RSNA 2017 – Dominated by AI Imaging Startups

What is RSNA?

Every year, the Radiological Society of North America (RSNA) hosts its annual meeting the week after Thanksgiving in Chicago. This is one of the largest medical conferences in the world, with over 50,000 attendees from 57 countries. This year, RSNA was organized from 26th Nov to 1st Dec and gathered approximately 700 exhibitors.

Highlight of RSNA 2017

During RSNA 2016, there was hype around AI in Radiology Imaging Diagnostics. This year, about 20 startup companies came up with the AI models that can augment radiologists findings. The AI models were available across Modalities and Pathology. Even though it can not replace a radiologist, it improves accuracy and speed of diagnostics thereby reducing the cost of diagnosis.  For some of the companies, FDA/CE has approved their AI Models which means that the results are as accurate as a human.

Relevance of AI machine learning/Deep learning in Radiology Diagnostics

Radiology diagnostic industry in the USA

US Diagnostic Imaging Market is around $4.5 billion and expected to grow 36.43 Billion by 2021.

North America is one of the most lucrative regions for medical imaging market because of its better infrastructure facilities. When compared to emerging regions, it has high-end purchasing power coupled with reimbursement facilities. U.S is the dominating region owing to its population base having large insurance coverage, advancement in technology, a sizable aging population along with the prevalence of chronic disease.

Radiology diagnostics current state

According to a market research, sponsored by IBM, there were roughly 800 million multi-slice exams performed in the United States in 2015 alone. Those studies generated approximately 60 billion medical images. At those volumes, each of 31,000 odd radiologists in the U.S., has to view an image every two seconds of every working day for an entire year to find potentially life-saving information from a handful of images hidden in a sea of data. It is evident from the data that medical images are going to get generated exponentially and there is a shortage of radiologist, on the other hand, it will take ten years of training to become a radiologist. In this scenario, AI Imaging technology has relevance.

RSNA1

Statistics of Medical images vs. Case studies conducted vs. Radiologists

Impact of the emerging trend for Radiologists

The average radiologist’s salary is $286,000 a year. In the U.S., there are 31,000 radiologists.

That means around 9 billion dollars a year is being spent on radiologists. AI and Deep learning is predicted to bring down the headcount of the radiologist but will not replace the radiologist. In RSNA 2017, some of the AI models developed demonstrated capability on par with a professional radiologist. The radiologist can embrace AI or be left behind.

Emerging Medical Imaging AI Companies who Participated in RSNA 2017

Arterys

Arterys helps doctors diagnose heart problems in just 15 seconds while it takes around 30 minutes for a human.

Zebra Medical Vision

Their application of machine learning identifies abnormalities in CT scans.  It can automatically detect low bone mineral density, fatty liver, calcium, emphysema, coronary artery, breast cancer and more. The machine can do all these analyses in an hour.

Enlitic 

Developed a deep learning algorithm that can increase the accuracy of a radiologist’s interpretation by 50-70% and at a speed 50,000 times faster.

Imagen Technologies

AI that is capable of detecting pathologies and early disease identification within medical images.

Bay Labs

Deep learning to ultrasounds and alleviate the leading cause of death – Cardiovascular disease

DiA Analysis

DiA’s flagship product LVIVO is an FDA/CE cleared, fully automated, and objective cardiac toolbox that helps physicians and echocardiologists analyze accurate and instant Echocardiogram scans

Lunit

Automated Detection and Classification of Breast Cancer Nodal Metastases

 RSNA

Medical Imaging AI Companies

Conclusion

We got the opportunity to see and understand the latest developments in RIS and PACS systems. We interacted with C-suite of the AI imaging startup companies and requested them to give their AI models on trial basis to integrate into our RIS application.

FacebookTwitterGoogle+Share
About Ciby Baby Punnamparambil

Ciby is a Solution Architect at Vmoksha with over 12 years of experience in the IT industry. He has in-depth knowledge and industry experience in delivering IoT embedded and Mobility solutions.



Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>