Cover Image

Machine learning and artificial intelligence in radiation oncology : a guide for clinicians /

"Machine Learning and Artificial Intelligence in Radiation Oncology: A Guide for Clinicians is designed for the application of practical concepts in machine learning to clinical radiation oncology. It addresses the existing void in a resource to educate practicing clinicians about how machine l...

Full description

Bibliographic Details
Corporate Author: ScienceDirect (Online service)
Other Authors: Kang, John (Editor), Rattay, Tim (Editor), Rosenstein, Barry S. (Editor)
Format: eBook
Language:English
Published: London, United Kingdom ; San Diego, CA : Academic Press, [2024]
Subjects:
Cancer > Radiotherapy > Data processing.
Artificial intelligence > Medical applications.
Machine learning.
Machine Learning
Cancer > Radiothérapie > Informatique.
Intelligence artificielle > Applications en médecine.
Apprentissage automatique.
Artificial intelligence > Medical applications
Cancer > Radiotherapy > Data processing
Machine learning
Electronic books.
Online Access:Connect to the full text of this electronic book
Table of Contents:
  • Fundamentals and overview. Fundamentals of machine learning. Abstract
  • Artificial intelligence and machine learning
  • Capturing and quantifying experience
  • Learning from experience
  • Nature of automated learning
  • Types of machine learning
  • Summary
  • References
  • Artificial intelligence, machine learning, and bioethics in clinical medicine. Abstract
  • Introduction
  • Principles of bioethics and AI/ML in clinical medicine and research
  • Ethical partnerships with AI/ML : recommendations for clinicians
  • Conclusion
  • References
  • Machine learning applications in cancer genomics. Abstract
  • Introduction
  • Overview of genomic technologies
  • Applications of genomics in oncology
  • Common hurdles of machine learning in genomics
  • Future directions
  • References
  • Radiomics : "unlocking the potential of medical images for precision radiation oncology." Abstract
  • Introduction
  • Radiomics workflow
  • Potential pitfalls in the radiomics pipeline
  • Recommendations for the standardization of radiomics research
  • A practical roadmap for radiomics research in radiation oncology
  • Translation of radiomics into the clinic
  • Conclusion
  • References
  • Deep learning for medical image segmentation. Abstract
  • Clinical need for automated image segmentation
  • Rationale of using deep learning for medical image segmentation
  • Typical deep learning framework
  • Practical considerations for segmentation model learning
  • Image pre-processing
  • Image patch selection
  • Data augmentation
  • Model fusion and output uncertainty assessment
  • Role of international competitions in medical image segmentation
  • AI-based image segmentation and beyond
  • Conclusion
  • References
  • Natural language processing in oncology. Abstract
  • What is natural language processing?
  • NLP in oncology
  • Use cases for NLP in oncology
  • The role of the clinician in developing an NLP system
  • General NLP tasks and challenges
  • Medical NLP tasks and challenges
  • NLP approaches
  • Tools and resources
  • Clinical implementation of an NLP system
  • Conclusions, limitations and future directions
  • References
  • Evaluating machine learning models: From development to clinical deployment. Abstract
  • Introduction
  • Model development
  • Model performance evaluation
  • Real world impact assessment
  • References
  • Research applications. Germline genomics in radiotherapy. Abstract
  • Overview of germline genomic analyses
  • Modern clinical genomics
  • Artificial intelligence in clinical genomics
  • Genome wide association studies (GWAS)
  • Radiogenomics
  • Machine learning and radiogenomics
  • Detection of epistasis using ML
  • Approaches to increasing statistical power using ML
  • Filtering : Pre-processing independent of model
  • Wrapper and embedded feature selection
  • Multi-step feature selection in radiogenomics
  • Conclusions
  • References
  • Tumor genomics in radiotherapy. Abstract
  • Introduction
  • Bioinformatics of tumor genomics
  • Example applications
  • Challenges and recommendations
  • Conclusions
  • References
  • Radiotherapy outcome prediction with medical imaging. Abstract
  • Introduction
  • Image biomarkers from pre-treatment imaging and RT outcome
  • Delta image biomarkers associations with radiation dose and outcome
  • Future directions and challenges in the clinical implementation and application of image biomarker prediction models in RT
  • Funding sources
  • Conclusion
  • References
  • Causal inference for oncology. Abstract
  • Introduction : background and history
  • Counterfactuals
  • Causal graphs
  • Emerging uses for machine learning for causal inference in oncology
  • References
  • Machine learning in quality assurance and treatment delivery. Abstract
  • Introduction
  • QA in the treatment planning process
  • QA in the treatment delivery process
  • Conclusion
  • References
  • Clinical applications and future developments. Case study : Deep learning in radiotherapy auto segmentation. Abstract
  • Clinical application of artificial intelligence (AI) to radiotherapy delineation
  • Optimization of AI driven auto-segmentation in the radiotherapy workflow
  • Clinical application of deep learning to radiotherapy
  • Challenges and solutions to clinical application of deep learning in auto-segmentation
  • Using federated learning to aid clinical adaptation
  • Conclusion
  • References
  • Case study : adaptive radiotherapy in the clinic. Abstract
  • Introduction
  • Adaptive radiation therapy for head and neck cancers
  • Adaptive radiation therapy workflows
  • Conclusion
  • References
  • Case study : handling small datasets Transfer learning for medical images. Abstract
  • Introduction
  • Dataset size
  • Data imbalance
  • Data augmentation
  • Transfer learning
  • Case study : Sarcopenia segmentation
  • Conclusion
  • References
  • Case study : lymph node malignancy classification for head and neck cancer radiation therapy. Abstract
  • Introduction
  • Initial model development using patients enrolled in the INFIELD trial
  • Model fine-tuning and validation on surgical patients with nodal status confirmed by pathology
  • Clinical implementation of the model for a prospective phase II study of involved nodal radiation therapy
  • Further development
  • Summary
  • References
  • Training the current and next generation in machine learning and artificial intelligence applications in radiation oncology. Abstract
  • Introduction
  • Learning to use, evaluate, and validate AI
  • Workforce needs in oncology
  • Case for informatics/ML integration into radiation oncology
  • Training opportunities during residency
  • Informatics fellowships
  • AI residencies in industry
  • Institutes, workshops, and conferences
  • Grant funding
  • Conclusion
  • References
  • Governance issues and commercialization. Abstract
  • Introduction
  • Developing commercial software
  • The regulatory landscape
  • A note on AI in clinical software
  • Conclusion
  • Index.