1. To learn what can be expected from AI in radiology and to know the limitations of the technology.
2. To learn how AI technology can be integrated in the radiology workflow.
3. To learn how to make radiology knowledge available for AI training.
4. To learn how the introduction of AI in radiology will change the doctor-patient and radiologist-clinician relationship.
1. To know the challenges of knowledge management in radiology.
2. To know the advantages of machine learning technologies compared to traditional approaches.
3. To know the technical limitations of machine learning.
In their recent editorial in Academic Radiology, Cohan and Davenport refer to radiologist “burnout” and having reached a “tipping point”. They suggest that despite improvements in PACS and EMR's, “Radiologists are still being told to work faster as the screws continue to tighten; more images, greater case volume, increasing complexity and less time to do the work”. Radiologists are increasingly asked to perform quantitative analysis on complex dynamic studies such as prostate and breast MRI, analyse multi-parametric imaging from MRI, PET, CT, and to follow new guidelines for lung cancer and other screening studies. Deep learning represents a fundamentally different approach to the development of algorithms for image acquisition, quantitative analysis, and interpretation based on learning by example from large image sets. It offers numerous advantages over more “traditional” Computer Aided Design approaches including decreased time, and less specialised medical imaging expertise required for development as well as the potential for continuous and personalised refinement of algorithms. In fact, Deep Learning may actually have its greatest initial success in solving non-image related challenges such as image quality, workflow efficiency, improved communication and patient safety. This technology, however, is also fraught with limitations including the requirement for large amounts of annotated data, regulatory, medicolegal, and relative brittleness with regard to lack of generalizability from a few to a multitude of different scanners. Overall, despite the challenges, Deep Learning will undoubtedly have a major impact in the next several years on positively resetting radiology’s current “tipping point”.
1. To know the challenge: multitude of AI engines to be integrated in one workflow.
2. To learn how to collect and annotate radiology data for machine learning.
3. To learn how to organise radiologist's workflow when using AI.
4. To learn to manage radiology data to be used for machine learning.
1. To learn how radiologists will use machine learning in clinical routine.
2. To learn how machine learning will change the role of the radiologist (doctors-patient relationship, relationship between radiologists and referring physicians).
3. To learn how radiologists can prepare for machine learning.
An overview of how machine learning technologies may play a role in the workflow and task automation of radiologists, from appropriateness criteria to image acquisition, to image perception tasks and report generation, this talk will look at the entire ecosystem of diagnostic radiology and AI in the coming years.
Is there a future for radiology without the usage of AI?
Discuss the main challenges from radiologist's perspective
Clinical validation of AI: it looks like it is lacking
Ethical considerations when using AI in radiology