Introducing 

Prezi AI.

Your new presentation assistant.

Refine, enhance, and tailor your content, source relevant images, and edit visuals quicker than ever before.

Loading content…
Loading…
Transcript

Carl Williams / SP20: INFO 282-11

Medical Imaging Applications For

Artificial Intelligence

05/01/2020

Summary

Artificial intelligence (AI) has become a hot topic for many different types of organizations and academic departments over the past decade. Medical professionals believe AI will have a great impact in the immediate future of medical imaging technology. Diagnosing and treating patients will be improved through the use of big data and deep learning algorithms. The possibility of improving healthcare outcomes related to accurate and efficient medical imaging is particularly relevant due to the ongoing COVID-19 (SARS-CoV-2) pandemic. I believe AI technology will be implemented with wide scale use in the medical imaging field over the coming decade.

The Past

1

Visualization

Information Visualization

Past work in computer-assisted medicine has focused on the interaction between humans and the vast amount of data that is generated by this field of work.

Early systems were designed to analyze and present this data in a more "human-friendly" graphical format. This allowed users to understand the information without the need to know how such analytical processes are performed by the system

Aigner, Kaiser, and Miksch (2008) explain that "Information Visualization aims to deepen exploration of the 'information space', support optimal use of data and information, and help avoid overload".

Rationalization

Clinical Thought

IBM's Watson technology has been in development for the past few years with a wide range of applications. It has the ability to analyze image data and suggest a clinical inference to radiologists based on sound reasoning and deduction principles that would be applied by human reviewers.

This system relies on a partnership between technology and medical professionals to consistently improve results through user feedback.

The video to the right is a showcase of how the technology could be implemented, presented by IBM Research in 2017.

Innovation

Innovation

This news video from 2017 shows the emergence of research into artificial intelligence use for medical imaging diagnosis.

The Present

2

Prevalence

Healthcare Artificial Intelligence Market Share

It is clear from the chart on the right that, next to Drug Discovery, Medical Imaging & Diagnostics has a commanding portion of the market in terms of application for artificial intelligence in the medical industry.

Implementation

Current State

This video is an example of how AI is being implemented in radiological settings today.

NVIDIA's Clara technology is one program that has been developed to improve medical imaging review processes and precision radiology applications.

Regulation

Regulation

"The FDA’s traditional paradigm of medical device regulation was not designed for adaptive artificial intelligence and machine learning technologies. Under the FDA’s current approach to software modifications, the FDA anticipates that many of these artificial intelligence and machine learning-driven software changes to a device may need a premarket review" (US Food & Drug Administration, 2020).

Federal guidelines have been slow to adapt to the rapid advancement of AI technologies in the medical field. It is clear that a new approach is needed to evaluate and approve this type of technology for use in a medical setting. Patients expect that all systems will be cleared for use with thorough regulatory testing before they are implemented in hospitals or doctor's offices.

The Future

3

AI Solutions

This video discusses the improvements to quality of care for physicians and patients that can be provided in the future with increased AI medical imaging technology.

Canon Medical Systems endeavors to create collaborative teams of researchers who can create the next generation of medical imaging hardware and software applications.

Roles & Responsibilities

Roles & Responsibilities

"Socio-technical design research has posited for decades that as information flows to people lower in any system, the potential for decision-making authority flows along with it. Equipped with this scanning technology, can decisions that have traditionally been reserved for physicians shift to their nursing colleagues? To community health workers in the field? These are profound changes in role as well as in practice that need to be considered, tested, validated and implemented if the true potential of AI technology is to be realized" (Knowledge@Wharton, 2018).

Future implementation of AI technology will require robust training methods to train users in the use of novel tools for imaging and analysis. Automation will allow new groups of users to play a role in the radiological processes of patient care. This may decrease workloads on some medical professionals, or help to delineate work in a more efficient manner.

Increasing Demand

Increasing Demand

This chart shows market predictions for the future of AI in medical imaging from 2019-2027. The field is expected to grow in many imaging specialty areas, and may be implemented most widely in North America.

Conclusion

Conclusion

It is clear from a healthcare perspective that AI will provide enhanced services and improve radiological workflows. Although there is some concern about the accuracy of automated imaging diagnostic systems, any false identifications can be drastically reduced by human interaction with the system. As AI technology continues to be implemented, I expect to see a greater emphasis on human/computer partnerships that allow for more logical input from users. This feedback will be used to enhance AI capabilities, and provide a professional level of authority for making a diagnosis. This technology has the capability to drastically reduce workloads and increase the efficiency of providing critical care for patients in need.

References

Aigner, W., Kaiser, K., & Miksch, S. (2008). Visualization methods to support

guideline-based care management. In A. ten Teije, S. Miksch, & P. Lucas (Eds.), Computer-based medical guidelines and protocols: A primer and current trends (pp. 140-159). IOS Press.

Cannon Medical Systems. (2019, November 27). President and CEO Toshio

Takiguchi - The future of medical imaging [Video]. YouTube. https://www.youtube.com/watch?v=YnBsDvxs0VI

IBM Research. (2017, June 26). IBM researchers bring AI to radiology [Video].

YouTube. https://www.youtube.com/watch?v=XLb0xUe80uo

KBS News. (2017, January 22). AI & Medicine [Video]. YouTube. https://

www.youtube.com/watch?v=YnBsDvxs0VI

Knowledge@Wharton. (n.d.). How AI-based Systems Can Improve Medical

Outcomes. Retrieved from https://knowledge.wharton.upenn.edu/article/ai-based-systems-can-improve-medical-outcomes/

NVIDIA. (2019, January 18). Augmenting Radiology with AI [Video]. YouTube.

https://www.youtube.com/watch?v=9fAcjfnWyso

U.S. Food & Drug Administration. (2020). Artificial Intelligence and Machine

Learning in Software. Retrieved from https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-software-medical-device#regulation

Learn more about creating dynamic, engaging presentations with Prezi