基于改进的YOLOv3算法的乳腺超声肿瘤识别  

Tumor recognition in breast ultrasound images based on an improved YOLOv3 algorithm

作　　者：徐立芳[1] 傅智杰 莫宏伟[2] XU Lifang;FU Zhijie;MO Hongwei(Engineering Training Center,Harbin Engineering University,Harbin 150001,China;Automation College,Harbin Engineering University,Harbin 150001,China)

机构地区：[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

出　　处：《智能系统学报》2021年第1期21-29,共9页CAAI Transactions on Intelligent Systems

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m AP提高了4.56%,取得较好的检测结果。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 Res2 Net to construct Se-Res2 Net 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 ResDenseNet 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.

关 键 词：乳腺癌 超声影像 YOLOv3 SE-Res2Net 下采样模块 残差连接 密集连接 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]