声明
Acknowledgements
Abstract
Table of contents
List of figures
List of tables
Chapter 1 Introduction
1.1 Research background and significance
1.2 Breast cancer imaging diagnostic technology
1.3 Computer-Aided Diagnosis Technology
1.4 Main content and arrangement of this paper
1.4.1 Main research contents of this paper
1.4.2 Main Arrangements of the Paper
Chapter 2 Medical Image Processing and Deep Learning Foundation
2.1 Image data processing
2.1.1 Image multi-resolution expression
2.1.2 Color Image Processing
2.1.3 Image segmentation
2.1.4 Data Augmentation
2.2 Deep learning foundation
2.2.1 Learning from shallow to deep learning
2.2.2 Unsupervised deep learning algorithm
2.2.3 Supervised deep learning algorithm
2.3 Convolutional Neural Network Theory
2.3.1 Convolutional Neural Networks
2.3.2 GoogLeNet Convolutional Neural Network
2.3.3 Deep residual convolutional neural network
2.4 Summary of this chapter
Chapter 3 Medical Image Recognition Based on GoogLeNet
3.1 Introduction
3.2 Breast cancer pathology image classification process
3.2.1 Setting up an experimental environment
3.2.2 Build data set
3.2.3 Image preprocessing
3.3 GoogLeNet neural network model
3.3.1 GoogLeNet neural network model construction
3.3.2 Softmax classifier
3.3.3 Model training
3.4 Experimental results and analysis
3.4.1 Evaluation standard
3.4.2 Result analysis
3.4.3 Experimental summary
3.5 Summary of this chapter
Chapter 4 Breast cancer classification system based on GoogLeNet transfer model
4.1 Introduction
4.2 Build data set
4.2.1 Data preparation
4.2.2 Data augmentation
4.3 Transfer learning
4.4 Breast cancer classification and recognition system
4.4.1 Setup model
4.4.2 Training strategy
4.5 Result analysis
4.6 Summary of this chapter
Chapter 5 Summary and Outlook
5.1 Summary
5.2 Future research plan
References
Appendix
华中师范大学;