基于迁移学习的多视图卷积神经网络在乳腺超声自动分类中的应用

BREAST CANCER CLASSIFICATION IN AUTOMATED BREAST ULTRASOUND USING MULTIVIEW CONVOLUTIONAL NEURAL NETWORK WITH TRANSFER LEARNING

YI WANG,*,1EUN JUNG CHOI,y,1YOUNHEE CHOI,* HAO ZHANG,* GONG YONG JIN,yand SEOK-BUM KO*TAGGEDEND
* Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Canada; andyDepartment of
Radiology, Research Institute of Clinical Medicine of Jeonbuk National University?Biomedical Research Institute of Jeonbuk
National University Hospital, Jeonbuk National University Medical School, Jeonju City, Jeollabuk-Do, South Korea
(Received 11 July 2019; revised 12 December 2019; in final from 2 January 2020)

 https://doi.org/10.1016/j.ultrasmedbio.2020.01.001

---

目录

基于迁移学习的多视图卷积神经网络在乳腺超声自动分类中的应用

 摘要:

介绍：

方法：

临床数据集

基于CNN的病灶特征提取与分类

 多视图CNN

 网络训练与评估

结果:

多视图CNN的分类性能

与传统机器学习特征提取器的比较

 观察者性能测试

 讨论

多视图CNN分析