Breast Cancer Medical Image Analysis Based on Transfer Learning Model
Breast cancer becomes one of the common cancer among women. The computer-aided diagnosis is a very available technology, and it becomes an inevitable trend of modern medicine. There is litter data in the medical field which is not enough to support training model. The paper aims to solve the problem in the case of insufficient data volume, and a transfer learning model combined with Convolutional Neural Network (CNN) is proposed to achieve the goal. This model has three innovations. The first one takes Xavier method to initialize parameter, which can make the training process more stable. The second innovation takes dropout method to discard some network nodes randomly, which can reduce overfitting problem. The third one adds two convolutional layers and one max pooling layer before final fully connected layer. The experimental results have shown that this strategy is suitable for the problem in this paper. The paper indicates that the transfer learning model is an effective method with small-scale data, and it can be combined with deep learning algorithms.
KeywordsBreast cancer Transfer learning Convolutional Neural Network
This work was supported in part by National Natural Science Foundation of China (61273225, 61373109, 61702381).
- 3.Heath, M., Bowyer, K., Kopans, D., et al.: The digital database for screening mammography. In: Digital Mammography, pp. 457–460. Springer, Netherlands (2001)Google Scholar
- 4.Sucking, J., Boggis, C.R.M., Hutt, I., et al.: The Mini-MIAS database of mammograms. In: International Congress Series, vol. 1069, pp. 375–378 (1994)Google Scholar
- 7.Sun, D., Wang, M., Li, A.: A multimodal deep neural network for human breast cancer prognosis prediction by integrating multi-dimensional data. IEEE/ACM Trans. Comput. Biol. Bioinform. 1 (2018)Google Scholar
- 9.Ma, Y., Tay, P.C., Adams, R.D., et al.: A novel shape feature to classify microcalcifications. In: IEEE International Conference on Image Processing, Western Carolina University, pp. 2265–2268. IEEE (2010)Google Scholar
- 12.Szegedy, C., Liu, W., Jia, Y., et al.: Going Deeper with Convolutions, pp. 1–9 (2014)Google Scholar
- 13.Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105. Curran Associates Inc. (2012)Google Scholar
- 15.Deng, J., Dong, W., Socher, R., et al.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248–255. IEEE (2009)Google Scholar
- 16.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science, pp. 1–15 (2014)Google Scholar
- 18.Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. J. Mach. Learn. Res. 9, 249–256 (2010)Google Scholar