Greg Freiherr, Industry Consultant

Greg Freiherr has reported on developments in radiology since 1983. He runs the consulting service, The Freiherr Group.

Blog | Greg Freiherr, Industry Consultant | Artificial Intelligence | February 08, 2019

Hear and Now: AI and Imaging, Your Data as Strategic Asset

artificial intelligence

Patient data is critically important to the continued development of artificial intelligence (AI). And the institutions that have this data should recognize it as a strategic asset, according Esteban Rubens, an IT infrastructure architect and executive at Pure Storage, a California company that develops flash data storage hardware and software. 

Rubens is scheduled to speak about AI and imaging at the annual meeting of the Healthcare Information and Management Systems Society (HIMSS) in Orlando.  He plans to explain why patient data is a strategic asset.

In the podcast, he said the prime message of this talk will be to “realize how valuable your data is … that you have to protect it … and that you have to use it.”

 

Why Providers Need To Value Their Data

The patient data at institutions uniquely reflects the patient population of the institution, Rubens said: “The population that you serve is yours. No one else has that same population.”

He noted that patient data accumulated over decades is particularly valuable. “If you are not using it now, somebody else — at some point — will,” he said.  “We are not talking about some crass notion of monetizing your data. We are talking about algorithms that will directly impact your patient care.”

Rubens acknowledged in the ITN podcast that there has been “a lot of hype” around medical AI. But he stated that the hype is giving way to real progress. “We are way past the pure hype stage, because we have real things happening,” he said. “We are starting to see a lot of actual applications down to the clinical practice level of AI.”

Rubens describes himself as a “flash storage evangelist,” explaining that flash storage is a critical element to the infrastructure needed for medical AI to succeed: “Flash storage is the perfect complement” to the graphic processing units (GPUs) that drive AI applications. Flash storage “is massively parallel … has low latency and allows you to process huge amounts of data very, very quickly.” Its use, he said, “is the only way that you can be efficient in your AI work.”

 

Infrastructure: A Weak Link in Medical AI

Calling infrastructure “fundamental” to continued progress, Rubens explained in the podcast that without the proper infrastructure, latency could result — and that would be very bad for AI applications in medicine.

“People are already overworked and there are all sorts of issues with burnout. You can’t say that (an AI app) is really cool, but it is going to make things slower. The only way to ensure that adding more layers of technology won’t slow things down is to have the right infrastructure.”

Speed is extremely important —  and configuring data centers properly is a key to it, he said. Putting all the data in a single place, such as a data center or data hub, will overcome what has been the Achilles heel of Medicine — data silos. This has been so not only because of the disparate locations where data is stored but because of the financial and logistical issues that surround doing so, for example, the need to maintain, upgrade and replace multiple sites and their data storage equipment.

“If you have a data hub, all the data lives in the same place as it really should,” he said. “All those logistical and financial issues get smoothed over because everything is in the same place.”

Just as configuring infrastructure efficiently will support the expansion of AI, so might the widening adoption of AI help in the evolution of medicine.

“There’s been a lot of really, really good work being done (in AI),” he said.  “It is really about improving the lives of patients and physicians and other actors in healthcare.”

 

Greg Freiherr is a contributing editor for Imaging Technology News (ITN). Over the past three decades, Freiherr has served as business and technology editor for publications in medical imaging, as well as consulted for vendors, professional organizations, academia and financial institutions.

 

Editor's note: In preparation for the upcoming HIMSS (Healthcare Information and Management Systems Society) Conference on Feb. 11, contributing editor Greg Freiherr begins the show coverage with this exclusive podcast and accompanying blog. This is the second podcast in a series of three. You can listen to the first podcast, Hear and Now: How to Boost Cybersecurity in Medical Imaginghere.

 

Related content:

ITN’s Artificial Intelligence channel 

Technology Report: Artificial Intelligence

Increasing Presence of AI at RSNA Reflects Emphasis on Efficiency 

Related Content

Generated heatmaps appropriately highlighted abnormalities in the lung fields in those images accurately labeled as COVID-19 positive (A-C) in contrast to images which were accurately labeled as negative for COVID-19 (D). Intensity of colors on the heatmap correspond to features of the image that are important for prediction of COVID-19 positivity. Image courtesy of Northwestern University

Generated heatmaps appropriately highlighted abnormalities in the lung fields in those images accurately labeled as COVID-19 positive (A-C) in contrast to images which were accurately labeled as negative for COVID-19 (D). Intensity of colors on the heatmap correspond to features of the image that are important for prediction of COVID-19 positivity. Image courtesy of Northwestern University

News | Artificial Intelligence | December 03, 2020
December 3, 2020 — Northwestern University researchers ha
eRAD announced at RSNA 2020 that Abercrombie Radiology in Knoxville has deployed eRAD’s Patient Portal, Mammography Tracking module, communications platform (called RADAR), and Radiology Information System (RIS).

Getty Images

News | Information Technology | December 03, 2020
December 3, 2020 — eRAD announced at RSNA 2020 that...
An example of a body composition analysis of an abdominal CT slice with the subcutaneous fat in green, skeletal muscle red and visceral fat in yellow. This was automatically identified and analyzed via a deep learning algorithm to assess the risk for heart attack and stroke in more than 12,000 patients. #RSNA2020 #RSNA20 #RSNA

An example of a body composition analysis of an abdominal CT slice with the subcutaneous fat in green, skeletal muscle red and visceral fat in yellow. This was automatically identified and analyzed via a deep learning algorithm to assess the risk for heart attack and stroke in more than 12,000 patients.

Feature | Artificial Intelligence | December 02, 2020
December 2, 2020 – Automated deep learning analysis of abdominal...
 Riverain Technologies will showcase its artificial intelligence solutions and enhancements at the now-virtual 2020 Radiological Society of North America Annual Meeting (RSNA).
News | Artificial Intelligence | December 02, 2020
December 2, 2020 — Riverain Technologies will showcase its...
 Philips highlighted its expanding enterprise imaging informatics portfolio that is enabling healthcare providers to advance digital health transformation at RSNA 2020.
News | Enterprise Imaging | December 02, 2020
December 2, 2020 — Philips highlighted its expanding...
Studies show new deep-learning algorithm helps radiologists detect breast cancers in their early stages when used with the Genius 3D Mammography exam
News | Breast Imaging | December 02, 2020
December 2, 2020 — Hologic, Inc., an innovative medical technology company primarily focused on improving women’s hea
Glassbeam Clinsights can help imaging departments capture service data to enhance operational efficiencies
News | Artificial Intelligence | December 02, 2020
December 2, 2020 — Hospitals and institutions face a significant challenge each year when it comes to the financial i
Lunit’s algorithm showed the best performance compared to other commercialized AI algorithms, ultimately reducing the workload of radiologists to classify mammography screenings
News | Artificial Intelligence | December 02, 2020
December 2, 2020 — Recent studies have shown that Lunit’s AI solution is as accurate as average radiologists when it
Medical imaging artificial intelligence (AI) vendor Avicenna.AI today announced its FDA-cleared CINA Head triage AI solution will be offered by cloud-based imaging platform Arterys. Supporting the treatment of stroke and neurovascular emergencies, CINA Head detects intracranial hemorrhages (ICHs) and large vessel occlusions (LVOs) from CT-scan imaging. #RSNA20 #RSNA2020

Medical imaging artificial intelligence (AI) vendor Avicenna.AI announced its FDA-cleared CINA Head triage AI solution will be offered by cloud-based imaging platform Arterys. Supporting the treatment of stroke and neurovascular emergencies, CINA Head detects intracranial hemorrhages (ICHs) and large vessel occlusions (LVOs) from CT-scan imaging.
 

News | Stroke | December 01, 2020
December 1, 2020 – Medical imaging ...