Tag: artificial intelligence

RP Builds AI Mosaic as Company’s IT Foundation

Posted on by Brian Casey

Radiology Partners announced a new initiative to guide the rollout of AI across its nationwide network of radiology practices. The company’s new MosaicOS will be the IT foundation that connects RP practices and supports clinical uses from AI-assisted reporting to report generation and even image management.

Radiology Partners has grown since its founding in 2012 to become the largest privately held provider of imaging services in the U.S. and a major force behind the consolidation of private-practice radiology groups.

  • RP has always maintained a heavy technology investment, and has been looking closely at the rise of AI in radiology.

That’s because the growth in imaging volume is so massive that clinicians will no longer be able to care for patients adequately without AI’s assistance, at least according to RP’s Associate Chief Medical Officer for Clinical AI Nina Kottler, MD.

RP laid the groundwork for MosaicOS in 2020 by first migrating its technology stack to a cloud-native infrastructure. 

  • This frees RP from reliance on on-premises legacy software and enables the company to push out updates that can be adopted quickly across its network.

RP’s Mosaic rollout includes the following components as the company…

  • Forms a new division, Mosaic Clinical Technologies, to oversee its AI activities.
  • Debuts MosaicOS, a cloud-native operating system that combines AI support with workflow and other IT tools.
  • Launches Mosaic Reporting, an automated structured reporting solution that combines ambient voice AI with large language model technology.
  • Develops Mosaic Drafting, a multimodal AI foundation model that pre-drafts X-ray reports that radiologists can review, edit, and sign. 

Mosaic Reporting is already in use at some RP sites, and the company is pursuing FDA clearance for broader use of Mosaic Drafting. More Mosaic applications are on the way.

  • Mosaic tools will be disseminated to RP centers using the cloud-native infrastructure, and MosaicOS will include image management functions that providers can choose to use in place of or alongside existing tools like viewers and archives. 

Kottler told The Imaging Wire that RP has de-emphasized individual pixel-based AI models in favor of foundation models that have broader application.

  • What’s more, RP CEO Rich Whitney said the company has chosen to develop AI technology internally rather than rely on outside vendors, as this gives it greater control over its own AI adoption.

The Takeaway

The launch of MosaicOS marks an exciting milestone not only for Radiology Partners but also for radiology in general that could address nagging concerns about clinical AI adoption on a broad scale. RP has not only the network but also the technology resources to make the rollout a success – the question is whether outside AI developers will share in the rewards.

Radiology AI Approvals Near 1k in New FDA Update

Posted on by Brian Casey

The FDA last week released the long-awaited update to its list of AI-enabled medical devices that have received marketing authorization. The closely watched list shows the number of AI-enabled radiology authorizations approaching the 1k mark.

The FDA has been tracking authorizations of AI-enabled devices going back to 1995, and the list gives industry watchers a feel for not only how quickly the agency is churning out reviews but also which medical specialties are generating the most approvals.

  • But the last time the FDA released an updated list was August 2024, and recent turmoil at the agency had some observers wondering if it would continue the tradition – as well as whether it could stay on pace for new approvals.

Those fears should be assuaged with the new release. The numbers indicate that through May 2025 the FDA has…

  • Granted authorization to 1.2k AI-enabled medical devices since it started tracking.
  • Approved 956 AI-enabled radiology products, or 77% of total medical authorizations.
  • Radiology’s share of overall authorizations from January to May 2025 ticked up to 78% (115/148), compared to 73% in the 2024 update, and 80% in all of 2023.
  • GE HealthCare remains the company with the most radiology AI authorizations, at 96 (including recent acquisitions like Caption Health and MIM Software), with Siemens Healthineers in second place at 80 (including Varian). 
  • Other notable mentions include Philips (42 including DiA Analysis), Canon (35), United Imaging (32), and Aidoc (30). 

In a significant regulatory development, the FDA said it was developing a plan to identify and tag medical devices that use foundation models, including large language models and multimodal architecture. 

  • The agency said the program would help healthcare providers and patients know when LLM-based functionality was included in a medical device (the FDA has yet to approve a medical device with LLM technology). 

In another interesting change, the FDA dropped “machine learning” from the title of its list, apparently with the idea that “AI” was sufficient as an umbrella term. 

The Takeaway

The FDA’s release of its AI approval list is a welcome return to past practices that should reassure agency watchers that recent turmoil isn’t affecting its basic operations. The LLM guidance suggests the agency may be changing its approach to the technology in favor of disclosure and transparency instead of more stringent regulation that could delay some LLM solutions from reaching the market.

AI and Legal Liability in Radiology

Posted on by Brian Casey

What impact will artificial intelligence have on the legal liability of the radiologists who use it? A new study in NEJM AI suggests that medical malpractice juries may pass harsher judgment on radiologists when they make mistakes that disagree with AI findings.

AI is viewed as a technology that can save radiologists time while also helping them make more accurate diagnoses.

  • But there’s a dark side to AI as well – what happens when AI findings aren’t correct, or when radiologists disagree with AI only to discover it was right all along?

In the new study, a research team led by Michael Bernstein, PhD, of Brown University queried 1.3k U.S. adults on their attitudes toward radiologists’ legal liability in two clinical use cases for AI – identifying brain bleeds and detecting lung cancers.

  • Participants were asked if they felt radiologists met their duty of care to patients across different scenarios, such as whether the AI and the radiologist agreed or disagreed on the original diagnosis. 

Responses were compared to a “no AI” control scenario in which respondents assessed legal liability if radiologists hadn’t used AI at all, with researchers finding …

  • If radiologists disagreed with AI, more respondents found radiologists liable …
    • Brain bleeds: 73% found radiologist liable (vs. 50% with no AI)
    • Lung cancer: 79% found radiologist liable (vs. 64% with no AI)
  • If both radiologists and AI missed the diagnosis, there was no statistically significant difference …
    • Brain bleeds: (50% vs. 56% with no AI, p=0.33)
    • Lung cancer: (64% vs. 65% with no AI, p=0.77)
  • Respondents were less likely to side with plaintiffs when given information about standard AI error rates …
    • When AI agreed with the radiologist diagnosis:
      • Brain bleeds: (73% plaintiff agreement fell to 49%)
      • Lung cancer: (79% fell to 73%)
    • When AI disagreed with the radiologist diagnosis:
      • Brain bleeds: (50% plaintiff agreement fell to 34%)
      • Lung cancer: (64% fell to 56%)

The Takeaway

The new study offers a fascinating look at AI’s future in radiology from a medico-legal perspective. But there’s one question the researchers didn’t address: If AI-supported image interpretation eventually becomes the standard of care, will radiologists be found liable for not using it at all? Stay tuned. 

All-Star AI for Prostate MRI

Posted on by Brian Casey

An AI model for prostate MRI that combines the best features of five separate algorithms helped radiologists diagnose clinically significant prostate cancer in a new study in JAMA Network Open. 

The Prostate Imaging-Cancer AI consortium was formed to address a nagging problem in prostate cancer screening.

  • Studies have shown that MRI can reduce biopsies and minimize workup of clinically insignificant disease, but it also has high inter-reader variability and requires a high level of expertise. 

The PI-CAI challenge brought together researchers from multiple countries with a single goal: develop an AI algorithm for prostate MRI that would improve radiologists’ performance.

  • Results were presented at RSNA and ECR conferences, as well as in a 2024 paper in Lancet Oncology that showed that individually the algorithms improved radiologist performance and generated fewer false positives.

But what if you combined the best of the PI-CAI algorithms into a single all-star AI model? 

  • Researchers did just that in the new study, combining the top five algorithms from the PI-CAI challenge into a single AI model in which each algorithm’s results were pooled to create an average detection map indicating the presence of prostate cancer. 

To test the new algorithm, 61 readers from 17 countries interpreted 360 prostate MRI scans with and without the model. 

  • Patients in the test cohort had a median age of 65 years and a median PSA level of 7.0 ng/mL; 34% were eventually diagnosed with clinically significant prostate cancer.

Results of PI-CAI-aided prostate MRI were as follows …

  • Radiologists using the algorithm had higher diagnostic performance than those who didn’t (AUROC=0.92 vs. 0.88).
  • PI-CAI working on its own had the highest performance (AUROC=0.95).
  • Sensitivity improved for cases rated as PI-RADS 3 or higher (97% vs. 94%).
  • Specificity also improved (50% vs. 48%).
  • AI assistance improved the performance of non-expert readers more than expert readers, with greater increases in sensitivity (3.7% vs. 1.5%) and specificity (4.3% vs. 2.8%).

The Takeaway

The new PI-CAI study is an important advance not only for prostate cancer diagnosis but also for the broader AI industry. It points to a future where multiple AI algorithms could be combined to tackle clinical challenges with better diagnostic performance than any model working alone.

Mammo Risk Prediction Improves with AI

Posted on by Brian Casey

Artificial intelligence is beginning to show that it can not only detect breast cancer on mammograms, but it can predict a patient’s future risk of cancer. A new study in JAMA Network Open showed that a U.S. university’s homegrown AI algorithm worked well in predicting breast cancer risk across diverse ethnic groups. 

Breast cancer screening traditionally has used a one-size-fits-all model based on age for determining who gets mammography.

  • But screening might be better tailored to a woman’s risk, which can be calculated from various clinical factors like breast density and family history.

At the same time, research into mammography AI has uncovered an interesting phenomenon – AI algorithms can predict whether a woman will develop breast cancer later in life even if her current mammograms are normal. 

The new study involves a risk prediction algorithm developed at Washington University School of Medicine in St. Louis that uses AI to analyze subtle differences and changes in mammograms over time, including texture, calcification, and breast asymmetry.

  • The algorithm then generates a mammogram risk score that can indicate the risk of developing a new tumor.

In clinical trials in British Columbia, the algorithm was used to analyze full-field digital mammograms of 206.9k women aged 40-74, with up to four years of prior mammograms available. Results were as follows …

  • The algorithm had an AUROC of 0.78 for predicting cancer over the next five years.
  • Performance was higher for women older than 50 compared to 40-50 (AUROC of 0.80 vs. 0.76).
  • Performance was consistent across women of different races.
  • 9% of women had a five-year risk higher than 3%. 

The algorithm’s inclusion of multiple mammography screening rounds is a major advantage over algorithms that use a single mammogram as it can capture changes in the breast over time. 

  • The model also showed consistent performance across ethnic groups, a problem that has befallen other risk prediction algorithms trained mostly on data from White women. 

The Takeaway

The new study advances the field of breast cancer risk prediction with a powerful new approach that supports the concept of more tailored screening. This could make mammography even more effective than the one-size-fits-all approach used for decades.

AI Boosts DBT in Detecting More Breast Cancer

Posted on by Brian Casey

A real-world study of AI for DBT screening found that AI-assisted mammogram interpretation nearly doubled the breast cancer detection rate. Radiologists using iCAD’s ProFound AI software saw sharp improvements across multiple metrics. 

Mammography screening has quickly become one of the most promising use cases for AI. 

  • Multiple large-scale studies published in 2024 and 2025 have documented improved radiologist performance when using AI for mammogram interpretation, with the largest studies performed in Europe.

Another new technology changing mammography screening is digital breast tomosynthesis, which is being rapidly adopted in the U.S. 

  • DBT use in Europe is occurring more slowly, so questions have arisen about whether AI’s benefits for 2D mammography would also be found with 3D systems.

To investigate this question, researchers writing in Clinical Breast Cancer tested radiologist performance for DBT screening before and after implementation of iCAD’s ProFound V2.1 AI algorithm in 2020 at Indiana University. 

  • Interestingly, the pre-AI period included use of iCAD’s older PowerLook CAD software. 

Across the 16.7k DBT cases studied, those with AI saw …

  • A sharp improvement in cancer detection rate per 1k exams (6.1 vs. 3.7).
  • A decline in the abnormal interpretation rate (6.5% vs. 8.2%).
  • Higher PPV1 (rate that abnormal mammograms would be positive) (8.8% vs. 4.2%).
  • Higher PPV3 (rate that biopsies would be positive) (57% vs. 32%). 
  • Higher specificity (94% vs. 92%).
  • No statistically significant change in sensitivity.

The findings on sensitivity are curious given AI’s positive impact on other interpretation metrics.

  • Researchers postulated that there was higher breast cancer incidence in the post-AI implementation period, which could have been caused by AI finding cancers that were missed in the period without AI.

The Takeaway

The radiology world has seen multiple positive studies on AI for mammography, but most of these have come from Europe and involved 2D mammography not DBT. The new results suggest that AI’s benefits will also transfer to DBT, the technology that’s becoming the standard of care for breast screening in the U.S.

Integrated Solutions for Managing Incidental CAC Findings

Posted on by Partner Content

The rising prominence of coronary artery calcium as a prognostic marker for heart disease has created an emerging challenge for radiologists: how should they manage incidental CAC findings discovered on routine CT exams? Fortunately, new industry collaborations are making it possible to deliver CAC reports to clinicians without disrupting workflow. 

Routine CT scans are revealing data beyond their original diagnostic intent.

  • AI solutions – such as AVIEW CAC from Coreline Soft – play a pivotal role in identifying risks for cardiovascular disease, osteoporosis, and metabolic disorders – all from a single scan.

AI allows one CT scan to assess lung, cardiovascular, and skeletal health, improving diagnosis and treatment planning.

One imaging services provider that has put AVIEW CAC into use is 3DR Labs, which has been actively integrating the solution into its nationwide clinical network.

  • The partnership enables 3DR Labs radiologists to generate consistent, high-quality CAC reports directly within PACS, while significantly reducing turnaround times.

3DR Labs is finding that AVIEW CAC optimizes workflow efficiency and significantly reduces the time required for CAC assessment. 

  • It also ensures that radiologic technologists can perform quick QA checks, enhancing consistency and reliability in the delivery of the report.

The latest generation of the FDA-cleared AVIEW CAC features an upgraded user interface and advanced batch-scoring functionality. 

  • 3DR Labs is now working to expand AI-driven insights into lung and neuroimaging through Coreline’s broader AVIEW platform (AVIEW ILA for interstitial lung abnormalities and AVIEW BAS for brain CT).

Beyond diagnostic imaging, this collaboration supports growing demands for cost-efficiency in healthcare. 

  • As U.S. insurers and government agencies recognize the ROI potential of early AI detection, platforms like AVIEW CAC offer scalable, high-performance solutions that lower costs and streamline care delivery.

3DR Labs has also highlighted Coreline Soft’s role as a founding partner in AI Labs, the company’s vendor-neutral platform to deliver the latest AI innovations to radiology workflows.

The Takeaway

New partnerships like the collaboration between Coreline Soft and 3DR Labs are advancing the future of AI in radiology – focusing on automation, early detection, and better patient outcomes through powerful, clinically validated technologies. Such partnerships not only reflect increasing adoption of AI in U.S. healthcare but set the stage for global transformation in diagnostic imaging.

Getting Paid for AI – Will It Get Easier?

Posted on by Brian Casey

Reimbursement is one of the major stumbling blocks holding back wider clinical adoption of artificial intelligence. But new legislation was introduced into the U.S. Congress last week that could ease AI’s reimbursement path. 

For AI developers, getting an algorithm approved is just the first step toward commercial acceptance. 

  • Perhaps even more important than FDA clearance is Medicare reimbursement, as healthcare providers are reluctant to use a product they won’t get paid for. 

Reimbursement drives clinical AI adoption, as evidenced by a 2023 analysis listing the top algorithms by CPT claims submitted (Heartflow Analysis topped the list). 

  • But CMS uses a patchwork system governing reimbursement, from temporary codes like New Technology Add-On Payment codes that expire after 2-3 years to G-codes for procedures that don’t have CPT codes, on up to the holy grail of medical reimbursement: Category I codes. 

The new legislation – S.1399 or the Health Tech Investment Act – would simplify the situation by setting up a dedicated Medicare coverage pathway for AI-enabled medical devices approved by the FDA (called “algorithm-based healthcare services”), as follows … 

  • All FDA-approved products would be assigned a Category III New Technology Ambulatory Payment Classification in the HOPPS program.
  • NTAPC codes would last for five years to enable collection of cost data before a permanent payment code is assigned. 
  • Payment classifications will be based on the cost of service as estimated by the manufacturer. 

The bill at present has co-sponsors from both political parties, Sen. Mike Rounds (R-SD) and Sen. Martin Heinrich (D-NM). 

  • The legislation has also drawn support from industry heavyweights like GE HealthCare and Siemens Healthineers, as well as industry groups like AdvaMed and others.

The Takeaway

The new bill sounds like a great idea, but it’s easy to be skeptical about its prospects in today’s highly charged political environment – especially when even bipartisan compromises like the 2025 Medicare fix got scuttled. Still, S.1399’s introduction at least shows that the highest levels of the U.S. government are cognizant of the need to improve clinical AI reimbursement.

6 Imaging IT Tools Radiologists Want Now

Posted on by Brian Casey

It’s no secret that radiology faces a variety of challenges, from rising imaging volumes to workforce shortages. But can imaging IT vendors help? A new paper in Academic Radiology suggests they can, and provides a list of the half-dozen imaging IT tools that radiologists say they need most. 

Radiology is already one of the most software-oriented specialties in medicine. 

  • It was an early adopter of digital healthcare through tools like PACS, and is reprising its leadership in the coming AI era with the lion’s share of FDA-approved medical AI applications. 

But that doesn’t mean radiologists have all the IT tools at their disposal that they feel they need. 

  • The new paper is a sort of radiologist wish list, developed after a 2024 meeting between vendors and members of the Association of Academic Radiologists.

Some three dozen key opinion leaders met for breakout discussions on radiology’s unmet IT needs. The discussion was then boiled down into six major areas …

  1. Increased workstation efficiency, with better tools for looking through medical records to find clinical information. 
  2. Better AI tools for radiology reporting, such as auto-generated measurements and findings from prior studies for comparison. 
  3. Better methods for controlling imaging overutilization, such as clinical decision support systems to be used by referring physicians to order exams.
  4. Help from vendors to improve access to high-level radiology services in underserved areas like rural communities, such as through industry-sponsored training positions or improved telemedicine access to patients with follow-up appointments.
  5. Patient engagement tools that promote direct communication between radiologists and patients, including industry-sponsored training modules for radiologists to discuss findings with patients. 
  6. Simpler scheduling systems that allow patients to pick appointment times from their smartphones.

One possible question to ask about the recommendations is whether the needs of academic radiologists truly reflect those of radiologists in general, especially those in private practice.

  • But the items on the wish list appear broad enough that they hit the requirements of a wide range of imaging practitioners. 

The Takeaway

Sure, radiologists face many challenges in today’s healthcare environment. But the fact that radiology is such an IT-centered specialty offers hope that new software tools can help them – and that radiology vendors can lend a hand. 

Will FDA Staff Cuts Slow AI Adoption?

Posted on by Brian Casey

The Trump Administration’s campaign to cut the federal workforce arrived at the FDA last weekend – in particular its division regulating AI in healthcare. Multiple staff cuts were reported at the Center for Devices and Radiological Health, which had been in the midst of a major overhaul of AI regulation. 

A February 15 article in STAT News first reported the layoffs, which as with other recent staff reductions concentrated on FDA employees with probationary status and was part of a larger initiative that has also affected the CDC and NIH. 

The rapid growth of medical AI has had a major impact on the center, which as of its last report had given regulatory authorization to over 1k AI-enabled devices (76% of which are for radiology). 

  • To deal with the deluge, CDRH reportedly had been hiring many new staffers who were still on probationary status, making them targets for layoffs (permanent federal employees have civil service protections that make them harder to fire). 

FDA also has been retooling its regulatory approach to AI with new initiatives that reflect the fact that AI products continue learning (and changing) after they’ve been approved, and thus require more aggressive post-market surveillance than other medical devices…

So what impact – if any – will the layoffs have on the rapidly growing medical AI segment? 

  • The FDA may simply scale back its new AI initiatives and regulate the field under more traditional avenues that have served the medical device industry well for decades.

In another scenario, the FDA’s frenzied pace of AI approvals and initiatives could slow as the agency struggles to handle a growing number of product submissions with less staff. 

The Takeaway

The FDA layoffs couldn’t have come at a worse time for medical AI, which is on the cusp of wider clinical acceptance but still suffers from shaky confidence and poor understanding on the part of both providers and patients (see story below). The question is whether providers, organized radiology, or developers themselves will be able to step into the gap being left.

Get every issue of The Imaging Wire, delivered right to your inbox.

You might also like..

Select All

You're signed up!

It's great to have you as a reader. Check your inbox for a welcome email.

-- The Imaging Wire team

You're all set!