Tag: cancer screening

How to Improve CT Lung Cancer Screening

Posted on by Brian Casey

As the US grapples with low CT lung cancer screening rates, researchers and clinicians around the world are pressing ahead with ways to make the exam more effective – especially in countries with high smoking rates. Two new studies published this week show the progress that’s being made.

In Brazil, researchers in JAMA Network Open found that using broader criteria to determine who should get CT lung screening not only expanded the eligible population, but it also reduced racial disparities in screening’s effectiveness. 

Researchers compared three strategies for determining screening eligibility: two based on 2013 and 2021 USPSTF criteria, and one in which all ever-smokers ages 50-80 were screened, finding: 

  • Screening all ever-smokers generated the largest possible screening population (27.3M people) compared to USPSTF criteria for 2013 (5.1M) and 2021 (8.4M)
  • Number of life-years gained if lung cancer is averted due to screening was highest with all-screening (23 vs. 19 & 21)
  • But the all-screening strategy also had the highest number needed to screen to prevent one lung cancer death (472 vs 177 & 242)
  • The USPSTF 2021 criteria reduced (but did not eliminate) racial disparities; the USPSTF 2013 criteria produced the greatest disparity 

The authors said the results showed that CT lung cancer screening in Brazil could identify 57% of preventable lung cancer deaths if 22% of ever-smokers are screened. Their study should help the country decide which screening strategy to adopt. 

In a second paper in the same journal, researchers from China described how they performed CT lung cancer screening via opportunistic screening, offering low-dose CT scans to patients visiting their doctor for other reasons, such as a routine checkup or a health problem other than a pulmonary issue. Among 5.2k patients, researchers found that people who got opportunistic LDCT screening had:

  • 49% lower risk of lung cancer death by hazard ratio
  • 46% lower risk of all-cause mortality
  • 43% received their lung cancer diagnosis through opportunistic screening

The Takeaway

This week’s studies continue the positive progress toward CT lung cancer screening that’s being made around the world. Both offer different strategies for making screening even more effective, and add to the growing weight of evidence in favor of population-based lung screening.

AI Powers Opportunistic Screening

Posted on by Brian Casey

The growing power of AI is opening up new possibilities for opportunistic screening – the detection of pathology using data acquired for other clinical indications. The potential of CT-based opportunistic screening – and AI’s role in its growth – was explored in a session at RSNA 2023.

What’s so interesting about opportunistic screening with CT? 

  • As one of imaging’s most widely used modalities, CT scans are already being acquired for many clinical indications, collecting body composition data on muscle, fat, and bone that can be biomarkers for hidden pathology. 

What’s more, AI-based tools are replacing many of the onerous manual measurement tasks that previously required radiologist involvement. There are four primary biomarkers for opportunistic screening, which are typically related to several major pathologies, said Perry Pickhardt, MD, of the University of Wisconsin-Madison, who led off the RSNA session:

  • Skeletal muscle density (sarcopenia)
  • Hard calcified plaque, either coronary or aortic (cardiovascular risk)
  • Visceral fat (cardiovascular risk)
  • Bone mineral density (osteoporosis and fractures) 

But what about the economics of opportunistic screening? 

  • A recent study in Abdominal Radiology found that in a hypothetical cohort of 55-year-old men and women, AI-assisted opportunistic screening for cardiovascular disease, osteoporosis, and sarcopenia was more cost-effective compared to both “no-treatment” and “statins for all” strategies – even assuming a $250/scan charge for use of AI.

But there are barriers to opportunistic screening, despite its potential. In a follow-up talk, Arun Krishnaraj, MD, of UVA Health in Virginia said he believes fully automated AI algorithms are needed to avoid putting the burden on radiologists. 

And the regulatory environment for AI tools is complex and must be navigated, said Bernardo Bizzo, MD, PhD, of Mass General Brigham.

Ready to take the plunge? The steps for setting up a screening program using AI were described in another talk by John Garrett, PhD, Pickhardt’s colleague at UW-Madison. This includes: 

  • Normalizing your data for AI tools
  • Identifying the anatomical landmarks you want to focus on
  • Automatically segmenting areas of interest
  • Making the biomarker measurements
  • Plugging your data into AI models to predict outcomes and risk-stratify patients

The Takeaway

Opportunistic screening has the potential to flip the script in the debate over radiology utilization, making imaging exams more cost-effective while detecting additional pathology and paving the way to more personalized medicine. With AI’s help, radiologists have the opportunity to place themselves at the center of modern healthcare. 

Making Screening Better

Posted on by Brian Casey

While population-based cancer screening has demonstrated its value, there’s no question that screening could use improvement. Two new studies this week show how to improve on one of screening’s biggest challenges: getting patients to attend their follow-up exams.

In the first study in JACR, researchers from the University of Rochester wanted to see if notifying people about actionable findings shortly after screening exams had an impact on follow-up rates. Patients were notified within one to three weeks after the radiology report was completed. 

They also examined different methods for patient communication, including snail-mail letters, notifications from Epic’s MyChart electronic patient portal, and phone calls. In approximately 2.5k patients within one month of due date, they found that follow-up adherence rates varied for each outreach method as follows:

  • Phone calls – 60%
  • Letters – 57%
  • Controls – 53%
  • MyChart notifications – 36%

(The researchers noted that the COVID-19 pandemic may have disproportionately affected those in the MyChart group.) 

Fortunately, the university uses natural language processing-based software called Backstop to make sure no follow-up recommendations fall through the cracks. 

  • Backstop includes Nuance’s mPower technology to identify actionable findings from unstructured radiology reports; it triggers notifications to both primary care providers and patients about the need to complete follow-up.

Once the full round of Backstop notifications had taken place, compliance rates rose and there was no statistically significant difference between how patients got the early notification: letter (89%), phone (91%), MyChart (90%), and control (88%). 

In the second study, researchers in JAMA described how they used automated algorithms to analyze EHR data from 12k patients to identify those eligible for follow-up for cancer screening exams.

  • They then tested three levels of intervention to get people to their exams, ranging from EHR reminders to outreach to patient navigation to all three. 

Patients who got EHR reminders, outreach, and navigation or EHR reminders and outreach had the highest follow-up completion rates at 120 days compared to usual care (31% for both vs. 23%). Rates were similar to usual care for those who only got EHR reminders (23%).

The Takeaway

This week’s studies indicate that while health technology is great, it’s how you use it that matters. While IT tools can identify the people who need follow-up, it’s up to healthcare personnel to make sure patients get the care they need.

Mammography AI’s Leap Forward

Posted on by Brian Casey

A new study out of Sweden offers a resounding vote of confidence in the use of AI for analyzing screening mammograms. Published in The Lancet Oncology, researchers found that AI cut radiologist workload almost by half without affecting cancer detection or recall rates.

AI has been promoted as the technology that could save radiology from rising imaging volumes, growing burnout, and pressure to perform at a higher level with fewer resources. But many radiology professionals remember similar promises made in the 1990s around computer-aided detection (CAD), which failed to live up to the hype.

Breast screening presents a particular challenge in Europe, where clinical guidelines call for all screening exams to be double-read by two radiologists – leading to better sensitivity but also imposing a higher workload. AI could help by working as a triage tool, enabling radiologists to only double-read those cases most likely to have cancer.

In the MASAI study, researchers are assessing AI for breast screening in 100k women in a population-based screening program in Sweden, with mammograms being analyzed by ScreenPoint’s Transpara version 1.7.0 software. In an in-progress analysis, researchers looked at results for 80k mammography-eligible women ages 40-80. 

The Transpara software applies a 10-point score to mammograms; in MASAI those scored 1-9 are read by a single radiologist, while those scored 10 are read by two breast radiologists. This technique was compared to double-reading, finding that:

  • AI reduced the mammography reading workload by almost 37k screening mammograms, or 44%
  • AI had a higher cancer detection rate per 1k screened participants (6.1 vs. 5.1) although the difference was not statistically significant (P=0.052)
  • Recall rates were comparable (2.2% vs. 2.0%)

The results demonstrate the safety of using AI as a triage tool, and the MASAI researchers plan to continue the study until it reaches 100k participants so they can measure the impact of AI on detection of interval cancers – cancers that appear between screening rounds.

The Takeaway

It’s hard to overestimate the MASAI study’s significance. The findings strongly support what AI proponents have been saying all along – that AI can save radiologists time while maintaining diagnostic performance. The question is the extent to which the MASAI results will apply outside of the double-reading environment, or to other clinical use cases.

Cancer Moonshot

Posted on by Jake Fishman

The Biden administration “reignited” the US’ Cancer Moonshot initiative, setting a goal to halve the country’s age-adjusted cancer death rate within the next 25 years. Here’s how they plan to achieve this “Moonshot” of a goal, and what that means for imaging.

Cancer Moonshot History – Biden spearheaded the Obama administration’s Cancer Moonshot initiative, inspired by losing his son to brain cancer. The 7-year initiative used $1.8B in federal funding to improve cancer therapeutics, prevention, and detection through scientific discovery, collaboration, and data sharing.

The Reignited Moonshot – The revamped initiative inherits these same goals and approaches, while adding new focus areas and operational structures:

  • Overcoming the COVID pandemic’s cancer screening backlog
  • Addressing inequity in cancer incidence, detection, and care
  • Developing new treatments for rare and childhood cancers
  • Fast-tracking the development of multi-cancer tests
  • Improving the experience of cancer survivors and caregivers
  • Leveraging data to “turn our cancer care system into a learning system”
  • Creating a cancer research funding program modeled after DARPA
  • Appointing federal Cancer Moonshot leaders to coordinate this work

Imaging Alignment – Any government attempt to overcome cancer screening backlogs and to make early detection mainstream would surely result in more imaging, while the Moonshot initiative’s focus on “learning from data” could hold imaging AI upsides. That said, the announcement placed a much brighter spotlight on non-imaging areas (blood tests, vaccines, treatments), and few people on the clinical side of radiology believe more imaging is necessarily better for patients.

Moonshot Critics – The Cancer Moonshot initiative has its fair share of critics, who argued that cutting cancer deaths by 50% would require “curing” cancer (not just catching and treating it), expanding screening has downsides (radiation, unnecessary treatments), and that initiatives like this are largely done for appearances.

The Takeaway
The White House just made the fight against cancer a top administrative priority, meaning that a lot more government attention and resources are on the way, and notable changes in cancer imaging policies and volumes might follow.

Creating a Cancer Screening Giant

Posted on by Jake Fishman

A few days after shocking the AI and imaging center industries with its acquisitions of Aidence and Quantib, RadNet’s Friday investor briefing revealed a far more ambitious AI-enabled cancer screening strategy than many might have imagined.

Expanding to Colon Cancer – RadNet will complete its AI screening platform by developing a homegrown colon cancer detection system, estimating that its four AI-based cancer detection solutions (breast, prostate, lung, colon) could screen for 70% of cancers that are imaging-detectable at early stages.

Population Detection – Once its AI platform is complete, RadNet plans to launch a strategy to expand cancer screening’s role in population health, while making prostate, lung, and colon cancer screening as mainstream as breast cancer screening.

Becoming an AI Vendor – RadNet revealed plans to launch an externally-focused AI business that will lead with its multi-cancer AI screening platform, but will also create opportunities for RadNet’s eRAD PACS/RIS software. There are plenty of players in the AI-based cancer detection arena, but RadNet’s unique multi-cancer platform, significant funding, and training data advantage would make it a formidable competitor.

Geographic Expansion – RadNet will leverage Aidence and Quantib’s European presence to expand its software business internationally, as well as into parts of the US where RadNet doesn’t own imaging centers (RadNet has centers in just 7 states).

Imaging Center Upsides – RadNet’s cancer screening AI strategy will of course benefit its core imaging center business. In addition to improving operational efficiency and driving more cancer screening volumes, RadNet believes that the unique benefits of its AI platform will drive more hospital system joint ventures.

AI Financials – The briefing also provided rare insights into AI vendor finances, revealing that DeepHealth has been running at a $4M-$5M annual loss and adding Aidence / Quantib might expand that loss to $10M- $12M (seems OK given RadNet’s $215M EBITDA). RadNet hopes its AI division will become cash flow neutral within the next few years as revenue from outside companies ramp up.

The Takeaway

RadNet has very big ambitions to become a global cancer screening leader and significantly expand cancer screening’s role in society. Changing society doesn’t come fast or easy, but a goal like that reveals how much emphasis RadNet is going to place on developing and distributing its AI cancer screening platform going forward.

RadNet’s Big AI Play

Posted on by Jake Fishman

Imaging center giant RadNet shocked the AI world this week, acquiring Dutch startups Aidence and Quantib to support its AI-enabled cancer screening strategy.

Acquisition Details – RadNet acquired Aidence for $40M-$50M and Quantib for $45M, positioning them alongside DeepHealth within its new AI division. Aidence’s Veye Lung Nodules solution (CT lung nodule detection) is used across seven European countries and has been submitted for FDA 510(k) clearance, while Quantib’s prostate and brain MRI solutions have CE and FDA clearance and are used in 20 countries worldwide.

RadNet’s Cancer Screening Strategy – RadNet sees a huge future for cancer screening and believes Aidence (lung cancer) and Quantib (prostate cancer) will combine with DeepHealth (breast cancer) to make it a population health screening leader. 

RadNet’s AI Screening History – Even if these acquisitions weren’t expected, they aren’t out of character for RadNet, which created its mammography AI portfolio through a series of 2019-2020 acquisitions (DeepHealth, Nulogix) and equity investments (WhiteRabbit.ai). Plus, acquisitions have been a core part of RadNet’s imaging center strategy since before we were even talking about AI.

Unanswered Questions – It’s still unclear whether RadNet will take advantage of Aidence / Quantib’s European presence to expand internationally or if RadNet will start selling its AI portfolio to other hospitals and imaging center chains.

Another Consolidation Milestone – All those forecasts of imaging AI market consolidation seem to be quickly coming true in 2022, following MaxQ’s pivot out of imaging and RadNet’s Aidence / Quantib acquisitions. It’s also becoming clearer what type of returns AI startups and VCs are willing to accept, as Aidance and Quantib sold for about 3.5-times and 5.5-times their respective venture funding ($14M & $8M) and Nanox acquired Zebra-Med for 1.7 to 3.5-times its VC funding ($57.4M).

The Takeaway

It seems that RadNet will leverage its newly-expanded AI portfolio to become the US’ premier cancer screening company. That would be a huge accomplishment if cancer screening volumes grow as RadNet is forecasting. However, RadNet’s combination of imaging AI expertise, technology, funding, and training data could allow it to have an even bigger impact beyond the walls of its imaging centers.

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!