乳腺癌是威全球女性健康最常见的恶性肿瘤。乳腺线摄影术是目前国际上公认的乳腺癌筛查及早期诊断的有效手段。最近人工智能技术迅速发展，计算机辅助诊断技术成为人工智能+医学图像领域的主要研究热点。作者综合论述了计算机视觉和图像处理技术在乳腺线图像分析中的应用，采用深度学习等人工智能域前沿技术，提出了一系列乳腺线图像分析方法，构建了新的自动化乳腺癌风险评估框架及肿块病变检测与良恶性诊断模型。

Contents
Chapter 1 Introduction
1.1 Breast Cancer Status
1.2 Mammography
1.3 Mammographic Risk Assessment
1.3.1 Wolfe’s Four Risk Categories
1.3.2 Boyd’s Six Class Categories
1.3.3 Four BIRADS Density Categories
1.3.4 Tabár’s Five Patterns
1.4 CAD in Mammography
1.5 Clinical Utility of the Present Research
1.6 Focus and Contributions of the Book
1.7 Book Outline
Chapter 2 A Literature Review of Mammographic Image Analysis
2.1 Mammographic Image Segmentation
2.1.1 Breast Region Segmentation
2.1.2 Breast Density Segmentation
2.2 Estimation of Mammographic Density
2.3 Characterisation of Mammographic Parenchymal Patterns
2.4 Breast Density Classification
2.5 Summary
Chapter 3 Image Segmentation in Mammography
3.1 Breast Region Segmentation in Mammograms
3.1.1 Methodology
3.1.2 Results and Discussion
3.2 A Modified FCM Algorithm for Breast Density Segmentation
3.2.1 FCM Algorithms
3.2.2 A Modified FCM Algorithm
3.2.3 Experimental Results
3.3 Topographic Representation Based Breast Density Segmentation
3.3.1 Topographic Representation
3.3.2 Segmentation of Dense Tissue Regions
3.3.3 Breast Density Quantification
3.3.4 Results
3.4 Summary
Chapter 4 Texture Analysis in Mammography
4.1 Local Feature Based Texture Representations
4.1.1 Local Binary Patterns
4.1.2 Local Grey-Level Appearances
4.1.3 Basic Image Features
4.1.4 Textons
4.2 Mammographic Tissue Appearance Modelling
4.3 Summary
Chapter 5 Multiscale Blob Detection in Mammography
5.1 Blob Detection
5.1.1 Laplacian of Gaussian
5.1.2 Difference of Gaussian
5.1.3 Determinant of the Hessian Matrix
5.1.4 Hessian-Laplacian
5.1.5 Fast-Hessian
5.1.6 Salient Region
5.2 A Blob Based Representation of Mammographic Parenchymal Patterns
5.2.1 Detection of Multiscale Blobs
5.2.2 Blob Merging
5.2.3 Blob Encoding
5.3 Results and Discussion
5.4 Summary
Chapter 6 Breast Cancer Risk Assessment
6.1 Experimental Data
6.1.1 MIAS Database
6.1.2 DDSM Database
6.2 Evaluation Methodology
6.2.1 Classification Algorithm
6.2.2 Cross-Validation Scheme
6.2.3 Result Representation
6.3 Evaluating the Proposed Methods
6.3.1 Evaluation of Breast Density Segmentation
6.3.2 Evaluation of Breast Tissue Appearance Modelling
6.3.3 A Combined Modelling of Breast Tissue
6.3.4 Evaluation of Blob-Based Representation
6.4 Summary
Chapter 7 Discussions on Breast Cancer Risk Assessment in Mammography
7.1 Comparison of the Proposed Methods
7.2 Comparing with Related Publications
7.3 Summary
Chapter 8 Computer-Aided Diagnosis of Breast Cancer Based on Deep Learning
8.1 Literature Review on Deep Learning Based Mammographic Image Analysis
8.2 Mass Detection and Classification in Mammograms withaDeepPipeline
8.2.1 Dataset Information
8.2.2 Model Architecture
8.2.3 Training
8.2.4 Results & Discussion
8.3 Summary
Chapter 9 Conclusions
9.1 Summary of the Book
9.2 Contributions and Novel Aspects
9.3 Future Work
Bibliography
Biography