Keynote address: ​Radiology’s post pandemic future

How will the profound global disruption created by the novel coronavirus impactthe future of radiology? Will innovation be accelerated or grind to a halt? Which of the emergency accommodations in regulatory policy outlast the virus and how will they change the practice of radiology? How will we take the valuable lessons we have learned during this crisis and use them to shape our profession in apositive way?

Geraldine McGinty MD MBA FACR, President, ​American College of Radiology, Departments of Radiology and Population Science, ​Weill Cornell Medicine

 

 

Module 1: Data issues in radiology for artificial intelligence

For AI innovation, the starting point always has to be the data. But what constitutes good quality data, how can it be accessed, and can you ever have enough?

  • Understanding the different types of data and how to integrate and harmonize datasets
  • Acknowledging the limitations of healthcare data, including heterogeneity
  • Challenges around data privacy and security

 

Dr Matthew Lungren, Co-Director, Stanford Center for Artificial Intelligence in Medicine and Imaging

Dr Sudhen Desai, Director of Research, Interventional Radiology, Baylor College of Medicine

 

 

Education partner presentation: An epidemic during a pandemic: Radiologist burnout in the setting of COVID-19

COVID-19 pandemic has turned the world upside down and the field of radiology is not immune. How has radiology changed? Are you prepared for what the future might hold? Learn how radiologists as individuals, radiology as a field, and emerging technologies will all need to adapt to a changing healthcare environment.


David Gruen, MD, MBA, FACR, Chief Medical Officer, Imaging, Watson Health and Diagnostic Radiologist, Jefferson Radiology, CT, USA

 

 

Module 2: Machine and Deep Learning in Medical Imaging

Machine and deep learning can help in reviewing data, as well as potentially seeing patterns which clinicians might not otherwise pick up. This session will offer real examples that are happening in radiology right now.

  • Convolutional neural networks
  • Recurrent neural networks
  • Deep reinforcement learning

Peter Chang, MD, Assistant Professor In-Residence, Department of Radiology, and Co-Director, Center of AI in Diagnostic Medicine, UC Irvine Medical Center

Dr Tanveer Syeda-Mahmood, IBM Fellow, Chief Scientist, IBM Almaden Research Center and Visiting Scholar, Stanford University

 

 

Education partner presentation: The clinical value of radiology AI

Sharing reflections on the clinical value of the AI-Rad Companion and how AI is supporting radiologists in their daily work. Also sharing experiences of AI algorithms that bring value and support in the fight against COVID-19.

Professor Philippe Grenier, Former Professor of Radiology and Chairman, Sorbonne University, and AI Implementation Lead, Hôpital Foch

 

 

Module 3: Natural language processing in radiology workflow

NLP is already being used to great effect in radiology workflow. This session will feature live examples, as well as the different business and care delivery models that are working in deployment.

  • Applying NLP to EHR and data mining
  • Reflections on the deployment of chatbots
  • Labeling and NLP

Dr Matthew Lungren, Co-Director, Stanford Center for Artificial Intelligence in Medicine and Imaging

Dr Orest Boyko, Associate Professor of Radiology, University of Southern California

 

 

Education partner presentation: Simplifying DevOps for AI Projects

Modern businesses are building smarter applications powered by massive amounts of data generated at scale. Utilizing the right AI infrastructure lets you unleash the productivity of your data scientists. Providing a containerized AI platform improves data scientists and IT productivity. For example, enable users to access large, shared datasets with minimal data management hassle. 

We’ll discuss ways a DevOps-minded AI strategy can impact time to production. 

Emily Potyraj, AI Solution Architect, Pure Storage

 

 

Module 4: Essential issues in AI in radiology

Picking up on some of the prevailing concerns around AI in radiology, including data governance and liability, regulatory compliance and explainability.

  • Addressing the key ethical questions around artificial intelligence
  • Mitigating bias through true data diversity
  • Regulation and control of data sharing: public interest vs. patient privacy
  • FDA clearance and CE marks

Dr Woojin Kim, Musculoskeletal Radiologist and Imaging Informaticist, Palo Alto VA Hospital

Dr Orest Boyko, Associate Professor of Radiology, University of Southern California

David Gruen, MD, MBA, FACR, Chief Medical Officer, Imaging, Watson Health and Diagnostic Radiologist, Jefferson Radiology, CT, USA

Dr Antonio Cisternino, Professor of Computer Science and Chief Information Officer, University of Pisa