Tag: artificial intelligence

AI for Chest X-Ray Varies

Posted on by Brian Casey

Not all AI is created equal when it comes to analyzing chest X-rays. A new study in Radiology found wide variation in performance for seven commercially available chest X-ray algorithms to detect lung cancer. 

X-ray is by far the most widely used imaging modality. Radiography is often the first imaging exam a patient receives, and it frequently serves as a gateway to other more advanced imaging modalities. 

  • But radiography also has well-known shortcomings (which is why advanced imaging is needed for follow-up). Could AI help unlock X-ray’s value and make it more useful?

That’s what a host of AI algorithm developers are banking on, but the wide variety of solutions can create confusion for clinicians.

  • So U.K. researchers decided to hold an AI bake-off, comparing commercially available algorithms from seven developers for detecting lung cancer on chest X-rays. 

The competing companies included Annalise/Harrison.ai, Gleamer, Infervision, Milvue, Oxipit, Qure.ai, and Rayscape. Researchers anonymized performance results from the different products.

In all, chest radiographs from a dataset of 5.2k patients with a real-world lung cancer prevalence rate were included, with researchers finding…

  • Significant variance in algorithm performance by each of the major accuracy measures: sensitivity (21%-78%), specificity (59%-98%), and positive predictive value (1.5%-28%). 
  • All the algorithms increased the number of false positives, and with significant variation. One model generated only 10 more false positives than radiologists, while another produced – wait for it – over 2k. 
  • If used to triage patients for follow-up CT exams, one model would generate $1.6k in additional costs while another would produce $327k.

What accounts for the variation? An underlying factor is most likely differences in the datasets used for model training. 

  • In any event, the study underscores the need for more head-to-head comparisons to determine the strengths and weaknesses of individual AI algorithms. 

The Takeaway

This week’s study on how AI performance varies between commercially available algorithms initially seems disturbing and might suggest a need for stronger regulatory oversight. But AI’s diversity could be its strength in a future where every patient case is analyzed by multiple different algorithms, each with its own advantages. This could ultimately produce a more complete picture of the patient than any one algorithm on its own.

AI for PE Detection: ‘Selective but Meaningful’

Posted on by Brian Casey

AI made a “selective but meaningful” contribution to radiologist interpretations of CT pulmonary angiography scans for pulmonary embolism. The study, published in Radiology: Artificial Intelligence, offers valuable insights into real-world implementation of AI on a large scale. 

One of the major criticisms of AI is that algorithms used in real-world clinical situations don’t perform as well as they do in the controlled environments that vendors use to acquire data for regulatory submissions.

  • AI performance can drop off as much as 20 to 30 percentage points for important metrics like sensitivity and specificity. 

The new study sought to investigate this phenomenon by analyzing a real-world implementation of Aidoc’s AI algorithm for PE detection. 

  • Researchers assessed the algorithm’s performance for analyzing CTPA exams across a variety of clinical environments in an integrated health network, including the emergency department and inpatient and outpatient settings. 

Scans of 29.5k patients acquired from 2021 to 2023 were included. AI analyzed images in real time, after which exams were interpreted by radiologists who knew the AI findings. Researchers found…

  • Radiologists using AI had higher sensitivity than the algorithm on its own (99% vs. 85%).
  • Specificity was more or less the same (99.8% vs. 99.5%).
  • Agreement between radiologists and AI was high (98%).
  • Agreement was higher when AI assessed cases as negative rather than positive (98% vs. 94%).
  • Radiologists disagreed with AI in 2.2% of cases. The final determination by a panel of expert thoracic radiologists strongly favored radiologists (89%).
  • Of the 3.3k cases positive for PE, 0.81% were detected only by AI – or 26 cases.

In analyzing the results, the researchers characterized AI’s contribution as “selective but meaningful.”

  • AI-positive results meant scans might require more scrutiny from radiologists, while an AI-negative call might be supportive – but not definitive – for negative PE.

The Takeaway

The new study of AI for PE detection is a fascinating look at real-world AI deployment. While the sensitivity, specificity, and agreement numbers are interesting, what draws our attention is the 26 PE cases caught only by AI over 18 months of use. That boils down to 26 patients whose clinical condition wasn’t missed, and 26 potential malpractice lawsuits that were never filed.

AI’s ROI Paradox

Posted on by Brian Casey

As radiology AI slowly moves from pilot projects to widespread clinical adoption, a new survey reveals a paradox: The technology is popular with radiologists, but few imaging facilities using AI have collected hard data showing its return on investment.

AI’s slow clinical adoption has frustrated both clinicians and algorithm developers alike, but the technology is gaining steam.

  • Despite growing clinical evidence, research on AI’s financial value and ROI has been slower in coming. 

To remedy that situation, AI governance startup Croviz.ai conducted a study of 445 radiology AI users on the economics and evaluation of AI. The full report is available here.

  • Survey respondents came from 12 different countries and included a variety of professional roles, including vendor executives, radiologists, and IT and informatics personnel.

Croviz founders Ayman Talkani and AadilMehdi Sanchawala found that while radiology AI power users loved the technology – and some refused to work without it – few had determined a positive financial return from it. Findings included…

  • 95% of sites already using AI had renewed at least one contract with an AI vendor in the last 12 months.
  • But only 30% had quantified a positive financial ROI from AI.
  • 54% cited better quality of life for radiologists as their main reason for renewing an AI contract.

So if AI’s value hasn’t been demonstrated, why are radiology sites renewing AI contracts?

  • The number one reason cited by 54% of those renewing contracts was because their radiologists felt AI improved their quality of life – the only outcome measure leadership could quickly measure with qualitative user feedback.
  • Lower on the scale was reduced turnaround time (18%), more scans per reader (10%), reduced downstream patient costs (10%), and better diagnostic accuracy (8%). 
  • Just 6% paid attention to hard metrics like staff retention rates.

What’s the best way out of the AI ROI paradox? The Croviz researchers recommended more frequent and transparent AI governance.

  • Survey respondents who monitored AI performance more closely – such as more often than once per quarter – exhibited more trust in AI.

The Takeaway

The new survey offers an intriguing look at AI adoption and the question of ROI for the technology. It suggests that – much like another digital technology, PACS – AI adoption is being driven more by its popularity among radiologists than hard ROI considerations.

FDA Updates AI List with New Clearances

Posted on by Brian Casey

The FDA last week updated its list of cleared AI-enabled medical devices, with the new list showing AI marketing authorizations through the end of 2025. The updated list reveals that radiology is maintaining its lead as the medical specialty with the most clearances.

The FDA’s previous update featured data through the end of September 2025, and showed the number of AI-enabled medical devices for radiology crossed the 1k mark. The new numbers show continued momentum for medical imaging.

  • The agency’s data go all the way back to 1995 (the first cleared radiology device on the list was ImageChecker from R2 Technology/Hologic in 1998). 

The new list tracks authorizations through the end of December 2025, and indicates the agency has…

  • Authorized 1,451 AI-enabled medical devices since it began keeping track in 1995.
  • Approved 1,104 radiology devices, or 76% of total AI-enabled medical authorizations.
  • In the fourth quarter of 2025, the FDA cleared 72 AI-enabled medical devices, of which 55 (76%) were radiology devices. 
  • For all of 2025, radiology secured 75% of authorizations, compared to 73% for all of 2024 and 80% for 2023. 
  • GE HealthCare retained the top spot as the company with the most radiology AI authorizations at 120 (including acquisitions Bay Labs, BK Medical, Caption Health, MIM Software, icometrix, and Spectronic Medical).
  • Next is Siemens Healthineers at 89 (including Varian), then Philips at 50 (including DiA Analysis and TomTec), Canon at 45 (including Vital Images and Olea), United Imaging at 38, Aidoc at 31, and DeepHealth at 28 (including Quantib and iCAD). 

As we’ve noted in the past, the FDA’s list includes not only standalone software applications, but also imaging hardware with embedded AI applications, such as a mobile X-ray system with AI algorithms for detecting emergent conditions. 

The Takeaway

The new FDA list shows radiology’s continued dominance when it comes to AI-enabled medical device technology. But an interesting subtext is the ongoing consolidation in the radiology AI space, which could mean that some firms may be climbing the list quickly.

Agentic AI for Radiology Follow-Up

Posted on by Brian Casey

Agentic AI has quickly become one of the hottest topics in radiology. But what is it really good for? Texas researchers offer one possible use case in a new study in NEJM Catalyst: scouring radiology reports to identify patients who require follow-up. 

Agentic AI is a new flavor of artificial intelligence that’s capable of working autonomously to complete tasks with minimal human supervision.

  • In healthcare, it’s being applied to a wide range of tasks, from improving health system operations to clinical and administrative jobs.

In the current study, researchers from Parkland Health in Dallas assigned agentic AI to one of the trickiest tasks in radiology: making sure patients with suspicious findings comply with recommendations for follow-up procedures.  

  • Previous studies have documented low rates of adherence to radiologist recommendations for follow-up imaging (possibly as low as 50%), creating the uncomfortable possibility of missed opportunities that could have major patient-care ramifications.

The dilemma can be compounded with the use of structured note templates in EHRs, as improper use or modification of these macros can lead to missed notifications. 

  • To address the problem, Parkland clinicians developed an AI agent based on a pretrained open-source large language model (Meta’s LLM Llama 3 70B) that reviews clinical impressions, extracts important details for follow-up, and integrates its findings into departmental workflow to enable patient outreach.

In tests on 10k radiologist notes, Parkland researchers found that their AI agent…

  • Had an overall detection rate of ~5.1%, slightly lower than other published studies (8% to 12%).
  • Had far higher sensitivity than Parkland’s previous macro-based follow-up notification system (99% vs. 16%), correctly flagging 6X more cases (513 vs. 83).
  • Achieved higher accuracy (99% vs. 58%), and 94% accuracy for characterizing follow-up timing, recommended procedure, and underlying abnormality. 

Considering Parkland’s annual volume of 500k imaging studies, the AI agent could identify 21.5k follow-up cases a year. 

  • Many of these could be serious issues, such as new cancer diagnoses or pathologies that require surgical intervention. 

The Takeaway

The new study shows that agentic AI isn’t some technogeek’s far-off dream – it’s a useful tool on the verge of real-world implementation, with the potential to improve patient care without overburdening radiology staff.

Doctors Adopt ‘Shadow AI’ for Efficiency Gains

Posted on by Brian Casey

Doctors under pressure to work more efficiently are looking for help from “shadow AI” – artificial intelligence applications adopted outside a formal hospital approval process. A new survey of U.S. healthcare personnel found that many administrators have encountered unauthorized AI tools in their organizations, including some used for direct patient care. 

U.S. healthcare providers are struggling under rising patient volumes in the midst of an ongoing workforce shortage, a situation that’s leading to burnout among clinicians. 

  • AI is often touted as a possible solution by enabling providers to do more with less, but the jury is still out on whether this works in the real world. 

The new survey was conducted by Wolters Kluwer Health to assess usage of what the report described as “shadow AI,” or AI that’s adopted without proper hospital authorization processes. 

  • Shadow AI introduces risk to data, security, and privacy, and providers should better understand the need for an enterprise approach to AI with appropriate controls.

It’s worth noting that the report’s use of the term “authorization” applies primarily to an institution’s internal approval and governance processes for AI rather than formal FDA regulatory authorization. 

  • AI algorithms that aren’t used for direct patient care don’t require FDA authorization, as the agency pointed out in a guidance just a few weeks ago. 

Researchers surveyed 518 health professionals, finding…

  • 41% were aware of colleagues using unauthorized AI tools.
  • 17% said they had personally used an unauthorized tool.
  • 10% said they had used an unauthorized AI tool for direct patient care.

While the report’s recommendation for stronger AI governance is valid, there could be a competitive subtext to the findings. Wolters Kluwer offers healthcare clinical decision support solutions, and the company is currently locked in a fierce battle with OpenEvidence for dominance in the CDS space.

  • OpenEvidence’s CDS solution is wildly popular with clinicians, many of whom install and consult with the software on their own, outside an enterprise-level governance – exactly the kind of “unauthorized” model the new report criticizes.

The Takeaway

The Wolters Kluwer report could be shedding light on a concerning new trend, or it could represent an effort by an established player to shut out a competitive threat. Either way, its warning on the need for appropriate enterprise-level AI governance should not be ignored.

Canon Celebrates 50 Years of CT Innovation: Redefining Healthcare with Meaningful AI

Posted on by Partner Content

This year marks a historic milestone for Canon – five decades of pioneering CT innovation that has transformed the landscape of healthcare. From introducing industry-first technologies to setting new standards in diagnostic imaging, Canon continues to lead the way in delivering solutions that matter.

Canon’s legacy is built on breakthroughs such as its three-time award-winning wide-area CT systems, deep learning reconstruction that brings 1K resolution to CT imaging, and automation improving workflow. 

  • These innovations have consistently elevated diagnostic confidence, patient safety, and operational efficiency.

In today’s world, AI is everywhere – but Canon’s AI is Meaningful AI. It’s not about AI for the sake of technology; it’s about creating real-world impact on patient care. 

  • Canon’s portfolio of scanner-integrated AI applications is designed to enhance image quality, streamline workflows, and improve consistency – ultimately delivering better care, better experience, and better efficiency for patients and providers alike.

Canon is redefining CT by making AI a core component across its portfolio. Key innovations include…

  • AI-Assisted Scanner Workflow Automation. Canon’s INSTINX platform introduces intuitive, intelligent, and integrated AI technologies that enable autonomous CT operations. By simplifying complex workflows, INSTINX helps technologists focus on patient care while improving throughput and reducing variability.
  • AI-Assisted Post-Processing. Canon’s Automation Platform offers a zero-click, AI-driven solution that accelerates image post-processing. By delivering fast, actionable insights, this platform ensures time-critical results reach care teams when they need them most.
  • AI-Assisted Reconstruction. Advanced algorithms such as AiCE DLR and PIQE DLR leverage deep learning to reveal critical diagnostic information – contrast and resolution – while optimizing dose efficiency. These tools empower clinicians to make confident diagnoses and reduce the need for additional downstream studies. Additionally, CLEARMotion, a DCNN-based algorithm, compensates for patient motion, reducing blur and delivering high-quality results even in challenging cases.

The Takeaway 

As Canon celebrates 50 years of CT innovation, its commitment remains clear: harnessing AI to make imaging smarter, faster, and more meaningful. With these advancements, Canon is not just shaping the future of CT – it’s setting a new benchmark for patient-centered care.

Next-Generation AI Platform Redefines Radiology Workflow Standards

Posted on by Partner Content

AI is no longer being viewed as a diagnostic aid but as essential medical infrastructure. Nowhere is that more apparent than in lung screening, with Germany and other European Union countries increasingly embedding AI into their lung cancer screening guidelines and pilot programs.

This evolution will be on display at RSNA 2025, where Coreline Soft will introduce its groundbreaking chest AI platform AVIEW 2.0.

  • The solution demonstrates how unified AI automation is fundamentally transforming radiology workflows and elevating diagnostic precision across pulmonary, cardiac, and airway pathologies.

AVIEW 2.0 represents a paradigm shift from task-specific tools to an integrated diagnostic ecosystem. 

  • The platform seamlessly combines lung-cancer screening (LCS), coronary-artery calcium (CAC) scoring, and COPD quantification into a single, continuous analytical pipeline. 

Clinical validation shows radiologists using AVIEW 2.0 achieve 89% increase in case throughput and 60% reduction in interpretation time compared to the previous generation. 

  • This effectively consolidates multi-disease CT assessment into one streamlined, automated workflow.

AVIEW’s clinical foundation extends far beyond pilot studies. The platform has processed over 2.5M cases across 19 countries, establishing itself as a proven solution in diverse healthcare ecosystems. 

  • Most notably, AVIEW has been selected as the AI platform for major government-led lung cancer screening pilots and programs in Germany, France, and Italy.

Beyond Europe, AVIEW solutions are already integrated into major U.S. medical centers, where their clinical reliability has been independently validated in real-world settings…

  • UMass Memorial Medical Center has deployed the system as an integrated platform for LCS, CAC, and COPD diagnosis, supporting full-spectrum thoracic screening in daily radiology operations.
  • Temple Lung Center, 3DR Labs, and ImageCare Radiology have incorporated AVIEW products into their research and diagnostic environments – each adapting AI functions to site-specific workflows and physician preferences.

SOL Radiology, a fast-growing radiologist-owned practice serving communities across California and Illinois, has deployed AVIEW LCS Plus across its outpatient centers and hospital network, leveraging the platform for high-confidence nodule detection, rapid turnaround, and integrated COPD/CAC assessment. 

  • The group reports significant gains in diagnostic efficiency and consistency within one week of implementation, supporting its vision for technology-driven, high-quality community radiology.

With national-scale validation in Europe, clinical adoption across top-tier U.S. institutions, and 2.5M cases processed globally, Coreline Soft is positioning AVIEW 2.0 as the new benchmark for AI-driven thoracic imaging – where efficiency, accuracy, and scalability converge.

The Takeaway

Coreline Soft will conduct an end-to-end AI workflow demonstration in the “Radiology Reimagined” demo zone at RSNA 2025, using real-world clinical scenarios. With AVIEW and HUB, the full pathway – from triage and interpretation to reporting and quality management – will be validated against standards such as IHE and FHIR, allowing attendees to experience integrated flow firsthand. Learn more or book an appointment on Coreline Soft’s website.

AI First Drafts: A New Dawn for Radiology Reporting

Posted on by Partner Content

For radiologists – the medical detectives who find clues in our medical images – the daily grind can feel like a “death by a thousand cuts.” Much of their time is spent not on diagnosis, but on tedious reporting. 

Now, a new generation of artificial intelligence is stepping in to serve as a high-tech scribe, automating the drudgery.

  • This AI tackles reporting, the most time-consuming part of radiologists’ workflow.

AI-enabled radiology reporting makes transcribing data from technologist worksheets a thing of the past, using Optical Character Recognition (OCR) to decipher everything, even what looks like “chicken scratch handwriting.” Then…

  • A large language model (LLM) applies clinical context to ensure it understands the meaning.
  • It intelligently injects that data into the correct sections of the radiologist’s personal report template.
  • Finally, it performs its own “inference,” like calculating a TI-RADS score and dropping it right into the impression.

Modern AI also learns from a radiologist’s actions, providing a hands-free way to build a report, with features such as…

Smart Measurements: When a lesion is measured, the AI recognizes the location and automatically adds the data and comparisons to prior scans into the report.

Automated Prior Population: Instead of struggling with speech-to-text, the AI notices when a prior study is opened for comparison and automatically populates that exam’s date.

Streamlined Expert Findings: A radiologist can simply state positive findings, and the AI acts as both writer and editor. 

AI-enabled radiology reporting weaves dictated phrases into complete sentences, generates an impression based on clinical guidelines like BI-RADS, and serves as a vigilant proofreader, flagging errors like laterality mistakes or semantic impossibilities. 

As AI technology matures, the software itself is becoming easier to build. The true differentiator is the team behind it. 

  • For radiologists evaluating these new reporting tools, it’s critical to look for teams that are “AI native” – built from the ground up with AI at their core. 

Companies founded on these principles, such as New Lantern, are pioneering these all-in-one radiology reporting solutions, treating the challenge not as a problem to be fixed with another widget, but as an opportunity to build one complete, intelligent platform. 

The Takeaway 

The evolution in AI-enabled radiology reporting isn’t about replacing radiologists; it’s a tool to augment their skills. Radiologists who harness AI to create reports faster will significantly outpace those who do not, allowing them to return their full focus to the art of diagnosis.

Ensemble Mammo AI Combines Competing Algorithms

Posted on by Brian Casey

If one AI algorithm works great for breast cancer screening, would two be even better? That’s the question addressed by a new study that combined two commercially available AI algorithms and applied them in different configurations to help radiologists interpret mammograms.

Mammography AI is emerging as one of the primary use cases for medical AI, understandable given that breast imaging specialists have to sort through thousands of normal cases to find one cancer. 

Most of these studies applied a single AI algorithm to mammograms, but multiple algorithms are available, so why not see how they work together? 

  • This kind of ensemble approach has already been tried with AI for prostate MRI scans – for example in the PI-CAI challenge – but South Korean researchers writing in European Radiology believed it would be a novel approach for mammography.

So they combined two commercially available algorithms – Lunit’s Insight MMG and ScreenPoint Medical’s Transpara – and used them to analyze 3k screening and diagnostic mammograms.

  • Not only did the authors combine competing algorithms, but they adjusted the ensemble’s output to emphasize five different screening parameters, such as sensitivity and specificity, or by having the algorithms assess cases in different sequences.

The authors assessed ensemble AI’s accuracy and ability to reduce workload by triaging cases that didn’t need radiologist review, finding…

  • Outperformed single-algorithm AI’s sensitivity in Sensitive Mode (84% vs. 81%-82%) with an 18% radiologist workload reduction.
  • Outperformed single-algorithm AI’s specificity in Specific Mode (88% vs. 84%-85%) with a 42% workload reduction.
  • Had 82% sensitivity in Conservative Mode but only reduced workload by 9.8%.
  • Saw little difference in sensitivity based on which algorithm read mammograms first (80.3% and 80.8%), but both approaches reduced workload 50%.

The authors suggested that if applied in routine clinical use, ensemble AI could be tailored based on each breast imaging practice’s preferences and where they felt they needed the most help.

The Takeaway

The new results offer an intriguing application of the ensemble AI strategy to mammography screening. Given the plethora of breast AI algorithms available and the rise of platform AI companies that put dozens of solutions at clinicians’ fingertips, it’s not hard to see this approach being put into clinical practice soon.

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