Breast Cancer Malignancy Prediction Using Incremental Combination of Multiple Recurrent Neural Networks
Breast cancer is the most common cancer among women worldwide. An early detection of malignant of breast cancer, followed by proper treatment, can great improve the survival rate of patients. Recently, the deep learning based malignancy prediction models for breast cancer have been proposed. However, these models are usually trained with single type of clinical text, which are still not effective enough to predict breast cancer malignancy. In this paper, we follow the deep incremental learning framework and propose a prediction model of breast cancer malignancy by incremental combination of multiple recurrent neural networks. Specially, the model first uses multiple recurrent neural networks (RNNs) for generating features from the multi-types of clinical text including B-ultrasound, X-rays, Computed Tomography (CT), and Nuclear Magnetic Resonance Imaging (MRI), and then combines the generated features in an incremental way. Finally, we add one more recurrent neural network layer for classifying benign and malignant of breast cancer based on combined generated features.
KeywordsBreast cancer Text classification Deep learning Recurrent neural networks
This work was supported by the Shanghai Innovation Action Project of Science and Technology (15511106900), the Science and Technology Development Foundation of Shanghai (16JC1400802), the Special Fund of Shanghai Economic and Trade Commission Software and Integrated Circuit Industry Development (No. 160623), and the Shanghai Specific Fund Project for Information Development (XX-XXFZ-01-14-6349).
- 2.Mikolov, T., Kombrink, S., Burget, L., Černocký, J., Khudanpur, S.: Extensions of recurrent neural network language model. In: IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 125, pp. 5528–5531 (2011)Google Scholar
- 5.Guo, H., Nandi, A.K.: Breast cancer diagnosis using genetic programming generated feature. In: 2005 IEEE Workshop on Machine Learning for Signal Processing, vol. 39, pp. 215–220 (2005)Google Scholar
- 7.Zribi, M.: The neural networks with an incremental learning algorithm approach for mass classification in breast cancer. Int. J. Biomed. Data Min. 5(1) (2016)Google Scholar
- 9.Jozefowicz, R., Zaremba, W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: Proceedings of the 32nd International Conference on Machine Learning (ICML-15), pp. 2342–2350 (2015)Google Scholar