Computational Intelligence and Modelling Techniques for Disease Detection in Mammogram Images / edited by D. Jude Hemanth.

Format:

Book

Contributor:

Hemanth, D. Jude, editor.

Language:

English

Subjects (All):

Breast--Cancer--Diagnosis.

Breast.

Breast--Cancer--Imaging.

Artificial intelligence--Medical applications.

Artificial intelligence.

Physical Description:

1 online resource (350 pages)

Edition:

First edition.

Place of Publication:

London, England : Academic Press, [2024]

Summary:

Computational Intelligence and Modelling Techniques for Disease Detection in Mammogram Images comprehensively examines the wide range of AI-based mammogram analysis methods for medical applications. Beginning with an introductory overview of mammogram data analysis, the book covers the current technologies such as ultrasound, molecular breast imaging (MBI), magnetic resonance (MR), and Positron Emission mammography (PEM), as well as the recent advancements in 3D breast tomosynthesis and 4D mammogram. Deep learning models are presented in each chapter to show how they can assist in the efficient processing of breast images. The book also discusses hybrid intelligence approaches for early-stage detection and the use of machine learning classifiers for cancer detection, staging and density assessment in order to develop a proper treatment plan. This book will not only aid computer scientists and medical practitioners in developing a real-time AI based mammogram analysis system, but also addresses the issues and challenges with the current processing methods which are not conducive for real-time applications. Presents novel ideas for AI based mammogram data analysis Discusses the roles deep learning and machine learning techniques play in efficient processing of mammogram images and in the accurate defining of different types of breast cancer Features dozens of real-world case studies from contributors across the globe.

Contents:

Front Cover

Computational Intelligence and Modelling Techniques for Disease Detection in Mammogram Images

Copyright

Contents

Contributors

Preface

1 - Mammogram data analysis: Trends, challenges, and future directions

1. Introduction

1.1 Theoretical background

1.1.1 "Sick lobe" model

1.1.2 Neoductgenesis

1.2 Technical knowledge

1.3 BC diagnosis using several imaging modalities

1.3.1 Mammography

1.3.2 Ultrasound

1.3.3 MRI

1.3.4 Histopathology

1.3.5 Thermography

1.4 Risk factors

1.5 Advantages in mammography

2. Related works

2.1 Microcalcification detection

2.2 Classification of mass

2.3 Feature-based BC detection

2.4 Computer-aided mammography

2.5 Database for mammogram images

2.5.1 INbreast

2.5.2 CBIS-DDSM

2.5.3 Image retrieval in medical applications

2.5.4 Mammographic Image Analysis Society

2.5.5 Breast cancer digital repository

2.5.6 BancoWeb LAPIMO

2.5.7 UCHC DigiMammo

3. Current trends in mammography analysis

3.1 Full field digital mammography

3.2 Digital mammography

3.2.1 Computed tomography electro-optical tomographic laser mammography

3.3 Scintimammography

3.4 Optical mammography

3.5 Digital breast tomosynthesis

3.6 Future of DBT imaging

4. Challenges in mammogram data analysis

4.1 General challenges in BC measurement and analysis

4.1.1 Shortcomings in primary care

4.1.2 Public secondary healthcare clinic mammography concerns

4.1.3 A gap between the BC detection strategy for primary care and secondary

4.1.4 Potential risks of mammography

4.1.5 Physical and mental suffering

4.1.6 Biopsies

4.2 Obstacles to data analytics in BC

4.2.1 Personal encounters and obstacles to obtaining assistance.

4.2.2 Connecting theory into practice

4.2.3 Carrying out mammograms

4.2.4 Communication

4.3 Breast density versus mammographic sensitivity

4.4 False alarms

4.5 Radiation dose and digital breast tomosynthesis

4.6 Artifacts caused by surgical staples

4.6.1 Imbalanced database

4.6.2 Insufficient standardization

4.7 Challenges in data analytics models

4.8 Robustness

4.9 Cyber security

5. Future directions of mammogram analysis

6. Conclusion

References

2 - AI in breast imaging: Applications, challenges, and future research

1.1 Breast cancer: Statistics

1.2 Breast imaging techniques and common breast abnormalities

1.3 Mammogram datasets

2. Toward AI for breast cancer diagnosis

2.1 AI applications for mammogram-based breast cancer analysis

2.1.1 Breast abnormality identification and categorization

2.1.2 Breast mass segmentation

2.1.3 Breast density assessment

2.1.4 Breast cancer risk assessment

2.1.5 BI-RADS classification

2.1.6 Axillary node assessment

2.2 Challenges and future research

3. Conclusion

3 - Prediction of breast cancer diagnosis using random forest classifier

2. Data set used

3. Several breast cancer risk factors

4. Various machine learning algorithms

4.1 Linear regression

4.2 SVM

4.3 Naive Bayes

4.4 Logistic regression

4.5 k-Nearest neighbors

4.6 Decision trees

4.7 RF algorithm

4.8 Boosted gradient decision trees

4.9 Clustering with k-means

4.10 Analysis by principal components

5. Case study

5.1 Various machine learning libraries used

5.1.1 Handling missing values

6. Experimental results and discussions

7. Conclusion

Further reading.

4 - Medical image analysis of masses in mammography using deep learning model for early diagnosis of cancer tissues

2. Related work

3. Proposed methodology

3.1 Datasets

3.2 Preprocessing

3.3 Image augmentation

3.4 Deep convolutional neural network

3.4.1 Training and testing

3.4.2 YOLO series object detectors

4. Performance analysis

4.1 Accuracy

4.2 Sensitivity

4.3 Specificity

4.4 Precision

5. Experimental results and discussions

5 - A framework for breast cancer diagnostics based on MobileNetV2 and LSTM-based deep learning

3. Deep learning framework for breast cancer diagnosis

3.1 MobileNet

3.1.1 Depthwise separable convolution

3.1.2 Pointwise convolution

3.1.3 ReLU activation

3.2 Long short-term memory

3.2.1 LSTM equation for cell state update

3.2.2 LSTM equation for hidden state update

3.2.3 LSTM equation for input gate

3.2.4 LSTM equation for output gate

3.2.5 LSTM equation for input transformation

4. Experimental results and discussion

4.1 Dataset collection

4.2 Feature set extraction

4.3 Performance evaluation

4.4 Exploring the efficacy of pretrained models in the training phase

4.5 Exploring the efficacy of models in the testing phase

4.6 Discussion

5. Conclusion

6 - Autoencoder-based dimensionality reduction in 3D breast images for efficient classification with processing by ...

3. System model

3.1 Autoencoder-based Kernel Principal analysis in dimensionality reduction

3.2 Regressive convolutional AlexNet architecture-based classification

4.1 Dataset description

7 - Prognosis of breast cancer using machine learning classifiers

2. Breast cancer

3. Machine learning

4. Machine intelligence-aided mammography

8 - Breast cancer diagnosis through microcalcification

1.1 Feature extraction

1.2 Shape feature extraction

1.3 Statistical feature extraction

1.4 Multiscale texture features extraction-wavelet-based method

1.5 Cluster features extraction

1.6 Classifiers

1.6.1 Neural networks

1.6.2 k-nearest neighbor classifiers

1.6.3 Nearest neighbor classifiers based on Euclidean distance

1.6.4 Support vector machines

2. Proposed method

2.1 Dataset

2.2 Feature selection

2.3 Transfer learning

2.3.1 Using AlexNet for transfer learning

3. Results and discussion

4. Conclusion

Further reading

9 - Scrutinization of mammogram images using deep learning

2. Literature review

2.1 Risk factors

2.2 Related work

3. Methodologies

3.1 Deep learning in mammography

3.2 Deep learning approaches for mammographic image processing

3.3 CNN methodologies in mammography

3.4 Comprehensive architecture of CNN in mammography

4. Resources and procedures

4.1 Data exploration

4.2 Techniques and methodologies

4.2.1 ResNet50

4.2.2 DenseNet201

4.2.3 AlexNet

4.2.4 VGG16

4.2.5 Base model with Keras Tuner

5. Findings and analysis

5.1 Discussions

5.1.1 Base model with augmentation

5.1.2 Base model without augmentation

5.2 Model summary

5.2.1 Base model with Keras Tuner (Table 9.1) shows the summarization of base model

5.2.2 AlexNet (Table 9.2) shows the summarization of AlexNet model

5.2.3 ResNet50 (Table 9.3) shows the summarization of the ResNet50 model.

5.2.4 DenseNet 201 (Table 9.4) shows the summarization of the DenseNet201 model

5.2.5 VGG16 (Table 9.5) shows the summarization of the VGG16 model

5.3 Results

5.3.1 AlexNet

5.3.2 ResNet50

5.3.3 DenseNet 201

5.3.4 VGG16

5.3.5 Base model with Keras Tuner and augmentation

6. Conclusions

7. Future work

10 - Computational techniques for analysis of breast cancer using molecular breast imaging

1.1 Anatomy and physiology of the breast

3. Statistics

4. Types of breast cancer

4.1 Invasive ductal carcinoma

4.2 Ductal carcinoma in situ

4.3 Invasive lobular carcinoma

4.4 Lobular carcinoma in situ

4.5 Inflammatory breast cancer

4.6 Pagets disease of the breast

4.7 Angiosarcoma

4.8 Phyllodes tumors

5. Screening methods

5.1 Mammography

5.2 Digital breast tomosynthesis

5.3 Contrast mammography

5.4 Ultrasound approach

5.4.1 Sonography

5.4.2 Automatic breast ultrasound

5.4.3 Contrast-enhanced ultrasound

5.4.4 Ultrasonography in three dimensions

5.4.5 Color Doppler

5.4.6 Power Doppler

5.4.7 Tissue elasticity imaging (sonoelastography)

5.4.8 Stress elastography

5.4.9 Shear wave elastography

5.4.10 Diffusion-weighted imaging

5.5 Magnetic resonance elastography

5.6 Magnetic resonance spectroscopy

5.7 Magnetic resonance imaging

5.8 Optical imaging

5.9 Nuclear imaging techniques

5.10 Molecular breast imaging

5.11 Positron-emission mammography

5.12 CZT-based molecular breast imaging system

5.13 Alternative radiopharmaceuticals

6. Image processing techniques

6.1 Artificial intelligence technique

6.2 Dataset

6.3 QIN-breast

6.4 Databases management of querying breast cancer image

7. Image processing techniques

7.1 Preprocessing techniques

7.1.1 Thresholding.

7.1.2 Segmentation based on region.

Notes:

Description based on print version record.

Includes bibliographical references and index.

Includes index.

Other Format:

Print version: Hemanth, D. Jude Computational Intelligence and Modelling Techniques for Disease Detection in Mammogram Images

ISBN:

0-443-14000-6

OCLC:

1410023973