An MGH and Harvard Medical team developed a multimodal ultrasound AI platform that applies an interesting mix of AI techniques to accurately detect and stage thyroid cancer, potentially improving diagnosis and treatment planning.
The Platform – The platform combines radiomics, topological data analysis (TDA), ML-based TI-RADS assessments, and deep learning, allowing them to capture more data, minimize noise, and improve prediction accuracy.
The Study – Starting with 1,346 ultrasound images from 784 patients, the researchers trained the multimodal AI platform with 362 nodules (103 malignant) and validated it against a pair of internal (51 malignant, 98 benign) and external (270 malignant, 50 benign) datasets, finding that:
- The platform predicted 98.7% of internal dataset malignancies (0.99 AUC)
- The platform predicted 91.4% of external dataset malignancies (0.94 AUC)
- The individual AI methods were far less accurate (80% to 89% w/ internal)
- A version of the platform accurately predicted nodal pathological stages (93% for T-stage, 89% for N-stage, 98% for extrathyroidal extension)
- The platform predicted BRAF mutations with 96% accuracy
Next Steps – The researchers plan to validate their multimodal platform in prospective multicenter clinical trials, including in low-resource countries where it might be particularly helpful.
We cover plenty of ultrasound AI and thyroid cancer imaging studies, but this team’s multi-AI approach is unique and appears promising. A multimodal AI platform like this might make thyroid cancer diagnosis more efficient and less subjective, avoid unnecessary biopsies, allow non-invasive staging and mutation assessment, and lead to more personalized treatments. That would be a major accomplishment, and might suggest that similar multimodal AI platforms could be developed for other cancers and imaging modalities.
A thought-provoking JACR editorial by Emory’s Hari Trivedi MD suggests that AI’s slow adoption rate has little to do with its quality or clinical benefits, and a lot to do with radiology’s misaligned incentives.
After interviewing 25 clinical and industry leaders, the radiology professor and co-director of Emory’s HITI Lab detailed the following economic mismatches:
- Private Practices value AI that improves radiologist productivity, allowing them to increase reading volumes without equivalent increases in headcount. That makes triage or productivity-focused AI valuable, but gives them no economic justification to purchase AI that catches incidentals, ensures follow-ups, or reduces unnecessary biopsies.
- Academic centers or hospitals that own radiology groups have far more to gain from AI products that detect incidental/missed findings and then drive internal admissions, referrals, and procedures. That means their highest-ROI AI solutions often drive revenue outside of the radiology department, while creating more radiologist labor.
- Community hospital emergency departments value AI that allows them to discharge or treat emergency patients faster, although this often doesn’t economically benefit their radiology departments or partner practices.
- Payor/provider health systems (e.g. the VA, Intermountain, Kaiser) can be open to a broad range of AI, but they especially value AI that reduces costs by avoiding unnecessary tests or catching early signs of diseases.
People tend to paint imaging AI with a wide brush (AI is… all good, all bad, a job stealer, or the future) and we’ve seen a similar approach to AI adoption barrier editorials (AI just needs… trust, reimbursements, integration, better accuracy, or the killer app). However, even if each of these adoption barriers are solved, it’s hard to see how AI could achieve widespread adoption if the groups paying for AI aren’t economically benefiting from it.
Because of that, Dr. Trivedi encourages vendors to develop AI that provides “returns” to the same groups that make the “investments.” That might mean that few AI products achieve widespread adoption on their own, but a diverse group of specialized AI products achieve widespread use across all radiology settings.
Sirona Medical announced its acquisition of Nines’ AI assets and personnel, representing notable milestones for Sirona’s integrated RadOS platform and the quickly-changing imaging AI landscape.
Acquisition Details – Sirona acquired Nines’ AI portfolio (data pipeline, ML engines, workflow/analytics tools, AI models) and key team members (CRO, Direct of Product, AI engineers), while Nines’ teleradiology practice was reportedly absorbed by one of its telerad customers. Terms of the acquisition weren’t disclosed, although this wasn’t a traditional acquisition considering that Sirona and Nines had the same VC investor.
Sirona’s Nines Strategy – Sirona’s mission is to streamline radiologists’ overly-siloed workflows with its RadOS radiology operating system (unifies: worklist, viewer, reporting, AI, etc.), and it’s a safe bet that any acquisition or investment Sirona makes is intended to advance this mission. With that…
- Nine’s most tangible contributions to Sirona’s strategy are its FDA-cleared AI models: NinesMeasure (chest CT-based lung nodule measurements) and NinesAI Emergent Triage (head CT-based intracranial hemorrhage and mass effect triage). The AI models will be integrated into the RadOS platform, bolstering Sirona’s strategy to allow truly-integrated AI workflows.
- Nine’s personnel might have the most immediate impact at Sirona, given the value/scarcity of experienced imaging software engineers and the fact that Nines’ product team arguably has more hands-on experience with radiologist workflows than any other imaging AI firm (at least AI firms available for acquisition).
- Nine’s other AI and imaging workflow assets should also help support Sirona’s future RadOS and AI development, although it’s harder to assess their impact for now.
The AI Shakeup Angle – This acquisition has largely been covered as another example of 2022’s AI shakeup, which isn’t too surprising given how active this year has been (MaxQ’s shutdown, RadNet’s Aidence/Quantib acquisitions, IBM shedding Watson Health). However, Nines’ strategy to combine a telerad practice with in-house AI development was quite unique and its decision to sell might say more about its specific business model (at its scale) than it does about the overall AI market.
Since the day Sirona emerged from stealth, it’s done a masterful job articulating its mission to solve radiology’s workflow problems by unifying its IT infrastructure. Acquiring Nines’ AI assets certainly supports Sirona’s unified platform messaging, while giving it more technology and personnel resources to try to turn that message into a reality.
Meanwhile, Nines becomes the latest of surely many imaging AI startups to be acquired, pivoted, or shut down, as AI adoption evolves at a slower pace than some VC runways. Nines’ strategy was really interesting, they had some big-name founders and advisors, and now their work and teams will live on through Sirona.
A Stanford AIMI and Microsoft Healthcare team just took a step towards addressing imaging AI’s looming drift problem, unveiling their CheXstray drift detection system.
Imaging AI’s Drift Problem – The list of FDA-cleared imaging AI products continues to grow and we’re getting better at AI deployment. However, there’s no reasonable way to monitor how imaging AI models adapt to their constantly changing data environments (tech, vendors, protocols, patient & disease mix, etc.) or whether the models change on their own.
The CheXstray Solution – The team used a pair of public CXR datasets (n = 224k & 160k CXRs) to train/test the CheXstray solution to automatically detect drift by calculating a range of multi-modal inputs (DICOM metadata, image appearance, clinical workflows) and model performance.
CheXstray Results – Initial experiments showed that the automated CheXstray workflows rivaled ground truth audits for drift detection, essentially achieving the workflow’s proof-of-concept goal.
Automation Alternatives – Until we have automated monitoring solutions like CheXstray, AI vendors and radiology departments might have to rely on ongoing audits (requiring test set curation, labeling, analytics, etc.) and/or asking radiologists to provide ongoing model feedback. Unfortunately, those options undermine AI’s intended labor-reducing value proposition. Plus, radiologists have already made it quite clear that they don’t think monitoring should be their responsibility (and regulators might agree).
We haven’t solved imaging AI’s drift monitoring problem yet, and there will be other hurdles to overcome before we see a solution like this achieve clinical adoption (more research, regulatory changes, new modalities, training without massive public datasets). Still, the CheXstray team just showed how imaging AI performance could be automatically monitored in real-time. That’s an important step in imaging AI’s evolution, and it might prove to be critical as more hospitals head into the 2nd or 3rd years after their “successful” AI deployments.
A new Radiology: Artificial Intelligence study out of Switzerland highlighted how Aidoc’s Intracranial Hemorrhage AI solution improved emergency department workflows, without hurting patient care. Even if that’s exactly what solutions like this are supposed to do, real world AI studies that go beyond sensitivity and specificity are still rare and worth some extra attention.
The Study – The researchers analyzed University Hospital of Basel’s non-contrast CT intracranial hemorrhage (ICH) exams before and after adopting the Aidoc ICH solution (n = 1,433 before & 3,017 after; ~14% ICH incidence w/ both groups).
Diagnostic Results – The Aidoc solution produced “practicable” overall diagnostic results (93% accuracy, 87.2% sensitivity, 93.9% specificity, and 97.8% NPV), although accuracy was lower with certain ICH subtypes (e.g. subdural hemorrhage 69.2%, 74/107).
Efficiency Results – More notably, the Aidoc ICH solution “positively impacted” UBS’ ED workflows, with improvements across a range of key metrics:
- Communicating critical findings: 63 vs. 70 minutes
- Communicating acute ICH: 58 vs. 73 minutes
- Overall turnaround time to rule out ICH: 164 vs. 175 minutes
- Turnaround time to rule out ICH during working hours: 167 vs. 205 minutes
Next Steps – The authors called for further efforts to streamline their stroke workflows and to create a clear ICH AI framework, accurately noting that “AI tools are only as reliable as the environment they are deployed in.”
The internet hasn’t always been kind to emergency AI tools, and academic studies have rarely focused on the workflow efficiency outcomes that many radiologists and emergency teams care about. That’s not the case with this study, which did a good job showing the diagnostic and workflow upsides of ICH AI adoption, and added a nice reminder that imaging teams share responsibility for AI outcomes.
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 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.
Three independent radiology practices just merged with the goal of better serving their shared client, Trinity Health, representing an interesting example of how private rad groups can adapt to hospital and practice consolidation.
Becoming AIA – Michigan’s Huron Valley Radiology (54 radiologists), Indiana’s X-Ray Consultants (11 rads), and Connecticut’s Naugatuck Valley Radiological Associates (11 rads) will now become Advanced Imaging Alliance (AIA). Although technically a corporation, AIA is wholly owned by the groups’ physician shareholders, and will continue to operate as three separate divisions.
Trinity’s Consolidation – Trinity Health itself was created by the 2000 merger of the Holy Cross Health System (Indiana) and Mercy Health Services (Michigan), before acquiring St. Mary’s Hospital (Connecticut) in 2015 and eventually expanding to 89 hospitals in 25 states. Trinity’s expansion is what motivated the three groups to merge, allowing them to provide “a single level” of service for their shared client.
Consolidation Options – Mergers like this could represent a viable option for rad groups looking to remain independent and competitive, allowing them to better support multi-state hospital clients, while giving them workforce advantages (more subspecialists, shared overnight coverage) and better administrative / IT scale.
It appears that the trends towards multi-state hospital systems and expanding PE-backed radiology groups are here to stay, creating challenges for private radiology practices that have thrived on local relationships. That doesn’t mean that we’ll see a major trend towards three-practice mergers, but these mergers might make sense for some practices in similar situations.
UnitedHealthcare continued its war against imaging costs, introducing its new Designated Diagnostic Provider program. This program is built to drive more exams through providers that meet UnitedHealthcare’s definition of quality and cost, and could have a big impact on its imaging partners.
Designated Criteria – Hospital outpatient and freestanding imaging centers that are contracted with UHC to provide advanced imaging (MRI, CT, PET, MRA, nuclear) must apply to receive Designated Diagnostic Provider status. Imaging providers who don’t meet UHC’s cost / quality criteria will be instructed to make specific improvements or settle for “non-Designated” status (they’ll still be in-network).
Patient Incentives – UnitedHealthcare patients referred for advanced imaging will be automatically sent to Designated Diagnostic Providers, and will face far higher co-pays if they somehow find a non-Designated imaging center (e.g., $680 vs. $290 for a CT).
Designated Dilemma – UnitedHealthcare’s contracted imaging providers will now either have to adopt what are surely UHC-friendly policies, or brace for a lot less UHC patients. These Non-Designated Providers would also have to be okay with charging UHC patients far higher co-pays than if they went to a Designated Provider.
UHC’s Outpatient Push – UnitedHealthcare has been aggressively shifting patients away from hospitals and towards outpatient imaging centers for quite a while, and this latest move ensures that most of these outpatient exams will happen at its preferred imaging centers.
One of the ways UnitedHealth Group achieved its massive growth was by steering patients to the highest-value procedures and treatments. The new Designated Diagnostic Provider program seems like a very effective way to apply that strategy to medical imaging coverage, even if many imaging providers might not like it.