Tag: radiology

New Mammography AI Insights

Posted on by Brian Casey

Breast screening is becoming one of the most promising use cases for AI, but there’s still a lot we’re learning about it. A new study in Radiology: Artificial Intelligence revealed new insights into how well mammography AI performs in a screening environment. 

As we’ve reported in the past, mammography is one of radiology’s most challenging cancer screening exams, with radiologists sorting through large volumes of normal images before encountering a case that might be cancer.

In the new study, researchers applied Lunit’s Insight MMG algorithm to mammograms in a retrospective study of 136.7k women screened in British Columbia from 2019 to 2020. 

  • Canada uses single reading for mammography, unlike the double-reading protocols employed in the U.K. and Europe. 

AI’s performance was compared to single-reading radiologists using various metrics and follow-up periods, finding … 

  • At one-year follow-up, AI had slightly lower sensitivity (89% vs. 93%) and specificity (79% vs. 92%) compared to radiologists.
  • At two-year follow-up, there was no statistically significant difference in sensitivity between the two (83.5% vs. 84.3%, p=0.69). 
  • AI’s overall AUC at one year was 0.93, but this varied based on mammographic and demographic features, with AI performing better in cases with fatty versus dense breasts (0.96 vs. 0.84) and cases with architectural distortion (0.96 vs. 0.92) but worse in cases with calcifications (0.87 vs. 0.92).

The researchers then constructed hypothetical scenarios in which AI might be used to assist radiologists, finding …

  • If radiologists only read cases ruled abnormal by AI, it would reduce workload by 78%, but at a price of reduced sensitivity (86% vs. 93%) and 59 missed cancers across the cohort.

It’s worth noting that Insight MMG is designed to analyze 2D digital mammography exams.

The Takeaway

While the new findings aren’t a slam dunk for mammography AI, they do provide valuable insight into its performance that can inform future research, especially into areas where AI could use improvement. 

AI Helps Radiologists Read Prostate MRI

Posted on by Brian Casey

MRI is changing how prostate cancer is detected, diagnosed, and followed up. But even a technology as powerful as MRI could use a little help, as evidenced by a new study in Radiology showing that a commercially available AI algorithm could help radiologists diagnose clinically significant prostate cancer. 

Workup of suspicious prostate lesions is being reshaped by MRI in meaningful ways.

  • For example, MRI-guided biopsy is replacing systemic prostate biopsy without guidance, especially for patients with low to intermediate risk of prostate cancer. 

But prostate MRI isn’t perfect – yet. Radiologist performance can vary due to differences in experience, as well as variations in MRI acquisitions, tumor location, and cancer prevalence. Could AI help even out these variations? 

  • To find out, researchers from South Korea tested Siemens Healthineers’ syngo.via Prostate MR algorithm in 205 patients suspected of prostate cancer who were scheduled for biopsy based on clinical information (including previous MRI scans).

The AI algorithm’s performance was compared to that of experienced radiologists, and researchers also estimated its impact on radiologist interpretation if used as a reading aid, finding that for clinically significant prostate cancer… 

  • AI had lower sensitivity versus radiologists (80% vs. 93%).
  • But higher positive predictive value (58% vs. 48%).
  • Adding AI to radiologists’ interpretation more than doubled specificity (44% vs. 21%).
  • There were no cancer cases among lesions rated by both the algorithm and radiologists as not likely to be cancer (PI-RADS 1 or 2).

AI’s higher PPV indicates that it could help reduce unnecessary prostate biopsies, while also detecting clinically significant cancer that might have been missed by radiologists.  

The Takeaway

The new findings echo previous studies that demonstrate the value of AI for MRI of prostate cancer, but differ in that they investigate a commercially available algorithm – indicating that tools for better prostate MRI are becoming accessible to radiologists. 

More Radiologists Working for PE Practices

Posted on by Brian Casey

The share of U.S. radiologists working for practices owned by private equity has skyrocketed over the past decade, from 1% in 2013 to 12% in 2023. That’s according to a new study in AJR that documents the growing trend of PE ownership in medical imaging. 

As we reported recently, the growing number of private equity acquisitions in healthcare has raised questions about PE’s impact on patient care.

  • In radiology, some industry observers worry that PE acquisitions are changing the specialty in fundamental ways, turning radiologists from owner-stakeholders into corporate employees.

The new study analyzed PE acquisitions from 2013 to 2023, with a specific focus on geographic variations. 

  • Researchers found 151 PE acquisitions of radiology practices in the U.S. over the 11-year study period, through December 2023. 

Key findings were broken down as follows…

  • The share of radiologists working for PE practices boomed (12% from 1%). 
  • PE-acquired practices were associated with 16% of all U.S. radiology locations.
  • The states with the highest shares of PE-employed radiologists were Nevada (47%), Arizona (44%), Alaska (29%), Texas (27%), and Florida (24%).
  • Companies accounting for the largest number of PE-employed radiologists were Radiology Partners (70%), LucidHealth (8%), and U.S. Radiology Specialists (7%).

The new findings echo previous research showing PE’s geographic penetration to be greatest in the West and Southeast. 

  • They also underline the extent to which Radiology Partners dominates PE acquisitions as it brings independent imaging practices under its umbrella. 

The Takeaway

The new study – along with other recent research – demonstrates the extent to which private equity acquisitions are changing the face of radiology. Researchers should take the next step and investigate PE’s impact on radiologists’ career satisfaction, and by extension, patient care. 

Has Breast Cancer Mortality Bottomed Out?

Posted on by Brian Casey

The decades-long decline in breast cancer mortality has been lauded as a major public health success story. But a new study in Journal of Breast Imaging suggests that the long decline in breast cancer death rates may be coming to an end, at least for some women.

Breast cancer mortality’s drop has been well-documented, with studies estimating the drop to range between 44% to 58% over the last three to four decades – saving at least 500k lives. 

  • Most experts believe the breast cancer mortality decline has been driven by a combination of organized mammography screening and better cancer treatments.

But amid the success are disturbing signs. Cancer incidence rates are increasing for women younger than 40 – the established starting age for screening. 

  • Mammography screening also has seen disparities in care that have resulted in higher incidence and death rates for women of color. 

In the new study, researchers examined U.S. data for breast cancer mortality from 1990 to 2022, finding that over the study period breast cancer mortality …

  • Fell by 44% for women of all ages and ethnicities over the full study period.
  • Decreased by -1.7% to -3.3% annually from 1990 to 2010, but the decline slowed to -1.2% a year from 2010 to 2022. 
  • Declined -2.8% per year for women 20-39 years old from 1990-2010, but showed no decline from 2010-2022.
  • Lowered by -1.3% per year for women older than 75 from 1993-2014, but showed no decline from 2013-2022. 
  • Declined for White and Black women of all ages, but not for Asian, Hispanic, and Native American women.
  • Was 39% higher for Black women compared to White women from 2004-2022.   

The authors acknowledge that much of their data pertain to women who are outside current screening guidelines. 

  • But they see this as an opportunity to revisit whether screening guidelines should be extended – especially to women 75 and older – to realize the benefits of early breast cancer detection. 

The Takeaway

The new findings on breast cancer mortality indicate that even as mammography’s successes are celebrated, more work remains to be done to ensure that breast screening’s benefits are enjoyed by as many women as possible. 

ECR 2025 Video Highlights

Posted on by Brian Casey

The theme of ECR 2025 was Planet Radiology, and those who were in attendance at Austria Center Vienna last week witnessed the role that radiology can play in reducing medical imaging’s contribution to climate change.

As always, ECR 2025 was the focus of cutting-edge research in AI, as well as the latest findings in traditional applications like cancer screening.

In this special edition of The Imaging Wire newsletter, we offer a recap of our ECR 2025 videos with thought leaders and imaging vendors from the exhibit floor. 

We hope you enjoy watching our ECR 2025 videos as much as we enjoyed producing them! 

Check out the ECR 2025 videos below or visit the Shows page on our website, and keep an eye out for our next Imaging Wire newsletter on Thursday.

Screening Takes Center Stage at ECR 2025

Posted on by Brian Casey

New advances in cancer screening were among the major trends at last week’s ECR 2025 conference in Vienna. From traditional screening exams like mammography to up-and-coming tests like CT lung cancer exams, radiologists are emerging at the forefront of efforts to improve population health through early detection.

CT lung cancer screening is gaining momentum in Europe, and a Friday afternoon session explored the experiences of multiple sites…

  • U.K. researchers used DeepHealth’s Lung Nodules AI solution for automated triage of lung nodules found on non-screening CT chest exams, finding the approach could save £25k-£37k annually.
  • A German team documented technical lung CT acquisition parameters for screening centers in the SOLACE consortium across 10 countries, finding some room for improvement. 
  • Preliminary results from an Italian lung screening project were reported, with 2k people scanned with a 1.5% cancer detection rate (77% stage I-II) and 17% recall rate. Smoking cessation advice was also given.
  • Early results from a pilot screening project in Poland were given, with a 1.9% cancer detection rate in 3.1k people screened. They recommend screening be implemented nationwide. 
  • In a secondary analysis of 23.4k people in the NLST study, CT-derived body composition metrics predicted mortality beyond traditional risk factors.

Meanwhile, new ECR cancer screening research builds on the landmark accomplishments from 2024 in AI for breast screening. A Saturday afternoon session explored the progress being made…

  • German breast screening programs that deployed ScreenPoint Medical’s Transpara AI algorithm for 119k women saw their cancer detection rate grow (6 vs. 4.8 cancers per 1k) while the recall rate remained stable at around 2.5%. 
  • AI-supported double-reading in Italy for 120k women led to more breast cancers detected on baseline exams compared to subsequent screening rounds, as well as a 42% lower recall rate.
  • Patients found an AI chatbot based on GPT-4 generated responses to their questions that were more empathetic and readable than those of radiologists.
  • Another Italian study found that using AI for double-reading mammograms of 266k women led to a 21% increase in cancer detection rate and 15% drop in recall rate.
  • A secondary analysis of the MASAI trial suggested that double-reading with two radiologists continue to be used for high-risk women. Single reading of 3.8k high-risk exams resulted in 8.9% fewer detected cancers and 5.9% fewer recalls.

The Takeaway

Last week’s research on cancer screening at ECR 2025 shows that imaging experts see screening as a way to not only improve population health on a broad scale, but also to give radiologists the opportunity to raise their profile with patients and take a more direct role in patient care. The question is whether it’s an opportunity radiologists are ready to take.

Bridging Quality and Efficiency: Why Radiology Groups Are Adopting AI for Mammography Workflows

Posted on by Partner Content

By Dr. Roger Yang, President, University Radiology Group, and Mo Abdolell, CEO, Densitas

Radiology groups offering mammography services operate under ever-tightening demands, including MQSA EQUIP and ACR accreditation standards. Manual case selection, cumbersome paperwork, and lengthy review cycles often divert radiologists and technologists from what matters most – patient care.

But change is coming. By leveraging AI and mammography workflow automation, private radiology groups are reshaping how they manage quality, reduce administrative overhead, and advance patient care. 

AI-powered platforms can significantly streamline mammography quality management by:

  • Automating case selection for EQUIP reviews.
  • Measuring positioning metrics in near real-time.
  • Centralizing documentation to simplify compliance.

Some practices have reported up to a 90% reduction in EQUIP review time and 80% workload reduction in ACR accreditation using AI. But time savings are only part of the story.

Rather than waiting months for sporadic audits, technologists gain instant insights into positioning accuracy. This rapid feedback loop…

  • Accelerates targeted training.
  • Encourages continuous quality improvement.
  • Empowers technologists to self-monitor performance and identify gaps earlier. 

Today’s vendor-agnostic AI solutions integrate seamlessly with diverse imaging systems across multiple sites. 

  • Standards-based platforms can grow from a single mammography unit to dozens, helping radiology groups expand without adding complexity.

In a crowded marketplace, radiology practices that adopt AI-driven mammography quality management and automation stand out as forward-thinking leaders. Advantages include…

  • Enhancing patient perception: Offering efficient exams and high-quality imaging underscores a commitment to excellence, boosting satisfaction and referrals.
  • Leveraging analytics: Aggregated data on image quality and positioning helps leadership identify trends, optimize workflows, and highlight innovation.
  • Attracting top talent: Skilled technologists and radiologists gravitate toward practices with cutting-edge tools.

By integrating AI early, private practices can differentiate themselves, paving the way for growth and success.

Successful AI adoption and mammography workflow automation relies on more than just software. It requires:

  • Deep mammography expertise from vendors.
  • Robust training programs for staff.
  • Change training programs for staff.
  • Responsive customer support that fosters trust.

Mammography workflow automation cuts administrative burdens, curtails physician burnout, and speeds accreditation. Technologists receive clear, timely feedback, improving morale and performance. 

  • Meanwhile, patients benefit from streamlined workflows and consistent image quality, reinforcing trust in the practice.

The Takeaway

By embracing AI-driven mammography workflow automation and quality management, radiology groups can stay focused on delivering exceptional patient care while meeting regulatory requirements. This strategic investment propels private practices toward sustained growth and innovation, securing a competitive edge in a rapidly evolving healthcare landscape. Learn more.

Highlights from ECR 2025

Posted on by Brian Casey

This week’s European Congress of Radiology is underway in Vienna, and things are heating up in the cozy confines of Austria Center Vienna. 

The theme of this week’s meeting is Planet Radiology, and conference organizers have made sustainability a major priority. 

  • As one of healthcare’s biggest consumers of energy, radiology has a responsibility to lead efforts to reduce greenhouse gases – a challenge that ECR 2025 president Prof. Andrea Rockall compared to the discipline’s successful effort to reduce radiation exposure.

Planetary health was the focus of a glitzy opening ceremony on February 26 before a standing-room-only crowd.

  • The program featured not only the musical and dance performances that are an ECR hallmark but also awe-inspiring videos that focused on each of the four planetary elements: water, air, fire, and earth. 

But scientific content has always been ECR’s main draw, and ECR 2025 so far hasn’t disappointed. Below are some highlights from the first two days of clinical presentations … 

  • New data from the MASAI study of AI for mammography screening were presented Wednesday, finding that ScreenPoint Medical’s Transpara algorithm cut interval cancers 12%.
  • Using AI instead of double-reading for biennial digital mammography screening saved $64k per 1k patients thanks to lower cancer treatment costs. 
  • The MA-DETECT study of 350 women used breast MRI on women with negative mammograms, with a cancer detection rate of 26 additional cancers per 1k women.
  • Aidoc’s AI algorithm for detecting cervical spine fractures on CT found 23 fractures missed by radiologists out of 2.3k scans, saving €6k per missed fracture.
  • Gleamer’s BoneView AI algorithm for fracture detection detected 81% of fractures missed by radiologists in patients who had filed compensation claims, potentially saving €265k.
  • The percentage of AI research studies with peer-reviewed evidence grew in 2023 compared to 2020 (67% vs. 35%) but the ratio showing clinical efficacy fell (52% vs. 55%).
  • Subtle Medical’s SubtleHD MRI enhancement algorithm improved signal-to-noise ratio by 73% and image sharpness by 27% in 205 MRI scans.
  • In a secondary analysis of the MIDAS study of clinical decision support in Germany, requests for inappropriate imaging were more frequent in women than men (7.3% vs. 6.1%). 
  • A majority of patients in Italy preferred ChatGPT-authored reports over those penned by radiologists (61%), with 70% saying they were more readable and 58% saying they were easier to understand. 
  • Researchers found that oral glucosamine could be used for breast MRI exams with a chemical exchange saturation transfer sequence. They found higher CEST values in tumor regions in a small study of 16 patients.
  • Italian researchers combined CT and contrast-enhanced mammography with the same contrast agent, finding higher sensitivity and specificity for detecting metastases than traditional methods.
  • German researchers ran a 0.4T permanent magnet MRI scanner off the grid for a year with solar panels and a generator-supported battery system. 
  • Using deep-learning reconstruction for MRI scans reduced energy consumption 65% thanks to shorter scan times while maintaining image quality. 
  • More patients preferred contrast-enhanced mammography (72%) compared to breast MRI (26%), mostly due to faster exam times and lack of claustrophobia. 

The Takeaway

This week’s ECR 2025 demonstrates the rich scientific research being conducted across Europe – much of which will eventually translate into commercial products. As the U.S. experiences regulatory turbulence and uncertainty around long-term funding for academic research, the focal point of radiology innovation could soon shift across the Atlantic.

Are CT Lung Screening Patients Sicker?

Posted on by Brian Casey

Amid the rush of enthusiasm for CT lung cancer screening, a new study published in JAMA Health Forum offers a cautionary note. Researchers found that in the real world, people eligible for lung screening were sicker than those in research studies, and thus may not enjoy screening’s benefits to the same extent. 

Support for CT lung cancer screening is based on randomized controlled trials published in 2011 (NLST) and NELSON (2020) that showed screening reduced lung cancer mortality among high-risk individuals who typically had long smoking histories. 

  • The studies have spurred momentum for large-scale CT lung cancer screening programs, with a number of European and Asian countries starting national initiatives. 

But how generalizable are these results? Researchers noted that people who participated in the NLST study tended to be younger and healthier than individuals who qualify for screening in the real world. 

  • Co-morbidities like COPD, diabetes, and heart disease, as well as age and racial background, can have an impact on survival after treatment for lung cancer, and thus could reduce screening’s risk/benefit calculation. 

In the new Personalized Lung Cancer Screening study, researchers analyzed the comorbidity profiles of 31.8k people who got screened between 2016 and 2021 in California, Florida, and South Carolina. 

  • They noted that their PLuS study cohort was more diverse in terms of age, race, and ethnicity than that used in NLST, and potentially had more comorbid conditions. 

In analyzing their population, PLuS researchers found that compared to NLST participants, people screened in their real-world programs had …

  • Higher rates of COPD (33% vs. 18%).
  • Higher rates of diabetes (25% vs. 9.7%).
  • Higher rates of heart disease (16% vs. 13%).
  • Were more likely to be aged 70 and over (25% vs. 8.8%).
  • Had high scores on various metrics of comorbidity and frailty. 

Older, sicker patients are less likely to have good health outcomes after lung cancer surgery, and might also succumb to conditions like COPD, diabetes, and heart disease before lung cancer, which could also reduce lung screening’s benefits.

The Takeaway

While the new findings aren’t likely to seriously dampen CT lung cancer screening’s growing momentum, they do illustrate a point that should always be kept in mind when looking at research results: in the real world, your mileage may vary. 

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!