[1]徐立芳,傅智杰,莫宏伟.基于改进的YOLOv3算法的乳腺超声肿瘤识别[J].智能系统学报,2021,16(1):21-29.[doi:10.11992/tis.202010004]
 XU Lifang,FU Zhijie,MO Hongwei.Tumor recognition in breast ultrasound images based on an improved YOLOv3 algorithm[J].CAAI Transactions on Intelligent Systems,2021,16(1):21-29.[doi:10.11992/tis.202010004]
点击复制

基于改进的YOLOv3算法的乳腺超声肿瘤识别(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第16卷
期数:
2021年1期
页码:
21-29
栏目:
学术论文—机器学习
出版日期:
2021-01-05

文章信息/Info

Title:
Tumor recognition in breast ultrasound images based on an improved YOLOv3 algorithm
作者:
徐立芳1 傅智杰2 莫宏伟2
1. 哈尔滨工程大学 工程训练中心,黑龙江 哈尔滨 150001;
2. 哈尔滨工程大学 自动化学院,黑龙江 哈尔滨 150001
Author(s):
XU Lifang1 FU Zhijie2 MO Hongwei2
1. Engineering Training Center, Harbin Engineering University, Harbin 150001, China;
2. Automation College, Harbin Engineering University, Harbin 150001, China
关键词:
乳腺癌超声影像YOLOv3SE-Res2Net下采样模块残差连接密集连接
Keywords:
breast cancerultrasonographyYOLOv3SE-Res2Netdownsample blockresidual connectiondense connection
分类号:
TP181
DOI:
10.11992/tis.202010004
摘要:
为了提高乳腺癌诊断的效率以及准确性,本文提出一种基于改进的YOLOv3算法来构建一个乳腺超声肿瘤识别算法,辅助医生进行乳腺癌的诊断。首先在Res2Net网络上融入SE模块构建SE-Res2Net网络来取代原始YOLOv3中的特征提取网络,以此提升模型特征提取的能力。然后通过搭建一个新型下采样模块(downsample block)来解决原始模型中下采样操作容易出现信息丢失的不足。最后为了进一步提升模型特征提取的能力,结合残差连接网络以及密集连接网络的优点构建Res-DenseNet网络来替换原始模型的残差连接方式。实验结果表明:改进后的YOLOv3算法比原始YOLOv3算法的mAP提高了4.56%,取得较好的检测结果。
Abstract:
To improve the efficiency and accuracy of breast cancer diagnoses, a breast ultrasound tumor recognition algorithm based on an improved YOLOV3 algorithm is proposed to assist doctors in breast cancer diagnosis. First, the SE module is integrated into Res2Net to construct Se-Res2Net to replace the original feature extraction network in YOLOv3 to improve the ability of model feature extraction. Then, a new Downsample Block is built to solve the problem of information loss in the downsampling operation of the original model. Finally, to further improve the ability of feature extraction, the residual connection network and dense connection network are combined to construct Res-DenseNet to replace the residual connection mode of the original model. The experimental results show that the above improvements are effective, and the mAP of the improved algorithm is 4.56% higher than that of the original algorithm.

参考文献/References:

[1] CHEN Wanqing, ZHENG Rongshou, BAADE P D, et al. Cancer statistics in China, 2015[J]. CA:a cancer journal for clinicians, 2016, 66(2):115-132.
[2] SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics, 2016[J]. CA:a cancer journal for clinicians, 2016, 66(1):7-30.
[3] LO C S, WANG C M. Support vector machine for breast MR image classification[J]. Computers and mathematics with applications, 2012, 64(5):1153-1162.
[4] GINSBURG O, BRAY F, COLEMAN M P, et al. The global burden of women’s cancers:a grand challenge in global health[J]. The lancet, 2017, 389(10071):847-860.
[5] MENEZES G L, KNUTTEL F M, STEHOUWER B L, et al. Magnetic resonance imaging in breast cancer:a literature review and future perspectives[J]. World journal of clinical oncology, 2014, 5(2):61-70.
[6] 袁红梅, 余建群, 褚志刚, 等. 动态增强MRI、超声及X射线对乳腺良恶性病灶诊断的对比研究[J]. 中国普外基础与临床杂志, 2015, 22(2):246-250
YUAN Hongmei, YU Jianqun, CHU Zhigang, et al. Comparative study of dynamic contrast-enhanced breast MRI, ultrasound, and X-ray mammography in differential diagnosis of benign and malignant breast lesions[J]. Chinese journal of bases and clinics in general surgery, 2015, 22(2):246-250
[7] 中国抗癌协会乳腺癌专业委员会. 中国抗癌协会乳腺癌诊治指南与规范(2017年版)[J]. 中国癌症杂志, 2017,27(9):695-759
Breast cancer professional committee of Chinese anti-cancer association. Guidelines and specifications for breast cancer diagnosis and treatment of China anti cancer association (2017 Edition)[J]. China oncology, 2017,27(9):695-759
[8] 周星彤, 沈松杰, 孙强. 中国乳腺癌筛查现状及进展[J]. 中国医学前沿杂志, 2020, 12(3):6-11
ZHOU Xingtong, SHEN Songjie, SUN Qiang. Current situation and progress of breast cancer screening in China[J]. Chinese journal of the frontiers of medical science (electronic version), 2020, 12(3):6-11
[9] Cai L, Wang X, Wang Y, et al. Robust phase-based texture descriptor for classification of breast ultrasound images[J]. BioMedical Engineering OnLine, 2015, 14(1):1-21.
[10] HUANG Y L, JIANG Y R, CHEN D R, et al. Computer-aided diagnosis with morphological features for breast lesion on sonograms[J]. Ultrasound in obstetrics and gynecology, 2008, 32(4):565-572.
[11] KABIR S M, BHUIYAN M I H. Classification of breast tumour in contourlet transform domain[C]//2018 10th International Conference on Electrical and Computer Engineering (ICECE). Dhaka, Bangladesh, 2018:289-292.
[12] MENON R V, RAHA P, KOTHARI S, et al. Automated detection and classification of mass from breast ultrasound images[C]//2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics. Patna, India, 2015:1-4.
[13] 肖婷. 基于深度特征迁移与融合的乳腺超声图像分类[D]. 重庆:重庆大学, 2018.
XIAO Ting. Breast ultrasound image classification on deep feature based transfer learning and feature fusion[D]. Chongqing:Chongqing University, 2018.
[14] HAN S, KANG H K, JEONG J Y, et al. A deep learning framework for supporting the classification of breast lesions in ultrasound images[J]. Physics in medicine and biology, 2017, 62(19):7714-7728.
[15] 梁舒. 基于残差学习U型卷积神经网络的乳腺超声图像肿瘤分割研究[D]. 广州:华南理工大学, 2018.
LIANG Shu. Research on breast ultrasound image segmentaion based on residual U-shaped convolution neural network[D]. Guangzhou:South China University of Technology, 2018.
[16] 王恒立. 基于全卷积网络的乳腺超声图像语义分割方法[D]. 哈尔滨:哈尔滨工业大学, 2018.
WANG Hengli. Semantic segmentation method for breast ultrasound images based on fully convolutional network[D]. Harbin:Harbin Institute of Technology, 2018.
[17] YAP M H, GOYAL M, OSMAN F M, et al. End-to-end breast ultrasound lesions recognition with a deep learning approach[C]//Proceedings Volume 10578, Medical Imaging 2018:Biomedical Applications in Molecular, Structural, and Functional Imaging. Houston, Texas, United States, 2018:1057819.
[18] CHIAO J Y, CHEN K Y, LIAO K Y, et al. Detection and classification the breast tumors using mask R-CNN on sonograms[J]. Medicine, 2019, 98(19):e15200.
[19] SHIN S Y, LEE S, YUN I D, et al. Joint weakly and semi-supervised deep learning for localization and classification of masses in breast ultrasound images[J]. IEEE transactions on medical imaging, 2019, 38(3):762-774.
[20] REDMON J, FARHADI A. Yolov3:an incremental improvement[J]. arXiv preprint:arXiv:1804.02767, 2018.
[21] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:7132-7141.
[22] GAO Shanghua, CHENG Mingming, ZHAO Kai, et al. Res2Net:a new multi-scale backbone architecture[J]. IEEE transactions on pattern analysis and machine intelligence, 2019:1-10.

备注/Memo

备注/Memo:
收稿日期:2020-10-09。
作者简介:徐立芳,讲师,博士,主要研究方向为智能控制、机器视觉与机器认知、人机混合智能。主持、参与省部级科研项目10项,授权发明专利6项。发表学术论文20余篇。;傅智杰,硕士研究生,主要研究方向为深度学习、计算机视觉、医学影像;莫宏伟,教授,博士生导师,主要研究方向为类脑计算与人工智能、机器视觉与机器认知、人机混合智能。主持省部级科研项目24项,授权发明专利10项。发表学术论文80余篇。
通讯作者:莫宏伟. E-mail:honwei2004@126.com
更新日期/Last Update: 2021-02-25