Artificial Intelligence in Pathology

Principles and Applications

2nd Edition - November 15, 2024
Imprint: Elsevier
Editors: Chhavi Chauhan, Stanley Cohen
Language: English
Paperback ISBN:
9 7 8 - 0 - 3 2 3 - 9 5 3 5 9 - 7
eBook ISBN:
9 7 8 - 0 - 3 2 3 - 9 5 8 3 2 - 5

Artificial Intelligence in Pathology: Principles and Applications provides a strong foundation of core artificial intelligence principles and their applications in the field of… Read more

Purchase options

World Book Day Celebration!

Save up to 30% on books and eBooks!

Shop now

Institutional subscription on ScienceDirect

Request a sales quote

Artificial Intelligence in Pathology: Principles and Applications provides a strong foundation of core artificial intelligence principles and their applications in the field of digital pathology. This is a reference of current and emerging use of AI in digital pathology as well as the emerging utility of quantum artificial intelligence and neuromorphic computing in digital pathology. It is a must-have educational resource for lay public, researchers, academicians, practitioners, policymakers, key administrators, and vendors to stay current with the shifting landscapes within the emerging field of digital pathology. It is also of use to workers in other diagnostic imaging areas such as radiology.

This resource covers various aspects of the use of AI in pathology, including but not limited to the basic principles, advanced applications, challenges in the development, deployment, adoption, and scalability of AI-based models in pathology, the innumerous benefits of applying and integrating AI in the practice of pathology, ethical considerations for the safe adoption and deployment of AI in pathology.

Artificial Intelligence in Pathology
Cover image
Title page
Table of Contents
Copyright
Contributors
Preface
Acknowledgments
Part I: Principles
Chapter 1 The evolution of machine learning: Past, present, and future
Abstract
Keywords
Introduction
Rules-based vs machine learning: A deeper look
Varieties of machine learning
General aspects of machine learning
Deep learning and neural networks
The role of AI in pathology
Limitations of AI
General aspects of AI
References
Chapter 2 The basics of machine learning: Strategies and techniques
Abstract
Keywords
Introduction
Shallow learning
Geometric (distance-based) models
The K-means algorithm (KM)
Probabilistic models
Decision trees and random forests
The curse of dimensionality and PCA
Deep learning and the ANN
Neuroscience 101
The rise of the machines
The basic ANN
The weights in an ANN
Learning from examples: Backprop and stochastic gradient descent
Convolutional neural networks
Overview
Detailed explanation
Overfitting and underfitting
Things to come
References
Chapter 3 Overview of advanced neural network architectures
Abstract
Keywords
Introduction
Network depth and residual connections
Autoencoders and unsupervised pretraining
Transfer learning
Generative models and generative adversarial networks
Recurrent neural networks
Reinforcement learning
Ensembles
Genetic algorithms
References
Chapter 4 Complexity in the use of artificial intelligence in anatomic pathology
Abstract
Keywords
Introduction
Life before machine learning
Multilabel classification
Single object detection
Multiple objects
Advances in multilabel classification
Graphical neural networks
Capsule networks
Weakly supervised learning
Synthetic data
N-shot learning
One-class learning
Risk analysis
General considerations
Summary and conclusions
References
Chapter 5 Dealing with data: Strategies of preprocessing data
Abstract
Keywords
Introduction
Overview of preprocessing
Feature selection, extraction, and correction
Feature transformation, standardization, and normalization
Feature engineering
Mathematical approaches to dimensional reduction
Dimensional reduction in deep learning
Imperfect class separation in the training set
Fairness and bias in machine learning
Summary
References
Chapter 6 Artificial intelligence in pathology: Easing the burden of annotation
Abstract
Keywords
Introduction
Artificial intelligence 101
The human in the loop: Harvesting usable data
Reducing the need for annotated data
Overview of unsupervised pretraining
Transfer learning
Unsupervised pretraining via clustering
One class learning
Unsupervised pretraining via autoencoders
Unsupervised pretraining via generative adversarial networks
Reinforcement learning (RL)
Self-supervised learning
Zero shot learning
Drowning in data: Quantum computing to the rescue
Summary and overview
References
Chapter 7 Digital pathology as a platform for primary diagnosis and augmentation via deep learning
Abstract
Keywords
Introduction
Digital imaging in pathology
Telepathology
Whole slide imaging (WSI)
Whole slide image viewers
Whole slide image data and workflow management
Selection criteria for a whole slide scanner
Evolution of whole slide imaging systems
Infrastructure requirements and checklist for rolling out high-throughput whole slide imaging workflow solution
WSI and primary diagnosis
WSI and image analysis
WSI and deep learning
Conclusions
References
Chapter 8 Artificial intelligence model development, deployment, and regulatory challenges in anatomic pathology
Abstract
Keywords
Introduction
Development challenges
Problem identification
Dataset curation and annotation
Model development and training
Hardware and cost
Deployment challenges
Pathologist buy-in and transitioning to a digital workflow
IT infrastructure: Cloud computing vs. on-premises solutions
Lack of pathologist’s experience with AI
What is the right evidence standard for AI to be embedded in practice?
What is required for clinical validation prior to using AI for diagnostic purposes?
What is the ideal workflow when implementing AI in clinical practice?
What model do pathology laboratories use to pay AI vendors?
What is the business use case for deploying AI?
Should residents or fellows be allowed to use AI, or is this “cheating?”
Regulatory challenges
FDA
European Union Conformité Européenne
CMS/CLIA
Conclusion
References
Chapter 9 Ethics of AI in pathology: Current paradigms and emerging issues
Abstract
Keywords
Disclosures
Introduction
Ethical AI study designs in pathology
Inclusive AI design and bias
Race in ethical AI design
Stakeholder concerns: Consent and awareness
Risks of AI in pathology and to pathologists—Real or imagined?
Underestimating the risks of AI to pathology
Overestimating the risks of AI to pathology
Institutional frameworks to enable ethical AI in pathology
Transparency
Accountability
Governance
Recent developments in the use of AI in pathology
Conclusions
References
Part II: Applications
Chapter 10 Applications of artificial intelligence for image enhancement in pathology
Abstract
Keywords
Acknowledgement
Introduction
Common machine learning tasks
Classification
Segmentation
Image translation and style transfer
Commonly used deep learning methodologies
Convolutional neural networks
U-nets
Generative adversarial networks and their variants
Common training and testing practices
Dataset preparation and preprocessing
Loss functions
Metrics
Deep learning for microscopy enhancement in histopathology
Stain color normalization
Mode switching
In silico labeling
Super-resolution, extended depth-of-field, and denoising
Deep learning for computationally aided diagnosis in histopathology
A rationale for AI-assisted imaging and interpretation
Approaches to rapid histology interpretations
Future prospects
References
Chapter 11 Foundation models and information retrieval in digital pathology
Abstract
Keywords
Introduction
Information retrieval
Image search
Validation of image search methods
Large deep models
Foundation models
Generative AI
Information retrieval and foundation models
Conclusions
References
Chapter 12 Precision medicine in digital pathology via image analysis and machine learning
Abstract
Keywords
Acknowledgments
Introduction
Precision medicine
Digital pathology
Applications of image analysis and machine learning
Knowledge-driven image analysis
Machine learning for image segmentation
Deep learning for image segmentation
Spatial resolution
Machine learning on extracted data
Beyond augmentation
Practical concepts and theory of machine learning
Machine learning and digital pathology
Common techniques
Supervised learning
Unsupervised learning
Image-based digital pathology
Conventional approaches to image analysis
Deep learning on images
Regulatory concerns and considerations
References
Chapter 13 Generative deep learning in digital pathology
Abstract
Keywords
Acknowledgments
Introduction
Deep generative models
Generative models in the digital pathology pipeline
Color and intensity normalization
Data adaptation
Data synthesis
Future directions
Conclusion
References
Chapter 14 Artificial intelligence methods for predictive image-based grading of human cancers
Abstract
Keywords
Introduction
Tissue preparation and staining
Image acquisition
Stain normalization
Unmixing of immunofluorescence spectral images
Automated detection of tumor regions in whole-slide images
Localization of diagnostically relevant regions of interest in whole-slide images
Tumor detection
Image segmentation
Nuclear and epithelial segmentation in IF images
Nuclei detection and segmentation in H&E images
Epithelial segmentation in H&E images
Mitotic figure detection
Ring segmentation
Protein biomarker features
Morphological features for cancer grading and prognosis
Modeling
Cox proportional hazards model
Neural networks
Decision trees and random forests
SVM-based methods: Survival-SVM, SVCR, and SVRc
Feature selection tools
Ground truth data for AI-based features
Conclusion
References
Chapter 15 Artificial intelligence and the interplay between cancer and immunity
Abstract
Keywords
Introduction
Immune surveillance and immunotherapy
Identifying TILs with deep learning
Spatial cancer biology with Pathomics, immunohistochemistry, and immunofluorescence
Conclusion
References
Chapter 16 Overview of the role of artificial intelligence in pathology: The computer as a pathology digital assistant
Abstract
Keywords
Introduction
Computational pathology: Background and philosophy
The current state of diagnostics in pathology and the evolving computational opportunities: “why now?”
Digital pathology versus computational pathology
Data on scale
Machine learning tools in computational pathology: Types of artificial intelligence
The need for human intelligence-artificial intelligence partnerships
Human-transparent machine learning approaches
Explainable artificial intelligence
Cognitive artificial intelligence
Human-in-the-loop
One-shot learning
Image-based computational pathology
Core premise of image analytics: What is a high-resolution image?
The targets of image-based calculations
First fruits of computational pathology: The evolving digital assistant
The digital assistant for quality control
The digital assistant for histological object segmentation
The digital assistant in immunohistochemistry
The digital assistant in tissue classification
The digital assistant in finding metastases
The digital assistant in predictive modeling and precision medicine
The digital assistant for anatomical simulation learning
The digital assistant for image-omics data fusion
Artificial intelligence and regulatory challenges
Educating machines-educating us: Learning how to learn with machines
References
Chapter 17 Overview and coda: The future of AI
Abstract
Keywords
Introduction
Transformers and attention
Neuromorphic computing
Quantum computing
Summary and conclusions
References
Index

Chhavi Chauhan

Dr. Chhavi Chauhan works as Director for Scientific Outreach at the American Society for Investigative Pathology. She is one of the leaders of the Women in AI Ethics Collective and an expert at the AI Policy Exchange.  She is a biomedical researcher, expert scholarly communicator, and a sought-after mentor in the fields of scientific research, scholarly publishing, and AI Ethics, especially for women and minorities. She was honored to be featured in The AI Makers 150: top 150 AI &Analytics Leaders & Influencers 2021 list. She is a thought leader, a renowned international speaker, and a strong advocate for equitable and accessible healthcare.  She sits at the intersection of scientific research, scholarly communications, and AI Ethics in Healthcare.   Her vision is to provide equitable personalized healthcare to all, beyond geographies, and despite socioeconomic barriers.

Affiliations and expertise

Director of Scientific Outreach, American Society for Investigative Pathology, Rockville, MD, USA

Stanley Cohen

Dr. Cohen is currently interested in integrating computational imaging with digital workflows. He previously served as President of the American Society for Investigative Pathology (ASIP) and Treasurer and Member of the Executive Board of FASEB. Science-related activities also include chairmanships of study sections for the NIH and DOD and membership on multiple editorial boards. He is currently the Associate Editor for digital and computational pathology and artificial intelligence topic category for the American Journal of Pathology. He is a Senior Fellow of the Association of Pathology Chairs and Co-Chair of the ASIP Special Interest Group on Digital and Computational Pathology. Awards include the Gold-Headed Cane (ASIP) and the Golden Goose Award (AAAS). He is a member of the Digital Pathology Association (DPA), the Board of the International Academy of Digital Pathology (IADP), and Chair of the External Advisory Board of the Alpert Foundation.

Affiliations and expertise

PhD, MD

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health