2016, 66(2): 115-132.
2	Siegel RL, Miller KD, Jemal A. Cancer statistics, 2016 [J]. CA Cancer J Clin, 2016, 66(1): 7-30
3	Torre LA, Bray F, SIiegel RL, et al. Global cancer statistics, 2012 [J]. CA Cancer J Clin, 2015, 65(2): 87-108
4	Lee CH. Screening mammography: proven benefit, continued controversy [J]. Radiol Clin N Am, 2002, 40(3): 395-407.
5	Anderson BO, Shyyan R, Eniu A, et al. Breast cancer in limited-resource countries:an overview of the breast health global initiative 2005 guidelines [J]. Breast J, 2006, 12(s1): S3-S15
6	Noble JA, Boukerroui D. Ultrasound image segmentation: a survey [J]. IEEE Trans Med Imaging, 2006, 25(8): 987-1010.
7	Ikedo Y, Morita T, Fukuoka D, et al. Automated analysis of breast parenchymal patterns in whole breast ultrasound images: preliminary experience [J]. Comput Assist Radiol Sur, 2009, 4(3): 299-306
8	Huang YL, Jiang YR, Chen DR, et al. Computer-aided diagnosis with morphological features for breast lesion on sonograms [J]. Ultrasound Obstet Gynecol, 2008, 32(4): 565-572.
9	刘玉华，陈素贤. 乳癌综合诊断的计算机识别方法研究 [J]. 电子学报, 1988, (5): 110-112.
10	Chen DR, Hsiao YH. Computer-aided diagnosis in breast ultrasound [J]. J Ultrasound Med, 2008, 16(1): 46-56
11	Huang Q, Luo Y, Zhang Q. Breast ultrasound image segmentation:a survey [J]. Int J Comput Assist Radiol Surg, 2017, 12(3): 493-507
12	孙志军，薛磊，许阳明, 等. 深度学习研究综述 [J]. 计算机应用究, 2012, 29(8): 2806-2810.
13	Wang W, Zhu L, Qin J, et al. Multiscale geodesic active contours for ultrasound image segmentation using speckle reducing anisotropic diffusion [J]. OptLasersEng, 2014, 54(1): 105-116
14	李彦冬，郝宗波，雷航. 卷积神经网络研究综述 [J]. 计算机应用, 2016, 36(9): 2508-2515, 2565.
15	刘丹枫，刘建霞. 面向深度学习过拟合问题的神经网络模型 [J]. 湘潭大学自然科学学报, 2018, 40(2): 96-99.

评价指标	准确率	精确率	召回率	F1值	mAP
良性结节	0.8682	0.7789	0.8441	0.8102	0.76
恶性结节	0.8771	0.8773	0.7334	0.7992	0.75
正常腺体	0.9658	0.9155	0.9886	0.9506	-

评价指标	准确率	精确率	召回率	F1值	mAP
良性结节	0.8682	0.7789	0.8441	0.8102	0.76
恶性结节	0.8771	0.8773	0.7334	0.7992	0.75
正常腺体	0.9658	0.9155	0.9886	0.9506	-

评价指标	准确率	敏感度	特异度	曲线下面积
良性结节	0.8682	0.8441	0.8802	0.9367
恶性结节	0.8771	0.7334	0.9487	0.9434
正常腺体	0.9658	0.9886	0.9543	0.9968

评价指标	准确率	敏感度	特异度	曲线下面积
良性结节	0.8682	0.8441	0.8802	0.9367
恶性结节	0.8771	0.7334	0.9487	0.9434
正常腺体	0.9658	0.9886	0.9543	0.9968

Please choose a citation manager

Content to export

Study on the feasibility of automatic recognition technology based on depth learning for classification of benign and malignant breast nodules in ultrasound images

RichHTML

PDF (PC)

Knowledge