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
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.
So AI dominated the discussion at last week’s RSNA 2023 meeting. But does that mean it’s finally on the path to widespread clinical use?
Maybe not so much. For a technology that’s supposed to have a revolutionary impact on medicine, AI is taking a frustratingly long time to arrive.
Indeed, there was plenty of skepticism about AI in the halls of McCormick Place last week. (For two interesting looks at AI at RSNA 2023, also see Hugh Harvey, MD’s list of takeaways in a post on X/Twitter and Herman Oosterwijk’s post on LinkedIn.)
But as one executive we talked to pointed out, AI’s advance to routine clinical use in radiology is likely to be more incremental than all at once.
- And from that perspective, last week’s RSNA meeting was undoubtedly positive for AI. Scientific sessions were full of talks on practical clinical applications of AI, from breast AI to CT lung screening.
Researchers also discussed the use of AI apart from image interpretation, with generative AI and large language models taking on tasks from answering patient questions about their reports to helping radiologists with dictation.
It’s fine to be a skeptic (especially when it comes to things you hear at RSNA), but for perspective look at many of the past arguments casting doubt on AI:
- AI algorithms don’t have FDA clearance (the FDA authorized 171 algorithms in just the past year)
- You can’t get paid for using AI clinically (16 algorithms have CPT codes, with more on the way)
- There isn’t enough clinical evidence backing the use of AI (tell that to the authors of MASAI, PERFORMS, and a number of other recent studies with positive findings)
- The AI market is overcrowded with companies and ripe for consolidation (what exciting new growth market isn’t?)
Sure, it’s taking longer than expected for AI to take hold in radiology. But last week’s conference showed that AI’s incremental revolution is not only advancing but expanding in ways no one expected when IBM Watson was unveiled to an RSNA audience a mere 6-7 years ago. One can only imagine what the field will look like at RSNA 2030.
Looking for more coverage of RSNA 2023? Be sure to check out our videos from the technical exhibit floor, which you can find on our new Shows page.
Take a deep breath. You survived another RSNA conference.
While a few hardy souls are still enjoying educational sessions in the cozy confines of McCormick Place, the final day of the exhibit floor yesterday marks the end of RSNA 2023 for most attendees. And what a show it was.
Predictions were that AI would dominate the scientific sessions at RSNA 2023, a forecast that largely panned out. A November 28 session was a case in point, in which a series of top-quality papers were presented on one of the most promising use cases of AI, for breast screening:
- A homegrown AI algorithm that analyzed screening breast ultrasound exams in addition to FFDM and DBT mammograms boosted sensitivity for detecting cancer in 12.5k patients, with better sensitivity for women with dense breasts (71% vs. 60%) and non-dense breasts (79% vs. 63%)
- AI did a good job of detecting breast arterial calcification (BAC) when used prospectively to analyze screening mammograms in 16k women across 15 sites. It found 15% of women had BAC, a possible marker for atherosclerotic disease
- Swedish researchers used their VAI-B validation platform to compare three AI algorithms (Therapixel, Lunit, and Vara) in 34k women, finding that using AI with a single radiologist boosted sensitivity 10-30% compared to double reading, with a slight loss in specificity (2-7%). VAI-B could be used to validate AI implementation and guide purchasing decisions
- Why does AI miss some breast cancers? South Korean researchers addressed this question by analyzing 1.1k patients with invasive cancers in which AI had a miss rate of 14%. Luminal cancers were missed most often
- Adding AI analysis of prior images to current studies with FFDM and DBT boosted sensitivity for cancer detection in 30k patients, with sensitivity the highest for two years of priors compared to no priors (74% vs. 70%)
This week’s research points to an exciting near-term future in which AI will help make mammography screening more accurate while helping breast radiologists perform their jobs more efficiently. Landmark studies toward this end were published in 2023 – this week’s RSNA conference shows that we can expect the momentum to continue in 2024.