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.

[1]  Ian T. Jolliffe,et al.  Principal component analysis: A beginner's guide — II. Pitfalls, myths and extensions , 1993 .

[2]  Lukás Burget,et al.  Extensions of recurrent neural network language model , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Asoke K. Nandi,et al.  Breast Cancer Diagnosis Using Genetic Programming Generated Feature , 2005, 2005 IEEE Workshop on Machine Learning for Signal Processing.

[4]  Dino Isa,et al.  An enhanced Support Vector Machine classification framework by using Euclidean distance function for text document categorization , 2011, Applied Intelligence.

[5]  M. Cevdet Ince,et al.  An expert system for detection of breast cancer based on association rules and neural network , 2009, Expert Syst. Appl..

[6]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

[7]  Younes Boujelbene,et al.  The Neural Networks with an Incremental Learning Algorithm Approach for Mass Classification in Breast Cancer , 2016 .

[8]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[9]  J. Dayhoff,et al.  Artificial neural networks , 2001, Cancer.

[10]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[11]  Joel Quintanilla-Domínguez,et al.  WBCD breast cancer database classification applying artificial metaplasticity neural network , 2011, Expert Syst. Appl..