Tag: mammography

AI in Radiology: Old Problems, New Tech

Posted on by Partner Content

By Mo Abdolell, CEO, Densitas

Radiology has seen this movie before. Big promises (efficiency, accuracy, burnout relief). Big anxieties (ROI, workflow chaos, pressure to “keep up”). The question isn’t whether AI is powerful. It’s whether we’ve learned how to deploy new technology without repeating the pain of PACS migrations and the EHR era.

The Myth of the Perfect Rollout. Health technology assessment (HTA) sounds great in theory – rigorous, comprehensive, evidence-first. In practice, few organizations have the time, talent, or budget to execute it at scale. 

  • Remember EHRs: adoption happened because policy and money forced it, not because the playbook was tidy. Healthcare’s default pattern is to adopt, then evolve – messy, market-driven, and iterative. Waiting for perfect plans is how you get left behind.

Are AI’s Problems really new?

  • Black box déjà vu. Radiology has long trusted complex, opaque systems (reconstruction algorithms, vendor-specific pipelines). What mattered – and still matters – is validated performance and dependable outputs, not full internal transparency.
  • Model drift ≈ old friends. We’ve always recalibrated clinical tools as populations and scanners change. Monitoring and revalidation are known problems, not alien ones.

What’s Different This Time? Unlike the top-down EHR mandate, AI is largely market-driven. That gives providers agency. 

  • AI solutions must save time, improve outcomes, or avoid costs – not just publish a ROC curve. They must show operational value inside the native radiology workflow.

Fortunately, there are ways to adopt AI and then evolve your processes to make it work…

  • Workflow or bust. Demand in-viewer evidence objects, one-click report insertion, and EHR write-back. If AI adds steps, it subtracts value.
  • Start narrow, scale deliberately. Pick high-volume, high-friction tasks. Prove value in weeks, not years. Expand only when the operational signal is undeniable.
  • Measure what matters. Track operational metrics like seconds saved and coverage (e.g. eligible cases processed before dictation), reliability (e.g. results present before finalization, fail-open behavior), and user friction like context-switching rate and time-to-evidence.
  • Monitor. Stand up organization and site-level performance checks. Treat AI like equipment – scheduled, observed, and maintained.
  • Invest in long-term value. Favor standards, vendor-agnostic interoperability, clear telemetry, and transparent pricing.

The Takeaway

AI’s success in radiology won’t be defined by elegance of algorithms but by pragmatism of deployment. This will be an evolution – hands-on, incremental, sometimes messy. The difference now is that radiology can drive. Make the technology serve the service line – not the other way around.

Target the toughest workflows. Adapt and evolve with Densitas Breast Imaging AI Suite.

New Cancer Disparity Data Show Socioeconomic Impact

Posted on by Brian Casey

Cancer screening disparities continue to draw scrutiny in radiology. A new study in JAMA Network Open takes a closer look at why some people don’t get screened as often as they should – as well as the factors that contribute to cancer prevalence and mortality. 

There’s extensive research backing the lifesaving potential of the major cancer screening exams, and cancer mortality rates have consistently declined thanks to the combination of screening and better treatments. 

  • But the declines are uneven, prompting researchers to investigate reasons for the disparities, such as in a study earlier this month documenting geographic variations in cancer screening rates. 

In the new study, researchers from the ACR’s Harvey L. Neiman Health Policy Institute looked at how 24 measures like lifestyle, socioeconomic status, and environmental background affected breast, prostate, lung, and colorectal cancer, which account for 50% of new cancer cases.

  • In particular, they examined screening completion rates and cancer prevalence and mortality at the county level in a nationally representative sample of 5% of Medicare fee-for-service beneficiaries, of whom 87% were 65 years and older. 

There’s a lot to unpack in the study, but a few highlights are below as they relate to breast and lung cancer, the two cancers for which imaging-based screening is recommended. The top three factors affecting each (in order of importance) are…

  • Breast cancer:
    • Screening rates – Hispanic population share, levels of insufficient sleep, and poverty. 
    • Prevalence – uninsured status, obesity, and housing insecurity.
    • Mortality – non-Hispanic Black race, environmental justice index, and insufficient sleep.
  • Lung cancer:
    • Screening rates – air pollution exposure, lack of access to primary care physicians, and number of poor physical health days.
    • Prevalence – limited access to healthy foods, uninsured status, and severe housing problems.
    • Mortality – smoking, poor physical health days, and environmental justice index. 

While there are some obvious findings in the data (the connection between smoking and lung cancer mortality, for example), the dominance of socioeconomic measures may take some by surprise (or maybe not). 

  • But they do track with previous research finding that socioeconomic factors account for 40-50% of health impacts.

The Takeaway

The new study – as with previous research – reinforces what we know about the strong connection between socioeconomic status and cancer screening disparities. The new data should give clinicians and public health advocates more detail on the specific factors they need to focus on to improve screening compliance and reduce cancer’s burden on society.

Hologic to Go Private in $18.3B Buyout

Posted on by Brian Casey

Women’s imaging vendor Hologic will go private in an $18.3B buyout led by two private equity firms, Blackstone and TPG. The move is easily the largest acquisition in radiology this year – the question is how it will impact one of the biggest corporate success stories in women’s health. 

Hologic has a long history in medical imaging and was founded in 1985 to develop and market bone densitometry systems. It soon expanded into mammography, molecular diagnostics, and women’s health treatments.

  • The company went public in 1990, and has maintained its independence even as radiology underwent a period of consolidation in the 1990s and 2000s that saw most mid-cap firms get acquired by multinational OEMs.

Much of Hologic’s momentum was driven by the conversion of U.S. mammography facilities from standard 2D mammography to 3D digital breast tomosynthesis. 

  • This shift was led by Hologic’s Selenia Dimensions system, which in 2011 was the first DBT system to get FDA approval. Hologic rode its momentum to a U.S. mammography installed base market share approaching 70%. (Signify Research estimates Hologic currently has a 34% market share of the global mammography market.)

But as often happens to many market leaders, Hologic’s position began slipping in recent years. 

  • The multinational OEMs have improved their positions in women’s imaging, releasing DBT systems that are more competitive with Hologic’s offerings while also benefiting from multiyear purchasing agreements with large health systems in which mammography systems can be bundled with CT, MRI, and other equipment. 

Perhaps as a result, Hologic’s Breast Health segment has become a drag on revenue growth due to lower equipment sales. Breast Health revenues for the most recent Q3 period fell 5.8%, following a 6.9% drop in Q2 and a 2.1% decline in Q1. 

  • Indeed, reports began surfacing in May 2025 that Blackstone and TPG were targeting Hologic for acquisition, with Hologic reportedly rejecting a $16.7B offer. 

The bid was apparently sweetened, with an acquisition price of $79 a share, a 46% premium from before the acquisition rumors started, for a total value of $18.3B. The buyout should close in the first half of calendar 2026.

The Takeaway

Hologic built itself into a radiology success story through a combination of technological innovation and an obsessive focus on a single market segment – women’s health. The question is whether that focus will continue under its new PE-led ownership.

Cancer Screening Rates Vary Geographically

Posted on by Brian Casey

Progress has been made in some U.S. regions in boosting adherence rates for cancer screening exams like mammography, but clusters of regional variation remain. That’s according to a new study in JAMA Network Open that offers hope for reducing access disparities in disadvantaged areas.

Disparities in healthcare access remain one of the nagging problems in the U.S. healthcare system. 

  • Previous studies have shown that racial background, socioeconomic status, and geographic location can all affect access to care, and ultimately, patient outcomes.

Nowhere is this more apparent than in cancer screening, where getting patients in for their exams has always been a challenge. 

  • Screening compliance rates (as of 2021) were approximately 76% for breast cancer, 75% for cervical cancer, and 72% for colorectal cancer. 

But how does geography affect screening rates, and has progress been made over time? 

  • To answer these questions, researchers analyzed geographic variations in rates for the three major cancer screening tests (breast, cervical, and colorectal) over a 22-year period. 

Screening data were analyzed at the county level from 1997 to 2019, with screening prevalence estimated over 3-5-year periods. For mammography screening, authors found…

  • Screening rates were highest in the Northeast (Maine, New Hampshire, Vermont, and Massachusetts).
  • Rates were lowest in the Southwest (Texas, New Mexico, and Arizona).
  • Geographic areas that shifted from low to high uptake had lower socioeconomic status and more non-White residents, suggesting the success of efforts to improve screening in disadvantaged areas. 
  • Counties that did not improve had lower socioeconomic status than counties that maintained high screening rates. 
  • Rural areas had persistently low screening rates, reflecting lack of access to facilities as well as transportation. 

The Takeaway

The new study on geographic variation in cancer screening rates offers encouraging news that – at least in some disadvantaged areas – improving screening uptake is possible. But more research is needed to find out why some areas fail to see improvement. 

Perils of Missed Mammography

Posted on by Brian Casey

Yet another study is illustrating the perils of missing mammography screening. New research in JAMA Network Open found that women diagnosed with breast cancer who missed their previous screening exam had signs of delayed diagnosis and worse clinical outcomes. 

Mammography screening is generally credited – along with improved treatments – with a steady decline in breast cancer death rates since the start of population-based breast screening.

  • But most studies on mammography’s effectiveness tend to compare women who participated regularly in screening with those who never did. 

That’s not really a realistic comparison these days, as mammography’s relatively high compliance rate means that most women are getting screened at least some of the time.

  • But what happens if women miss a screening exam? In a BMJ study published last month, researchers found that women who missed their first screening exam had a 40% higher risk of breast cancer death.

In the current study, researchers took a slightly different tack, looking at 8.6k women in Sweden whose breast cancer was detected on screening exams starting in 2015. 

  • In all, 17% of women missed the screening exam immediately before their cancer diagnosis. 

Compared to women who attended all screening rounds, those who missed their previous exam had higher adjusted odds ratio for…

  • Larger tumors ≥ 20 mm (AOR = 1.55).
  • Lymph node involvement (AOR = 1.28).
  • Distant metastasis (AOR = 4.64).
  • Worse breast cancer-specific survival (AOR = 1.33).
  • Lower 20-year breast cancer-specific survival (86% vs. 89%). 

What’s more, the program’s cancer detection rate per 1k screenings was sharply higher in the second screening round for women who missed the first round (7.35 vs. 5.59). 

  • This is most likely a sign that cancers that could have been detected in the first round instead were detected in the second round – another sign of delayed diagnosis.

Women who had missed their previous screening tended to be younger, unemployed, unmarried, and born outside of Sweden, and also had lower income. 

  • Women with these characteristics could be targeted for more intensive outreach, such as shorter invitation intervals or outreach after a missed appointment. 

The Takeaway

The new study once again highlights the importance of regular mammography screening in detecting breast cancer. Even one missed exam can have serious clinical consequences – highlighting the importance of identifying and contacting women who might be more prone to missed appointments.

Missing Breast Screening Boosts Death Risk

Posted on by Brian Casey

Missing a first breast cancer screening exam can be hazardous to your health. A new study in BMJ found that women who missed their first mammography screening had a 40% higher long-term risk of breast cancer death. 

Mammography screening has been shown to prevent breast cancer deaths by detecting cancer earlier, when it can be treated more effectively.

  • But breast screening adherence rates still aren’t as high as they should be, leaving women’s health advocates to wonder what they can do to spur better compliance.

In the new study, researchers investigated whether mammography compliance itself could be an early warning sign that women might not be taking screening seriously enough.

  • They analyzed data on 433k women invited to the Swedish Mammography Screening Programme from 1991 to 2020 and correlated clinical outcomes over 25 years with whether or not patients completed their first screening exam (32% didn’t).

Compared to women who missed their first mammography appointment, women who followed through with their exam…

  • Had a 40% lower risk of dying from breast cancer. 
  • Had lower breast cancer mortality rates per 1k women (7 vs. 9.9). 
  • Got nearly twice as many breast screenings over the study period (8.7 vs. 4.8 screenings).
  • Had similar breast cancer incidence rates (7.8% vs. 7.6%), a sign that non-participation delayed detection rather than increased incidence. 

What’s more, women who missed their first appointment were 32% more likely to have invasive cancer and had higher odds ratios for stage III and stage IV disease (OR = 1.53 and 3.61, respectively). 

Researchers concluded that women who missed their first mammography appointment were also more likely to miss future ones – putting them at higher risk of breast cancer death.

  • But a missed initial appointment also could serve as a warning to women’s health centers that these patients deserve extra attention, through tools as simple as more provider outreach or automatically scheduled second appointments. 

The Takeaway

The new findings offer – yet again – more support for the effectiveness of population-based breast screening in reducing breast cancer deaths. What’s novel is that they show that non-participation is an early warning sign that could activate a slate of more aggressive outreach measures to bring these women in. 

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.

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.

How Do Patients Feel about Mammo AI?

Posted on by Brian Casey

As radiology moves (albeit slowly) to adopt clinical AI, how do patients feel about having their images interpreted by a computer? Researchers in a new study in JACR queried patients about their attitudes regarding mammography AI, finding that for the most part the jury is still out. 

Researchers got responses to a 36-question survey from 3.5k patients presenting for breast imaging at eight U.S. practices from 2023-2024, finding …

  • The most common response to four questions on general perceptions of medical AI was “neutral,” with a range of 43-51%. 
  • When asked if using AI for medical tasks was a bad idea, more patients disagreed than agreed (28% vs. 25%). 
  • Regarding confidence that medical AI was safe, patients were more dubious, with higher levels of disagreement (27% vs. 20%).
  • When asked if medical AI was helpful, 43% were neutral but positive attitudes were higher (35% vs. 19%).

The Takeaway

Much like clinicians, patients seem to be taking a wait-and-see attitude toward mammography AI. The new survey does reveal fault lines – like privacy and equitability – that AI developers would do well to address as they work to win broader acceptance for their technology. 

We’re testing a new format today – let us know if you prefer two shorter Top Stories or one longer Top Story with this quick survey!

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

This content is exclusive to subscribers

Log in or join by entering your email below.

Completely free. Every Monday and Thursday