This year’s variability reminder from Penn Medicine radiologist, Saurabh Jha, MD.

Imaging Wire Sponsors

annalise.ai  •  Arterys  •  Bayer  •  Blackford  •  Canon Medical  •  CARPL.ai  •  Change Healthcare  •  Enlitic  •  GE Healthcare  •  Hyperfine  •  Intelerad  •  Novarad  •  Riverain Technologies  •  Siemens Healthineers  •  United Imaging  •  Us2.ai

Check out the latest Imaging Wire Show with United Imaging’s Jeffrey Bundy and Mike Coulter, who detail their unique approach to medical imaging innovations. If you’re trying to figure out a simpler and more scalable way to run your imaging organization, this interview is a great way to start.

Artificial Intelligence

Annalise.ai Gets ‘Comprehensive’ with Enterprise CTB

Annalise.ai doubled-down on its comprehensive AI strategy with the launch of its Annalise Enterprise CTB solution, which identifies a whopping 130 different non-contrast brain CT findings. 

Initially available for clinical use in the UK, Australia, and New Zealand, Annalise Enterprise CTB analyzes brain CTs as they are acquired, prioritizes urgent cases, and provides radiologists with details on each finding (types, locations, likelihood).  

If this sounds familiar, it’s because Annalise.ai’s original Enterprise CXR solution identifies 124 different chest X-ray findings, with previous clinical studies showing that it improves radiologists’ detection accuracy, diagnostic decision making, and reporting speed. 

We’re also seeing a (less-extreme) push towards comprehensive AI from other vendors, as Qure.ai’s brain CT solution detects 11 findings and a growing field of chest X-ray AI vendors lead with their ability to detect multiple findings (also Lunit, Qure.ai, Oxipit, Vuno).

The Takeaway

Whether Annalise.ai’s 10x-larger list of findings results in a similar performance advantage will be decided in the clinic, but Annalise Enterprise CTB and CXR (and any future solutions) should go a long way towards supporting radiology teams who want to improve their detection performance without patching together multiple “narrow AI” solutions .

Windsong’s Case for MEDRAD Stellant FLEX CT

Learn how Windsong Radiology Group used Bayer’s MEDRAD Stellant FLEX CT injection system to drive efficiencies and standardization across its imaging centers.

Leveraging Pediatric Imaging AI

Check out this Blackford Analysis white paper detailing how children’s hospital imaging teams can leverage AI to improve modality throughput and imaging device availability.

The Wire

• FAPI PET/CT Predicts Sudden Cardiac Death: A new Radiology study found that FAPI PET/CT radiotracer uptake can be used to identify hypertrophic cardiomyopathy (HCM) patients who have greater risk of sudden cardiac death. The researchers performed 18F-FAPI PET/CT imaging on 50 HCM patients and 22 healthy controls, finding that the HCM patients all had higher FAPI myocardial activity (8.8 vs. 2.1 median target-to-background ratio). HCM patients’ degree of FAPI activity was also directly correlated with higher 5-year sudden cardiac death risks (P = .03).

• GE Spinoff Advances: GE HealthCare continued its progress towards its early 2023 spinoff, filing its F-10 registration statement with the SEC. GE HealthCare will remain headquartered in Chicago, and will include businesses responsible for $17.6B in annual revenue, while inheriting $15B of GE’s debt. GE HealthCare will operate through four business segments (Imaging, Ultrasound, Patient Care, Pharmaceutical Diagnostics), while following a strategic plan that focuses on innovation, product and commercial execution leadership, and a simplified and more decentralized operating model

• Marrying Breast and Lung Cancer Screening: A recent JAMA commentary outlined the case for “marrying” lung cancer and breast cancer screening, by using mammography screening appointments to assess women’s lung cancer risk and educate them about screening options. The authors noted that breast cancer screenings are more frequently recommended by doctors and attended by patients, suggesting that this integration would improve lung cancer screening recruitment and detection.

• More Imaging Cyberattacks: Last week brought two more imaging provider cyberattack announcements, this time revealing breaches at Windsong Radiology’s Buffalo MRI branch (Western NY, December 2021) and Cardiac Imaging Associates (Los Angeles, April 2022). At least 12 US radiology practices and imaging centers have disclosed security incidents since the start of 2021, including five announcements in the last two months, a trend that might increase as hackers reportedly shift their focus to smaller “specialty clinics.”

• GE’s Contrast Supply Reinforcements: GE Healthcare announced a multi-year iodine supply agreement with Chilean mining company, SQM, and the opening of its new $30M imaging contrast production facility in Ireland. The announcement comes in the wake of 2022’s pandemic-driven iodinated contrast shortage and will support GE’s goal to increase its annual iodinated contrast media production by 30M additional patient doses by 2025.

• Inaccurate Saliency Maps: A new study in Nature confirmed what many in radiology AI already believed: saliency maps can’t accurately locate pathology in medical images and therefore shouldn’t be used to explain AI decision making (yet, anyway). Researchers compared the accuracy of seven widely used saliency methods to identify pathologies associated with 10 common CXR conditions, finding that the saliency tools consistently performed “significantly worse” than human radiologists. 

• Rhino Health’s Federated Funding: Federated learning developer Rhino Health added $6.7M to its seed round (total funding now $11.7M) that it will use to further develop its multi-institution/site AI development platform. Rhino Health is currently collaborating with dozens of medical centers and organizations who are applying its federated learning solution across disciplines.

• Healthcare Hiring Recovery: The September Jobs Report revealed that the healthcare sector has now fully recovered the 1.4M jobs lost early in the pandemic, adding 60k jobs throughout last month. Ambulatory services and hospitals added 28k workers each, while other gains came primarily from physician offices and home healthcare services.

• United Imaging’s Installation Milestone: United Imaging just shipped a trio of imaging systems to new Manhattan-based imaging center, AMRIC, allowing the OEM to surpass 20,000 global scanner installations (up from 8.5k 2.5yrs ago). AMRIC will operate United Imaging’s uMR OMEGA MRI, uCT ATLAS CT, and uMI 550 PET/CT systems when the new preventive and diagnostic imaging clinic opens its doors.

• Google’s Fetal Ultrasound AI: A Google Health-led study highlighted a fetal ultrasound AI model that significantly improved assessments performed using lower-cost handheld ultrasound systems and by novice operators. The AI model produced accurate gestational age estimates using exams from both standard ultrasound and handheld POCUS systems, when performed by both sonographers (difference from biometry age: −1.4 & −0.6 days) and midwives (−0.4 & 0.4 days). The AI model also predicted fetal malpresentation with similar accuracy using exams based on standard and handheld ultrasounds (AUROCs: 0.980 & 0.970) and performed by sonographers and midwives (AUROCs: 0.992 & 0.972).

• 5C Network Raises $4.6M: Indian teleradiology company 5C Network secured $4.6M in Series A funding to expand its team and radiologist network, grow its client base, and further develop its diagnostic platform. 5C Network’s unique patient management capabilities (exam scheduling, imaging delivery), large network of imaging centers (334 cities in 34 states) and radiologists (>500 rads), and AI-integrated platform reportedly make it particularly scalable.

• FDA Digital Health Policy Navigator: The FDA’s recently released regulatory guidance just became a lot more digestible after the agency debuted an extremely useful tool called the Digital Health Policy Navigator. The tool can help digital health startups determine whether their product falls under the FDA’s oversight through a relatively painless 7-step process.

What’s Next for Imaging AI Regulations?

Healthcare AI’s rapid evolution continues to challenge FDA regulators, leading to new AI frameworks and action plans, and a growing list of questions from AI developers and users. In this editorial, Intelerad’s A.J. Watson answers those questions and details a path forward that supports both AI regulations and innovations.

GE’s Smart X-Ray Workflow Assistance

What if your X-ray system could help you do more by doing less? See how GE’s AI-based X-ray workflow automations can reduce your repeat and rejected exams, while improving image quality, consistency, and productivity.

The Resource Wire

• See how Novarad’s CryptoChart solution allowed Central Ohio Primary Care (COPC, 70 practices, 400 physicians) to make the transition to digital imaging sharing in this Healthcare IT News case study.

• Change Healthcare’s cloud-native, zero-footprint Stratus Imaging PACS is live in clinical use. See how Stratus Imaging PACS is helping radiology practices improve productivity and patient care, while eliminating the cost and resource constraints of on-premise systems.

• AI delivers value to a wide range of healthcare stakeholders, but its primary value to health systems originate from its ability to automate tasks, democratize care, and deliver hard and soft ROI. See how these factors impact health systems’ bottom line in this latest Arterys report.

• Us2.ai’s echocardiography analysis automation solution is being integrated into the EchoNous Kosmos ultrasound platform, creating the most powerful diagnostic “power tool” ever created for the hand-carried POCUS market.

• When SyntheticMR validated its SyMRI MSK solution, they leveraged the CARPL platform to compare conventional knee and spine MRI image quality with SyntheticMR images. Check out their validation process and results here.

• Find out what built for the modern world means — and why it matters — in this Aunt Minnie profile on United Imaging’s more modern approach to vertical integration, leadership, and culture.

• Nuclear medicine teams are facing three significant SPECT/CT challenges: balancing dose with image optimization, addressing staffing constraints, and preparing for continued theranostics advances. See how redefining your SPECT/CT standards can address these challenges in this Siemens Healthineers report.

• During 25 years in the imaging informatics trenches you see a lot of patched together solutions to data governance problems. See how these work-arounds helped shape Enlitic product leader Rocky Lien’s vision for what can be accomplished using Curie|ENDEX.

• Check out this Imaging Wire Show featuring Canon Medical Systems’ David Hashimoto, exploring how Canon is connecting with imaging teams and working to address their needs.

• annalise.ai’s Annalise CXR solution detects up to 124 findings in a single chest X-ray. See how it detects such a wide range of abnormalities using these demo studies…  or upload your own CXR images.

• How patients interact with a medical device can have as much impact as the device itself. Check out this Q&A with Hyperfine Lead Product Designer Corinne Hay to learn how human factors influence the design of everything from prescription containers to portable MRI systems.

• This Riverain Technologies case study details how Einstein Medical Center adopted ClearRead CT enterprise-wide (all 13 CT scanners) and how the solution allowed Einstein radiologists to identify small nodules faster and more reliably.