Within this second volume dealing with breast and bladder cancer, the editors and authors will detail the latest research related to the application of AI to cancer diagnosis and prognosis and summarize its advantages. It's the editors and authors intention to explore how AI assists in these activities, specifically with regard to its unprecedented accuracy, which is even higher than that of general statistical applications in oncology. Ways will also be demonstrated as to how these methods in AI are advancing the field.
There have been thousands of papers written between 1995 and 2019 related to AI for cancer diagnosis and prognosis. However, to this date (and unknown to the Editors) there has not yet been published a comprehensive overview of the latest findings pertaining to these AI technologies, with a single book project(s). Therefore, the purpose of this three volume work and particularly for this second volume dealing with breast and bladder cancer, is to present a compendium of these findings related to these two pervasive cancers. Many of the chapter authors are world class researchers in these technologies. Within this coverage it's our hope that scientists, researchers and clinicians can successfully incorporate these techniques into other significant cancers such as pancreatic, esophageal, leukemia, melanoma, etc.
Author(s): Ayman El-Baz, Jasjit S. Suri
Series: IPEM–IOP Series in Physics and Engineering in Medicine and Biology
Publisher: IOP Publishing
Year: 2022
Language: English
Pages: 376
City: Bristol
PRELIMS.pdf
Preface
Acknowledgements
Editor biographies
Ayman El-Baz
Jasjit S Suri
List of contributors
Outline placeholder
Abdullah-Al Nahid
Fatma Anwar
Omneya Attallah
Bensujin Bennet
Yin Dai
Fei Gao
Yuliana Jiménez Gaona
Nagia M Ghanem
Agus Rizal A H Hamid
Tao Huang
Mohamed A Ismail
Shomona Gracia Jacob
R Karthiga
Elliot S Kim
Valentina L Kouznetsova
Vasudevan Lakshminarayanan
Yang Lei
Chen Li
Xiaoyan Li
Tian Liu
Darwin Castillo Malla
Shadab Momin
K Narasimhan
Anindya Pradipta
Keerthana Prasad
Saifur Rahman Sabuj
Johir Raihan
N Raju
R Rashmi
María José Rodríguez-Álvarez
Niloy Sikder
Mashiro Sugimoto
Shenghua Tian
Igor F Tsigelny
Chethana Babu K Udupa
Changchun Yang
Xiaofeng Yang
Prasandhya A Yusuf
Haiqing Zhang
Yuchao Zheng
Xiaomin Zhou
CH001.pdf
Chapter 1 Development of artificial neural networks for breast histopathological image analysis
1.1 Introduction
1.1.1 General development of the current AI analysis of histopathology
1.2 BHIA using classical ANNs
1.2.1 Related works
1.2.2 Summary
1.3 BHIA using deep neural networks
1.3.1 Related works
1.3.2 Summary
1.4 Methodological analysis
1.4.1 Analysis of classical ANN methods
1.4.2 Analysis of deep ANN methods
1.5 Conclusions
Acknowledgements
References
CH002.pdf
Chapter 2 Machine learning in bladder cancer diagnosis
2.1 Introduction
2.1.1 Previous metabolomic studies of BCa detection
2.2 The approach (overview)
2.2.1 MetaboAnalyst
2.2.2 Ingenuity® pathway analysis
2.2.3 Venny
2.2.4 Analysis via machine learning
2.2.5 Datasets
2.3 Results
2.3.1 BCa metabolic pathways
2.3.2 Integrative analysis of the networks
2.4 Feedback loops that include genes and metabolites
2.5 Machine learning classifiers
2.6 Conclusions
References
CH003.pdf
Chapter 3 Deep learning in photoacoustic breast cancer imaging
3.1 Introduction
3.1.1 Photoacoustic imaging
3.1.2 Deep learning
3.2 Deep learning in photoacoustic breast cancer imaging
3.2.1 Data synthesis
3.2.2 Semantic image annotation
3.3 Conclusions and outlook
References
CH004.pdf
Chapter 4 Histopathological breast cancer image classification with feature prioritization using a heuristic algorithm
4.1 Introduction
4.2 Methodology
4.2.1 Feature extraction
4.2.2 Classifier tools
4.2.3 Feature selection
4.2.4 Performance metrics
4.3 Results for extracted features
4.3.1 On separate datasets
4.3.2 Ensemble
4.4 Feature selection
4.4.1 Genetic-algorithm-based feature selection
4.4.2 Results for selected features
4.5 Comparison with other findings
4.6 Conclusions
References
CH005.pdf
Chapter 5 The use of machine learning and biofluid metabolomics in breast cancer diagnosis
5.1 Introduction
5.2 Metabolomics
5.2.1 Biomarkers for breast cancer diagnosis
5.3 Diagnosis method using multiple markers
5.3.1 Quality control of measurement and biomarker discoveries
5.3.2 Multivariate analysis for classification
5.3.3 Artificial intelligence-based approach
5.4 Discussion
5.5 Conclusions
References
CH006.pdf
Chapter 6 AUTO-BREAST: a fully automated pipeline for breast cancer diagnosis using AI technology
6.1 Introduction
6.2 Methods
6.2.1 Datasets
6.2.2 Proposed AUTO-BREAST pipeline
6.3 Assessment measures
6.4 Results
6.4.1 Scenario I results
6.4.2 Scenario II results
6.4.3 Scenario III results
6.5 Discussion
6.6 Conclusions
References
CH007.pdf
Chapter 7 Diagnosis of breast cancer from histopathological images using artificial intelligence
7.1 Background of artificial intelligence
7.2 Introduction to breast cancer
7.2.1 Histopathology
7.2.2 Histology tissue preparation procedures
7.2.3 Scarff–Bloom–Richardson (SBR) grading
7.2.4 Types of breast cancer
7.3 Application of AI to histopathological image analysis
7.3.1 Motivation
7.3.2 Datasets
7.3.3 Classification of AI methods
7.4 Discussion
References and further reading
CH008.pdf
Chapter 8 The role of artificial intelligence in the field of bladder cancer
8.1 Introduction
8.2 The unmet need in BCa management and how AI can help
8.2.1 Urinary cytology detection
8.2.2 Cystoscopy detection
8.2.3 Histopathology detection
8.2.4 Radiology detection
8.2.5 BCa predictive evaluation
8.3 The challenge of AI implementation in BCa management
8.4 Conclusions
Acknowledgment
References
CH009.pdf
Chapter 9 Exploring data science paradigms in breast cancer classification: linking data, learning, and artificial intelligence in medical diagnosis
9.1 Introduction
9.2 Data management for machine learning
9.2.1 Issues in data management for ML and AI
9.2.2 Data corroboration
9.2.3 Data correction
9.2.4 Data amelioration
9.3 Machine learning in breast cancer research
9.4 Computational approaches: challenges and achievements in healthcare
9.5 AI tools used in breast cancer research
9.6 Conclusions and the future of AI in healthcare
References and further reading
CH010.pdf
Chapter 10 Automatic detection and classification of invasive ductal carcinoma in histopathology images using convolutional neural networks
10.1 Introduction
10.1.1 Mammography
10.1.2 Digital breast tomosynthesis
10.1.3 Contrast-enhanced digital mammogram
10.1.4 Sonography
10.1.5 Automated breast ultrasound
10.1.6 Doppler techniques
10.1.7 Sonoelastography
10.1.8 Magnetic resonance imaging
10.1.9 Optical imaging
10.1.10 Microwave imaging
10.1.11 Thermal imaging
10.1.12 Histopathology
10.1.13 Artificial intelligence
10.1.14 Machine learning
10.1.15 Deep learning
10.2 Literature survey
10.3 Methodology
10.3.1 Dataset
10.3.2 Proposed work
10.3.3 Results and discussion
10.4 Conclusions
References
CH011.pdf
Chapter 11 Machine learning analysis of breast cancer single-cell omics data
11.1 Introduction
11.2 Single-cell data analysis
11.2.1 Imputation of gene expression
11.2.2 Cell clustering
11.2.3 Identification of marker genes
11.2.4 Regulatory network analysis
11.2.5 Spatial transcriptomics
11.2.6 scATAC
11.2.7 scDNA methylation
11.2.8 Single-cell exome
11.2.9 Single-cell metabolome
11.2.10 Integrated analysis
11.3 Breast cancer single-cell studies
11.4 Outlook
References
CH012.pdf
Chapter 12 Radiomics, deep learning, and breast cancer detection
12.1 Introduction
12.1.1 Imaging modalities used for breast cancer
12.2 Overview
12.2.1 Literature review
12.2.2 Blibliometric analysis
12.2.3 Imaging modalities and databases
12.2.4 Morphological features
12.2.5 Deep learning methods
12.2.6 Deep learning CAD system steps
12.3 Results
12.3.1 Databases
12.3.2 Deep learning architectures and performance metrics
12.4 Discussion and conclusions
References and further reading
CH013.pdf
Chapter 13 Artificial-intelligence-based techniques for the diagnosis of bladder and breast cancer
13.1 Introduction
13.2 Method
13.2.1 Article search and selection
13.3 Results
13.3.1 Traditional ML methods
13.3.2 DL methods
13.4 Discussion and conclusions
References
