Scribd
Upload
134 views21 pages

AI in Radiology

This document discusses artificial intelligence in radiology. It provides an overview of AI and machine learning techniques like deep learning. It describes how AI can benefit radiology by improving diagnostic accuracy, enabling personalized medicine, and optimizing workflows. Examples are given of AI applications like stroke prediction from brain imaging. The document outlines steps for implementing AI projects and challenges to clinical adoption, including the need for multidisciplinary collaboration and adapting education. It concludes that while AI shows great potential, real-world integration into radiology is still developing.

Uploaded by

frehanyaq
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
134 views21 pages

AI in Radiology

This document discusses artificial intelligence in radiology. It provides an overview of AI and machine learning techniques like deep learning. It describes how AI can benefit radiology by improving diagnostic accuracy, enabling personalized medicine, and optimizing workflows. Examples are given of AI applications like stroke prediction from brain imaging. The document outlines steps for implementing AI projects and challenges to clinical adoption, including the need for multidisciplinary collaboration and adapting education. It concludes that while AI shows great potential, real-world integration into radiology is still developing.

Uploaded by

frehanyaq
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 21

Artificial Intelligence in Radiology

Reyhan Eddy Yunus, MD, MSc


Department of Radiology
Universitas Indonesia Hospital
Cipto Mangunkusumo General Hospital

DISTP UI Webinar – 18th May 2020


Radiology: past, present, future
• Dartmouth College, Hanover, New Hampshire, AS, 1956
Artificial Intelligence • John McCarthy
Artificial Intelligence
• A set of tools and programs that
make software “smarter” to the
extent that an outside observer
thinks the output is generated by
human.
• Operates similarly to the way of
normal human brain functions
during regular tasks like common-
sense reasoning, forming an
opinion, or social behavior.
Artificial
Intelligence
Publications of
AI in medical
imaging

Pesapane, Filippo & Codari, Marina & Sardanelli, Francesco. (2018). Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the
forefront of innovation in medicine. European Radiology Experimental. 2. 10.1186/s41747-018-0061-6.
What is a medical image?
Machine learning - Deep learning
Deep learning in medical imaging
How do we do AI?

Machine Learning for Medical Imaging


RadioGraphics 2017; 37:505–515
Bradley J. Erickson, et al
Benefits of AI in medicine
• Improving patient outcome
• Increase diagnostic accuracy
• Personalized medicine
• Enhanced patient experience and workflow
• Speed up the patient management
• Management of big data in medicine
• Reducing cost of healthcare
• Workflow optimization
Radiology workflow with AI
Stroke score (ASPECTS) prediction
• Radiomics • Radiogenomics
• Automated extraction, storage, • Extension of radiomics, aiming to
and analysis of large amount of identify link between genotype
imaging features (morphology and and phenotype imaging.
imaging biomarkers).
AI in COVID-19 medical imaging
AI implementation steps in radiology
• Define purpose
• Data collecting
• Data cleaning
• Data grouping / labelling
• Preprocessing
• Training
• Testing
• Validating
• Improvement
• Implementation
Montagnon, E., Cerny, M., Cadrin-Chênevert, A. et al. Deep
learning workflow in radiology: a primer. Insights Imaging 11, 22
(2020).
Challenges of implementing AI in radiology
• Medicolegal
• Multidisciplinary approach
• Higher education institution
• Lack of interest
• Lack of knowledge
• Lack of speed to adapt
• Lack of resource
• Lack of rules and law

• Need to create a system and environment that promotes AI in


education, practice, and research
The (current) real world of AI in radiology
Medicine and Healthcare: Art and Science
Take home points
• Developing AI in radiology
• Machine learning - Deep learning
• Many benefits of AI in radiology
• From detection, diagnosis, to prediction
• Workflow improvement
• Implementation challenges
• Clinical implementation is still slow
• Multidisciplinary approach
• Research – education environment
• The (near) future of radiology
Thank you

You might also like