Integrate Domain Knowledge in Training CNN for Ultrasonography Breast Cancer Diagnosis
Breast cancer is the most common cancer in women, and ultrasound imaging is one of the most widely used approach for diagnosis. In this paper, we proposed to adopt Convolutional Neural Network (CNN) to classify ultrasound images and predict tumor malignancy. CNN is a successful algorithm for image recognition tasks and has achieved human-level performance in real applications. To improve the performance of CNN in breast cancer diagnosis, we integrated domain knowledge and conducted multi-task learning in the training process. After training, a radiologist visually inspected the class activation map of the last convolutional layer of trained network to evaluate the result. Our result showed that CNN classifier can not only give reasonable performance in predicting breast cancer, but also propose potential lesion regions which can be integrated into the breast ultrasound system in the future.
KeywordsBreast cancer Ultrasound BI-RADS assessments Convolutional neural network Multi-task learning
The work received supports from Shenzhen Municipal Government under the grants JCYJ20170413161913429 and KQTD2016112809330877.
- 4.Berg, W.A., et al.: Shear-wave elastography improves the specificity of breast US: the BE1 multinational study of 939 masses. Int. J. Med. Radiol. 262(2), 435 (2012)Google Scholar
- 5.Mendelson, E., et al.: Breast imaging reporting and data system, BI-RADS: ultrasound (2003)Google Scholar
- 6.D’Orsi, C., et al.: ACR BI-RADS® Atlas, Breast Imaging Reporting and Data System (2013)Google Scholar
- 7.Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 (2014)
- 12.Su, H., et al.: Region segmentation in histopathological breast cancer images using deep convolutional neural network. In: IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 55–58 (2015)Google Scholar
- 13.Kotikalapudi, Raghavendra and contributors: https://github.com/raghakot/keras-vis (2017)