Imaging executive Kyle Gibson on a new UN report predicting cancer rates. 

Imaging Wire Sponsors

Bayer  •  Blackford  •  CARPL.ai  •  Change Healthcare  •  Clearpath  •  Enlitic  •  GE HealthCare  •  Gleamer  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  PocketHealth  •  Riverain Technologies  •  Siemens Healthineers  •  SpinTech MRI  •  TeraRecon  •  United Imaging  •  Us2.ai  •  Visage Imaging

Artificial Intelligence

Real-World AI Experiences

Clinical studies showing that AI helps radiologists interpret medical images are great, but how well does AI work in the real world – and what do radiologists think about it? These questions are addressed in a new study in Applied Ergonomics that takes a deep dive into the real-world implementation of a commercially available AI algorithm at a German hospital. 

A slew of clinical studies supporting AI were published in 2023, from the MASAI study on AI for breast screening to smaller studies on applications like opportunistic screening or predicting who should get lung cancer screening. 

• But even an AI algorithm with the best clinical evidence behind it could fall flat if it’s difficult to use and doesn’t integrate well with existing radiology workflow.

To gain insight into this issue, the new study tracked University Hospital Bonn’s implementation of Quantib’s Prostate software for interpreting and documenting prostate MRI scans (Quantib was acquired by RadNet in January 2022). 

• Researchers described the solution as providing partial automation of prostate MRI workflow, such as helping segment the prostate, generating heat maps of areas of interest, and automatically producing patient reports based on lesions it identifies. 

Prostate was installed at the hospital in the spring of 2022, with nine radiology residents and three attending physicians interviewed before and after implementation, finding…

• All but one radiologist had a positive attitude toward AI before implementation and one was undecided 
• After implementation, seven said their attitudes were unchanged, one was disappointed, and one saw their opinion shift positively
• Use of the AI was inconsistent, with radiologists adopting different workflows and some using it all the time with others only using it occasionally
• Major concerns cited included workflow delays due to AI use, additional steps required such as sending images to a server, and unstable performance

The findings prompted the researchers to conclude that AI is likely to be implemented and used in the real world differently than in clinical trials. Radiologists should be included in AI algorithm development to provide insights into workflow where the tools will be used.

The Takeaway

The new study is unique in that – rather than focusing on AI algorithm performance – it concentrated on the experiences of radiologists using the software and how they changed following implementation. Such studies can be illuminating as AI developers seek broader clinical use of their tools. 

Automated Solutions for Patient and Provider Sharing

What’s the latest news from Clearpath? Find out how its fully automated patient and provider solutions for sharing medical records and images are making waves in healthcare.

Deciding Between Public and Private Cloud?

Trying to decide between public and private cloud? Watch this brief Change Healthcare animation detailing the operational benefits of public cloud hosting for imaging.

The Wire

• Global Cancer Spike: A new UN report is predicting a spike in global cancer cases, forecasting a 77% rise in cancer incidence by 2050, from 20M cases in 2022 to 35M. Some 9.7M people died from cancer worldwide in 2022, with tobacco, alcohol, and obesity contributing to rising incidence. Lung cancer was the most common (2.5M cases) as well as the deadliest (1.8M deaths), followed by colorectal (900k deaths), liver (760k deaths), and breast (670k deaths). Major disparities persist between high- and low-income countries. 

• Cancer Screenings Still Lag: A new study in JAMA Health Forum found that the decline in cancer screenings seen during the COVID-19 pandemic failed to bounce back in the two years afterward. Researchers analyzed screening rates for 89k people in 2021 and 2022, finding that the adjusted rate ratio for getting breast cancer screening was lower compared to 2019 (ARR=0.93), but the decline wasn’t as bad as for other screening tests like colorectal (0.88), cervical (0.86), and prostate (0.86). The declines also varied by race.

• Apple’s VR Play: Apple last week launched its long-awaited Apple Vision Pro headset, which supports image viewing in an augmented reality/virtual reality environment that Apple has dubbed spatial computing. With a list price of $3,499 the headsets are pricey for consumer use, but radiologists are eager to see how the technology could advance AR/VR in the clinical realm, where researchers have been experimenting with applications such as overlaying medical images on actual patients to assist with image-guided interventional procedures.

• Visage Goes Virtual with Apple VR: Hot on Apple’s launch, Visage Imaging debuted its Visage Ease VP application. The software supports immersive spatial experiences in Apple Vision Pro for medical imaging and multimedia. It includes the functionality of Visage’s Visage Ease solution while adding cinematic rendering in immersive space with virtual screens at more than 4k resolution per eye. Visage Ease VP also enables users to seamlessly interact with images in their physical space. UC San Diego is the first health system using Visage Ease VP.

• Radiologists and Follow-Up Imaging: A new study in AJR has found major variations in the rates at which radiologists order follow-up imaging studies of the head and neck. In a review of 32k patients who got CT and MRI scans from June 2021 to May 2022, researchers found that there was a 28-fold difference in ordering rates between the 61 radiologists in the study (0.8% to 22%). Radiologist behavior was believed to be the biggest factor behind the variation, indicating the need for quality improvement initiatives. 

• CARPL Raises $6M: AI platform developer CARPL.ai has raised $6M in a funding round led by Stellaris Venture Partners that included participation from a host of marquee names in the healthcare and investing worlds, including Bain & Co., Leapfrog PE, and United HealthGroup. An article on the company in TechCrunch notes that CARPL has onboarded more than 50 AI developers with 100 apps. CARPL plans to use the funds to build its tech stack and hire in North America.

• Photon-Counting CT at X-Ray Doses: Researchers using Siemens Healthineers’ Naeotom Alpha photon-counting CT scanner achieved radiation doses comparable to chest X-rays when scanning patients for suspicion of pneumonia. Researchers writing in Karger described their pilot study of 27 patients using an ultra-low-dose photon-counting CT protocol that produced a dose of 0.11 mSv. But how good were the images? The protocol changed patient diagnosis in 41% of cases. The study shows photon-counting CT could replace X-ray for some chest applications without exposing patients to more radiation dose.

• Enlitic Adds Rankin to C-Suite: Enlitic has hired medical imaging veteran Steve Rankin as chief strategy officer. Rankin has over 25 years of experience in the radiology IT industry, most recently as chief product officer at Mach7 Technologies; prior to that he was co-founder, president, and CEO of Client Outlook, which developed the eUnity universal viewer and was acquired by Mach7 in 2020. Rankin also served stints at Medicalis and Agfa HealthCare/Mitra Imaging.

• POCUS at the ‘Roof of the World’: Point-of-care ultrasound may have helped sharply reduce maternal mortality in Nepal thanks to a program started in 2006 that has been training midwives and nurses to use Philips Lumify POCUS scanners to identify high-risk pregnancies in rural areas and refer women to specialist hospitals in cities. In an article in JACR, researchers describe how Nepal saw its maternal mortality rate per 100k live births fall dramatically in 2016 compared to 1996 (239 vs. 539), and farther to 174 in 2020. 

• German Firm Launches Prostate AI: German radiology AI developer FUSE-AI has made the European launch of its Prostate.Carcinoma.ai algorithm after receiving EU MDR certification. The software automatically segments the prostate in MRI scans and identifies pathological changes; FUSE-AI touts a 30% time savings per patient. The company demonstrated the application at last week’s Arab Health meeting in Dubai. 

• No Surprises Act Delivers Surprises: A payor survey from AHIP and the BCBS Association estimates that the No Surprises Act blocked more than 10M unexpected medical charges through the first nine months of 2023. Although that pace is a surprise in and of itself, the survey also called out the “growing and troubling trend” of claims going through the independent dispute resolution process established by the No Surprises Act. Regulators estimated we’d see about 17k IDR cases annually, yet almost 670k cases were submitted to IDR between January and September of last year.

Treating Local Patients Like Family

Holzer Health System in the rural community of Jackson, Ohio, treats local patients like family, offering the same level of top-quality care that can be found anywhere. Find out how United Imaging’s Software Upgrades for Life program helps them stay current.

Focus on Actionable Data for Lung Abnormalities

The volume and complexity of imaging interpretation are exploding. Find out how ClearRead CT with Clear Visual Intelligence from Riverain Technologies can help you focus on actionable data for lung abnormalities in this article.

Unlocking the Potential of Radiology AI

How is AI revolutionizing radiology to enhance patient outcomes and streamline workflow? Find out in this video discussion between CARPL.ai CEO Vidur Mahajan and Mitchell Goldburgh of NTT Data USA.

The Resource Wire

• Leveraging a Proven Echo AI Platform: Us2.ai has developed a promising new pathway for bringing custom echo AI applications into widespread clinical and commercial use – historically a challenge for algorithms produced by health systems and academic institutions. Find out how it worked in Uganda in this article.

• Solutions to Support Breast Density Reporting: The FDA has ruled that healthcare providers must inform patients of their breast density status. Learn how Intelerad’s solutions can help mammography facilities comply with this new rule well ahead of next year’s deadline. 

• To Pay or Not to Pay for AI in Radiology: AI-supported digital applications are expected to transform radiology, but providers need motivation and incentives to adopt them. In this article, authors including executives from Bayer propose a framework to guide payers and AI developers in adoption of radiology AI. 

• Start at the Source to Improve MRI: Looking for ways to improve MRI speed and image quality while addressing broader concerns in healthcare? The answer may lie in proven MRI physics in your existing scanner – learn how to unlock it with STAGE from SpinTech MRI. 

• Seamless Integration and Efficient Reading: TeraRecon’s latest Intuition advanced visualization solution now features seamless integration with Mirada Medical’s Mirada XD, providing efficient diagnostic reading with automatic multi-modality and multi-time point registration capabilities. Schedule a demo to learn more. 

• Optimizing Lung Cancer Detection with the Power of AI: Progress has been made to expand CT lung cancer screening guidelines and capture more lung cancers early. But less than 6% of eligible individuals undergo recommended screenings. Learn what GE HealthCare is doing to leverage CT and AI to make a difference. 

• Revolutionizing Chest X-Ray Reporting: A new study in Radiology shows how Gleamer’s ChestView AI solution is revolutionizing chest X-ray reporting by helping radiologists detect lung abnormalities with greater accuracy while also reducing interpretation times. 

• Monitoring AI Solutions in Healthcare: Clinical applications for healthcare AI are rapidly expanding, but many barriers are still preventing widespread adoption. This Nuance post explores a critical set of questions: what happens after an AI model goes into production, and how to know if it continues to perform as expected?

• Joining Forces on Medical Imaging Data Standardization: Being a leader in healthcare and having to make decisions on technology purchases can be tough. Learn how Enlitic partner Blackford Analysis has made it easy, with many AI solutions all in one platform. 

• The Benefits of Breast Imaging AI: Breast imaging AI can help providers reduce their workload and improve patient care. Blackford Analysis offers a wide selection of breast imaging AI apps on its Blackford Platform – find out how they could benefit your organization. 

• Enhancing Patient Engagement through Effective Communication: A new downloadable guide from PocketHealth shows how you can create positive patient experiences, eliminate patient anxiety, and increase appointment and follow-up adherence.

• Leading the Way in Rural MR Imaging: Rural patients can experience transportation barriers for their medical needs, including medical imaging. In this February 21 webinar from Siemens Healthineers, find out how Weiser Memorial Hospital, a critical access hospital in rural Idaho, solved this challenge.

• The Path to Modernization in Enterprise Imaging:  Meet your challenges with innovation as you blaze a path to modernization with Merge by Merative’s Merge Imaging Suite, an array of solutions designed to enable imaging clinicians to enjoy a seamless and frictionless workflow experience.

• What You Need to Know about the 2024 MPFS Final Rule: CMS updates the Medicare Physician Fee Schedule (MPFS) annually, and 2024 is no different. Join Barbara Rubel of MSN Healthcare Solutions as she reviews the key provisions that will impact radiology in this February 13 webinar hosted by Medality. 

• Top 5 Trends from RSNA 2023: What were the top 5 trends from RSNA 2023? Check out this review from Brad Levin of Visage Imaging on the topics and technologies that took center stage in Chicago.