Halim Abbas of the Mayo Clinic, in a talk on Mayo Clinic Platform at AIMed Global Summit.

Imaging Wire Sponsors

Annalise.ai  •  Arterys  •  Bayer  •  Blackford  •  CARPL.ai  •  Change Healthcare  •  Enlitic  •  GE HealthCare  •  Hyperfine  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  Riverain Technologies  •  Siemens Healthineers  •  Subtle Medical  •  United Imaging  •  Us2.ai  •  Visage Imaging

Artificial Intelligence

Mayo’s AI Model

SAN DIEGO – What’s behind the slow clinical adoption of artificial intelligence? That question permeated the discussion at this week’s AIMed Global Summit, an up-and-coming conference dedicated to AI in healthcare.

Running June 4-7, this week’s meeting saw hundreds of healthcare professionals gather in San Diego. Radiology figured prominently as the medical specialty with a lion’s share of the over 500 FDA-cleared AI algorithms available for clinical use.

But being available for use and actually being used are two different things. A common refrain at AIMed 2023 was slow clinical uptake of AI, a problem widely attributed to difficulties in deploying and implementing the technology. One speaker noted that less than 5% of practices are using AI today.

One way to spur AI adoption is the platform approach, in which AI apps are vetted by a single entity for inclusion in a marketplace from which clinicians can pick and choose what they want. 

The platform approach is gaining steam in radiology, but Mayo Clinic is rolling the platform concept out across its entire healthcare enterprise. First launched in 2019, Mayo Clinic Platform aims to help clinicians enjoy the benefits of AI without the implementation headache, according to Halim Abbas, senior director of AI at Mayo, who discussed Mayo’s progress on the platform at AIMed. 

The Mayo Clinic Platform has several main features:

• Each medical specialty maintains its own internal AI R&D team with access to its own AI applications 
• At the same time, Mayo operates a centralized AI operation that provides tools and services accessible across departments, such as data de-identification and harmonization, augmented data curation, and validation benchmarks
• Clinical data is made available outside the -ologies, but the data is anonymized and secured, an approach Mayo calls “data behind glass”

Mayo Clinic Platform gives different -ologies some ownership of AI, but centralizes key functions and services to improve AI efficiency and smooth implementation. 

The Takeaway 

Mayo Clinic Platform offers an intriguing model for AI deployment. By removing AI’s implementation pain points, Mayo hopes to ramp up clinical utilization, and Mayo has the organizational heft and technical expertise to make it work (see below for news on Mayo’s new generative AI deal with Google Cloud). 

But can Mayo’s AI model be duplicated at smaller health systems and community providers that don’t have its IT resources? Maybe we’ll find out at AIMed 2024.

AI-Powered Protection for PHI

Medical images contain some of the most sensitive protected health information (PHI), so it’s essential to keep PHI secure. Learn how to use AI-powered software to protect PHI in this white paper from Enlitic.

Understanding the Platform Approach to AI

Here’s a quick introduction to Blackford Analysis’ dedicated AI platform and its service for the selection, deployment, orchestration, and use of imaging applications and AI.

The Wire

• Mayo AI Deal with Google Cloud: In other AI news from Mayo Clinic, the system signed an agreement with Google Cloud to make it easier for clinicians to use generative AI to find information spread across a healthcare enterprise. Mayo will use Google Cloud tools like its Enterprise Search on Generative AI App Builder to help clinicians find and access data that’s hard to locate otherwise, including medical histories, genomic information, and imaging and lab results.

• Mammography AI Predicts Cancer Risk: Mammography AI algorithms did a better job than the traditional Breast Cancer Surveillance Consortium model for predicting risk of breast cancer that might develop later in women with negative original screening mammograms. In a population of over 18k women studied in Radiology, any one of 5 different AI models predicted cancer risk over 5 years more accurately than the BCSC model (AUC range: 0.63-0.67 vs. 0.61).   

• Densitas Deal with ScreenPoint: Mammography software developers Densitas and ScreenPoint Medical have signed a deal to offer their AI technologies together to improve breast cancer detection. Densitas will contribute its intelliMammo quality platform, while ScreenPoint will offer its Transpara deep-learning algorithm for mammogram analysis. The AI offerings will work together to help improve breast cancer detection and reduce recalls and false-positive biopsies. ScreenPoint is also working with another density software developer, Volpara Health.

• Massive Review Supports Cardiac MRI: Results from stress cardiac MRI are highly predictive of future adverse events – particularly when 3-tesla scanners are used. That’s according to an article in JAMA Cardiology based on a massive review of 64 studies covering nearly 75k people over 20 years. Researchers found that inducible myocardial ischemia and late gadolinium enhancement were telltale signs of future major adverse cardiac events and mortality, and had a diagnostic odds ratio of 26.4 for detecting obstructive CAD.

• New GE MRI Recon Software: At this week’s ISMRM 2023 show, GE HealthCare launched Sonic DL, a new deep learning-based application for reconstructing MR images, with a particular focus on cardiac MRI. Sonic DL acquires high-quality MRI studies up to 12X faster than conventional methods, enabling cardiac imaging within a single heartbeat, and is well-suited for patients with arrhythmias and breath-holding challenges. Sonic DL attacks the challenges holding back MRI as a cardiac imaging modality, in particular scan acquisition time. 

• Muscle Fat Predicts Cognitive Decline: CT-based measurements of fat between skeletal muscle tissue can predict cognitive decline in women, says a new study in Journal of the American Geriatrics Society. Researchers acquired CT scans in 1,634 women from 1997 to 2011 and used software to measure intermuscular adipose tissue, or fat developing between muscles. Increases in this tissue corresponded to worse scores on mental ability exams over 10 years. The results suggest a role for opportunistic screening of dementia in women getting CT scans for other reasons.

• NY Times Spotlights 3D CT: A recent article in the New York Times on COVID-19’s impact on the lungs featured stunning 3D CT reconstructions. The story profiled three patients who contracted COVID-19 in the early days of the pandemic, showing their 3D CT scans indicating lung damage caused by the virus. The article used a cinematic rendering technique from Siemens Healthineers’ syngo.via workstation, with the assistance of radiologists Elliot Fishman, MD, and William Moore, MD.

• Riverain’s ClearRead CT VA Install: Riverain Technologies has installed its ClearRead CT software with Clear Visual Intelligence for chest imaging at the Pittsburgh VA Medical Center. The Pittsburgh VA and the H. John Heinz III Department of Veterans Affairs Medical Center are using ClearRead CT on chest-related cases; the software removes interfering normal structures on chest CT like vessels and machine noise to provide clearer images and detect lung nodules. Riverain has a relationship with the VA to provide ClearRead throughout the VA’s healthcare system.

• Patients Have Scanxiety: Some 51% of patients have “scanxiety” while waiting for results of their medical imaging scans, and 62% said they feel more informed about their online shopping deliveries than their imaging results. That’s according to an online survey conducted by PocketHealth of Canadian patients and their attitudes toward medical information access. What’s more, only 18% of respondents said they accessed their medical reports online, and 72% said they should have access to imaging results at the same time as their doctor.

• Healthcare’s Scariest Disruptors: What disruptive medical trends keep healthcare leaders up at night? A new article in Becker’s ASC Review based on interviews with 6 leaders touches on this, finding that AI is widely seen as one of the most disruptive technologies in healthcare. While AI will improve medicine in many ways, its rollout will require oversight to prevent unintended consequences. Other than AI, physician burnout, a wave of doctor retirements, and staffing shortages were also topics of concern. 

• Sonio Helps ID Anomalies: The Sonio Expert software from French decision support developer Sonio helped guide clinicians through fetal ultrasound exams for identifying rare diseases. In an article in Ultrasound in Obstetrics & Gynecology, Sonio Expert was used in 549 cases in which a fetal anomaly was detected; in 93% of positive cases, the diagnosis was in the software’s top 10 list. Sonio has been successful in raising funds over the past year, including a €10M round in December and a €5M round in July.

• BrightHeart’s Fetal Heart AI: Paris-based ultrasound AI startup BrightHeart launched to help clinicians catch the 70% of congenital fetal heart defects that go undetected. BrightHeart will use €2M in seed financing and a database of over 20k fetal ultrasound exams to further develop its AI technology, which helps clinicians detect complex fetal heart defects during screening exams. BrightHeart will also use the funds to prepare its regulatory submissions and facilitate the company’s expansion.

Optimize CT Workflow: From Scan to Recon

Learn how to optimize your CT workflow from scan to reconstruction in this webinar recording. Find out how NYU Langone Health leverages technologies from Siemens Healthineers to streamline their workflow and improve patient care. 

Enabling Remote Work for Radiologists

What tools are available to help radiologists work remotely? In this case study, teleradiology provider 4ways Healthcare of the UK describes how they used Merative’s Merge PACS 8.0 platform to improve their service to clients while supporting remote radiologists.

The Resource Wire

• Why should your health system/imaging organization be considering cloud-based PACS? Find out from real-world, live customers in this video why Visage Imaging’s Visage 7 CloudPACS offers major benefits over the limitations of legacy PACS.

• What’s the best way to eliminate patient frustration and get them engaged with healthcare again? Find out how technology can revamp the patient engagement experience in this article produced in collaboration with Nuance in Becker’s Hospital Review.

• What’s the latest news from United Imaging Healthcare? Driven by a focus on R&D, United has increased its brand influence and market share worldwide. Get the details in the company’s first annual report since going public. 

• Strain imaging is the most sensitive parameter for determining myocardial deformation and systolic left ventricular function. In this video, see how echo AI from Us2.ai was used to analyze myocardial global longitudinal strain. 

• Creating your AI adoption plan? This Arterys report details what clinical, efficiency, and regulatory factors to look for in radiology AI vendors.

• When the VA adopts your technology nationwide, you know you’ve been making an impact. That’s exactly what’s happening with Riverain Technologies’ ClearRead CT, which will be implemented across the VA Lung Precision Oncology Program (22 hub and 87 spoke locations).

• In today’s hyper-competitive radiologist job market, radiologist recruiting and retention is more important than ever. Learn from industry experts and practice leaders in this on-demand Medality webinar as they reveal how to overcome hiring challenges, keep your team engaged, and provide opportunities for growth.

• See how Thomas Jefferson University relied on CARPL.ai to accelerate its AI validation and clinical adoption in this presentation by informatics and AI leader, Dr. Paras Lakhani.

• There’s a lot to learn from St. Michael’s Hospital’s experience implementing the Hyperfine Swoop portable MRI at the point-of-care. See what their hospital leaders had to say about how the ultra-low-field MRI technology impacted their patients and clinicians in this on-demand webinar.

• Annalise.ai’s Annalise CXR solution detects up to 124 findings in a single chest X-ray. See how it detects such a wide range of abnormalities using these demo studies…  or upload your own CXR images.

• If you’re at SIIM 2023, be sure to attend the InformaticsTECH Talk on Wednesday, June 14 on the Power of the Platform for Imaging AI, by Aaron Sullivan, Head of Business Development for Bayer Digital Solutions. 

• Meet two patients, each thriving and enjoying life. They’ve been managing advanced-stage prostate cancer … for years. Their stories show how clinicians are using GE HealthCare technology to treat and deliver precision medicine with Theranostics today. 

• Is your department struggling with how to convert analog clinical documentation notes into actionable data that can be used in the EHR? Find out how Duke University turned that legacy information into structured data that can be used for registry reporting and analytics in this Intelerad Medical Systems white paper. 

• Want to perform PET scans faster, but keep the same image quality? With SubtlePET image enhancement from Subtle Medical, you can conduct PET exams in one-quarter of the original time while preserving image quality. Find out how in this case review. 

• Change Healthcare’s cloud-native, zero-footprint Stratus Imaging PACS is live in clinical use. See how Stratus Imaging PACS is helping radiology practices improve productivity and patient care, while eliminating the cost and resource constraints of on-premise systems.