- The 2022 Contrast Shortage: The iodinated contrast shortage remained medical imaging’s biggest story last week, making headlines across a wide range of news outlets and dominating radiology’s social media discussions. GE Healthcare since revealed that its Shanghai contrast facility has returned to 50% capacity, and it’s ramping up production at another global facility. GE is also allowing clients to source contrast from other vendors, some of which are actively working to meet demand. Until inventories rebound, here’s a good resource for how providers can manage the contrast shortage.
- Density & Benign Disease Risk Factor: A massive study out of South Korea added more evidence that women with dense breasts and benign breast disease face significantly higher future breast cancer risks. The researchers analyzed data from 3.9M women over a ~10.6-year follow-up period, finding that women with extremely dense breasts and benign breast disease at screening had far higher risk of breast cancer than women with fatty breasts and no breast disease (HR: 2.75). Meanwhile, women with benign breast disease and fatty breasts (HR: 1.49) and women with extremely dense breasts and no benign breast disease (HR: 2.28) also had higher breast cancer risks.
- Imaging IT’s Unprecedented Growth: Signify Research reports that imaging hardware supply chain challenges will suppress the global imaging IT market’s growth in 2022 (~2.5% in 2022 vs. ~4% in 2021), but forecast “unprecedented growth” in 2023 and 2024 (~4.5%/yr) driven by initiatives to improve imaging collaboration/productivity and new demand from the outpatient and ambulatory centers. Given imaging IT’s limited growth potential in most years, Signify advised vendors to start preparing to capitalize on 2023 and 2024’s unique growth opportunities.
- DECIDE-AI Reporting Guideline: A collection of AI and research leaders just rolled out the DECIDE-AI reporting guideline for the early-stage, live clinical evaluation of AI systems. Assembled with input from at least 138 experts, the DECIDE-AI guidelines feature 17 AI-specific reporting items and 10 generic reporting items that they believe will improve early-stage reporting quality and lead to higher impact large-scale trials.
- Google Hires Former FDA CDO: Google appointed the FDA’s former chief digital officer Bakul Patel to lead its global digital health and regulatory strategy. The hire looks like a clear sign that Google is getting more serious about its healthcare plans after reorganizing its Google Health division late last year. In a LinkedIn post announcing the move, Patel said that his “biggest northstar has been to make digital healthcare accessible and equitable for all,” a mission that’s well aligned with Google’s recently announced AI tools to improve early detection of complications with pregnancies and diabetes.
- CT Contrast Pooling & Cardiac Arrest: A new study out of Taiwan confirmed that CT contrast agent pooling (CAP) should be flagged as a sign of imminent cardiac arrest with a higher risk of poor outcomes. The researchers reviewed chest and abdominal CTs from 128-consecutive emergency department patients who later experienced cardiac arrest (11 CTs w/ CAP), finding that CAP in CT scans predicted which patients would experience cardiac arrest within one hour with 86% accuracy (7.35 adjusted odds ratio) and patients with CAP had far lower survival rates (0% vs. 15.4%).
- neuro42’s Neuro MRI Robot: neuro42 announced a licensing agreement with Johns Hopkins University, giving the point-of-care neuro MRI startup exclusive rights to Johns Hopkins’ MR-compatible robot for head, neck, and spine applications. The robot performs targeted needle insertion with precision depth control, and will be incorporated with the neuro42 MRI system to support image-guided interventions during brain biopsies, shunt placements, and laser ablations.
- Advocate Aurora + Atrium: Regional health systems Advocate Aurora Health and Atrium Health are merging to create one of the largest nonprofit health systems in the US, spanning 67 hospitals with $27B in combined revenue. The new system, called Advocate Health, gave a list of six key focus areas that the merger will support, which doubles as a cheat-sheet for anyone wondering about current health system priorities: clinical pre-eminence and safety, health equity, affordability, next-generation workforce, learning and discovery, and environmental sustainability.
- PCa Scores Align: A new study in Clinical Radiology showed that prostate cancer MRI assessments using the PI-RADS and Likert scoring systems are largely equivalent, while adding evidence that most men with negative prostate MRI findings can avoid immediate prostate biopsies. The study compared PI-RADS and Likert scores from 323 men with suspected prostate cancer, finding high concordance rates across the entire cohort (87%), among men with negative MRI results (99%), and men with 5 PI-RADS/Likert scores (96%). The only discordance was with the PI-RADS 4 group, 32% of whom were up-risked to Likert 5.
- Olympus & Bracco EUS Alliance: Olympus and Bracco Diagnostics launched a U.S. co-marketing alliance intended to expand the use of contrast-enhanced endoscopic ultrasound (EUS) for the characterization of focal liver lesions. Through the alliance, Olympus will offer Bracco’s Lumason ultrasound agent with its EUS systems, while the companies will collaborate to increase usage and awareness of the emerging diagnostic approach.
- AI + Reader Improvements: A Frontiers in Oncology study highlighted mammography AI’s ability to improve less-experienced radiologists’ performance with malignant architectural distortions (AD). The researchers had three general and three breast radiologists interpret exams from 267 patients as part of a double reading workflow (177 w/ malignant ADs). Working without AI, the three breast radiologists (AUCs: 0.875, 0.882, 0.884) outperformed the general radiologists (0.733, 0.652, 0.655) and the AI algorithm (0.792). However, AI support significantly improved the overall performance of the general rads (0.880 vs. 0.680), and improved the accuracy of the breast rads (0.893 vs. 0.880) and the double-reading consensus (0.908 vs. 0.878).
