Sadiya Khan, MD, Northwestern University, lead author of a new study using CAC scores to predict CHD risk.

Imaging Wire Sponsors

Annalise.ai  •  Arterys  •  Bayer  •  Blackford  •  CARPL.ai  •  Change Healthcare  •  Enlitic  •  GE HealthCare  •  Hyperfine  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  Riverain Technologies  •  Siemens Healthineers  •  Subtle Medical  •  United Imaging  •  Us2.ai  •  Visage Imaging

What can be done to make radiology workflow more efficient? We talked to Ernest Montañà of teleradiology services provider TMC, a Unilabs company, about technology it adopted to help radiologists do their jobs more efficiently. Check it out on our YouTube channel.

Cardiac Imaging

CT Flexes Muscles in Heart

CT continues to flex its muscles as a tool for predicting heart disease risk, in large measure due to its prowess for coronary artery calcium scoring. In JAMA, a new paper found CT-derived CAC scores to be more effective in predicting coronary heart disease than genetic scores when added to traditional risk scoring. 

Traditional risk scoring – based on factors such as cholesterol levels, blood pressure, and smoking status – has done a good job of directing cholesterol-lowering statin therapy to people at risk of future cardiac events. But these scores still provide an imprecise estimate of coronary heart disease risk. 

Two relatively new tools for improving CHD risk prediction are CAC scoring from CT scans and polygenic risk factors, based on genetic variants that could predispose people toward heart disease. But the impact of either of these tools (or both together) when added to traditional risk scoring hasn’t been investigated. 

To answer this question, researchers analyzed the impact of both types of scoring on participants in the Multi-Ethnic Study of Atherosclerosis (1,991 people) and the Rotterdam Study (1,217 people). CHD risk was predicted based on both CAC and PRS and then compared to actual CHD events over the long term. 

They also tracked how accurate both tools were in reclassifying people into different risk categories (higher than 7.5% risk calls for statins). Findings included: 

• Both CAC scores and PRS were effective in predicting 10-year risk of CHD in the MESA dataset (HR=2.60 for CAC score, HR=1.43 for PRS). Scores were slightly lower but similar in the Rotterdam Study
• The C statistic was higher for CAC scoring than PRS (0.76 vs. 0.69; 0.7 indicates a “good” model and 0.8 a “strong” model) 
• The improved accuracy in reclassifying patient risk was statistically significant when CAC was added to traditional factors (half of study participants moved into the high-risk group), but not when PRS was added  

The Takeaway 

This study adds to the growing body of evidence supporting cardiac CT as a prognostic tool for heart disease, and reinforces CT’s prowess in the heart. The findings also support the growing chorus in favor of using CT as a screening tool in cases of intermediate or uncertain risk for future heart disease.

All-In with United Imaging

United Imaging’s “all-in” approach means that every system ships with its entire suite of features and capabilities (no options), giving its clients more clinical flexibility and predictability.

Lung Cancer Programs: Go, Grow and Flow

Over 9 out of 10 people who should be screened for lung cancer aren’t, and nearly 50% of lung cancer cases are caught in the advanced stages. But lung cancer screening has been challenging. Riverain strives to make everything about the lungs clearer, so they assembled this resource page for anyone interested in starting or improving their lung screening program.

The Wire

• ChatGPT Co-Authors Paper On ChatGPT:  JACR has published an overview of ChatGPT… that was partially written by ChatGPT. The paper outlines the pros and cons of the large language model AI algorithm, noting that chatbots like ChatGPT can free healthcare professionals from mundane and repetitive tasks such as simplifying reports for patients and augmenting content creation. Downsides include doubts about the model’s accuracy and reliability, privacy concerns, and ethical implications of AI-generated content in research and publishing. 

• NEJM Reviews AI for Medical Imaging: One of healthcare’s most prestigious journals — New England Journal of Medicine — has turned its attention to the use of AI to interpret medical images. In a review article, Nuance CMIO Matt Lungren, MD, and Pranav Rajpurkar, PhD, of Harvard offer their thoughts on why AI has not been adopted more broadly, including a lack of real-world data, limited generalizability, and the scarcity of comprehensive AI solutions for image interpretation.

• Intelerad Names New CEO: Intelerad Medical Systems has named Jordan Bazinsky as its new CEO, replacing Mike Lipps, who is retiring after almost 3 years leading the company. Bazinsky has 20 years of relevant industry experience, most recently serving in executive leadership positions at Cotiviti and Verisk Health. His focus will be on enhancing healthcare outcomes and bringing value to Intelerad’s client base. Intelerad has acquired seven companies since December 2020, most recently Life Image and Penrad Technologies in 2022.

• Outreach Boosts CT Lung Screening: Offering CT lung cancer screening to women getting screening mammography could boost low lung screening rates, currently mired at about 5%. In a talk at ATS 2023, MUSC researchers discussed how they mined a database of ～34k women who had undergone mammography to find those also eligible for lung screening. They found that 16% had a smoking history; of these, 13.7% underwent lung screening, showing that breast screening offers a chance to introduce an “already engaged population” to CT lung screening.

• Siemens Secures Parts Supply: Siemens Healthineers has moved to secure its supply of parts by acquiring Block Imaging in collaboration with Catholic health system CommonSpirit Health. In addition to parts, Block also offers equipment refurbishing and service, and Siemens and CommonSpirit are positioning the move as a “green” deal that will extend the lifespan of medical equipment while also giving customers value-based options for equipment purchasing.

• CAD Elevates Breast Ultrasound: Samsung Medison’s S-Detect CAD application running on board ultrasound scanners helped improve the diagnostic performance of radiologists without breast ultrasound experience for differentiating malignant from benign lesions. In AJR, researchers from China used CAD on scans of 313 patients; the accuracy of radiologists rose with use of CAD (86.6% vs. 62.6%) as did specificity (82.9% vs. 46.0%), showing CAD’s impact on reducing breast biopsies, especially at sites with less access to breast imaging expertise.

• ImagineSoftware Acquires Within Health: Medical billing software developer ImagineSoftware has acquired radiology workflow automation firm Within Health. Within Health developed RadNav, an application that flags imaging follow-up recommendations, automates communication workflow, and updates case status. The companies see RadNav as a good fit with ImagineSoftware’s own medical billing and revenue cycle management applications.

• New PET Tracer for Tau: A new PET tracer under development for detecting tau accumulation in the brain changed management of Alzheimer’s disease patients in a Swedish study in JAMA Neurology. Researchers performed PET scans with fluorine-18 RO948 in working up 878 patients with cognitive complaints from 2017 to 2021. The tau PET scans changed both diagnosis and medication (7.5% and 5.5%). If commercialized, RO948 could compete with another tau agent, Eli Lilly’s Tauvid, approved in 2020.

• FES PET Added to Guidelines: In other PET news, the NCCN has recommended that breast cancer patients with cancer that’s hormone receptor positive (ER+) receive PET scans with a fluoroestradiol (FES) radiotracer as part of their workup. GE HealthCare markets the only approved FES radiotracer in the US, Cerianna, acquired through its 2021 purchase of Zionexa. FES PET is indicated as an adjunct to biopsy for patients with recurrent or metastatic breast cancer, and the NCCN’s move should spur broader use of the radiotracer. 

• Breast Imaging Disparities: Researchers examined breast imaging disparities in a new study in JACR, analyzing the prevalence of accredited breast imaging facilities by ZIP code. They found that areas classified as “high disadvantage” were less likely to have FDA-certified mammography facilities (28% vs. 35%). In urban areas, ACR-accredited stereotactic biopsy sites were less common in high-disadvantage ZIP codes (10% vs. 16%), as were sites with breast ultrasound (13% vs. 23%). The study again confirms the stark disparities that plague the US healthcare system. 

• AI+Breast Density Predicts Cancer Risk: Researchers found that the combination of ScreenPoint Medical’s Transpara Exam Score AI algorithm with Volpara’s TruDensity volumetric breast density analysis software was effective in predicting long-term breast cancer risk. In Journal of Clinical Oncology, they analyzed mammograms of 2,412 women with invasive breast cancer 2-5.5 years before their cancer diagnosis and assigned a malignancy score of 1-10. A one-unit increase in the AI score was associated with 20% higher odds of invasive breast cancer.

• Photon-Counting CT Benefits Kids: The higher image quality of photon-counting CT was a benefit when imaging infants and neonates with heart defects, says a new study in Radiology. German researchers scanned 113 children from 2019 to 2022, finding that PCCT images were sharper and more often of diagnostic quality than dual-source CT (97% vs. 77%), and PCCT’s average image quality score on a scale of 5 was also higher (4.17 vs. 3.16). Radiation dose was about the same.

• Medality Partners with SoCal Practice: Online education and training provider Medality has entered a partnership to provide advanced training and development to Advanced Imaging South Bay in Southern California. Medality (formerly known as MRI Online) will provide personalized and self-directed training programs to the practice’s radiologists with the goal of enhancing diagnostic quality, reducing turnaround times, and accelerating growth. Medality has been growing its customer base since a rebranding in December. 

• NLP Mines EMR for AAA: A commercially available NLP application (Softek Illuminate’s Illuminate ActKnowledge) was used in a paper in Journal of Vascular Surgery to review a massive database of 2.5M radiology reports in the EMR and identify patients who may have abdominal aortic aneurysm. The software flagged 1,934 patients who were included in the analysis; of these, 128 women and 353 men had AAA but were never screened despite meeting criteria. NLP software can help detect AAA in people who meet guidelines but have missed screening, the authors reported.

Qure.ai & CARPL.ai’s Real Time Validation

Faced with the task of monitoring the thousands of exams its algorithms analyze each day, Qure.ai leveraged CARPL.ai’s validation workflow to create a real-time performance dashboard.

Changing How We Think About MRI

How is Hyperfine changing our thoughts about MRI by making it possible to move its Swoop portable MR imaging system directly to patients? Find out in this Let’s Talk Medtech podcast interview with President and CEO Maria Sainz.

Change Healthcare’s Secure Cloud

Did you know one quarter of healthcare organizations have experienced a cyber-attack in the last year? This Change Healthcare animation explains how 3rd-party certified cloud-native enterprise imaging can help secure IT infrastructure that might be exposed with re-platformed imaging systems.

The Resource Wire

• Every 34 seconds, a patient dies of cardiovascular disease. Find out how you can better manage cardiovascular image data and improve patient care with syngo Dynamics from Siemens Healthineers.

• Join the conversation in this June 7 webinar and hear from PACS administrator Griff R. Van Dusen of Memorial Health System how Nuance PowerScribe One’s next-generation reporting experience helps streamline workflow and improve report quality so radiologists can get more done in less time. 

• Early diagnosis of Alzheimer’s disease can be helpful in delaying symptoms and preserving quality of life, helping patients start treatment more quickly. Brain perfusion SPECT can help physicians make a diagnosis of AD sooner, as explained in this article from GE HealthCare. 

• 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. Annalise Enterprise CTB analyzes brain CTs as they are acquired, prioritizes urgent cases, and provides radiologists with details on each finding (types, locations, likelihood).  

• Visage Imaging’s Visage 7 was named the #1 Universal Viewer in the 2023 Best in KLAS Software and Services Report. Find out what’s behind this award-winning solution and learn more about Visage’s One Viewer philosophy. 

• New AI-based reconstruction tools are making it possible to perform imaging exams that are faster and at lower radiation dose. Learn from the experts how it’s done in this webinar recording hosted by Subtle Medical and Incepto. 

• Strain imaging is the most sensitive parameter for determining myocardial deformation and systolic left ventricular function. In this video, see how echo AI from Us2.ai was used to analyze myocardial global longitudinal strain (GLS). 

• What are the factors that contribute to errors and misreads in radiology – and how can they be prevented? Find out how to improve your practice’s quality and accuracy in this white paper from Medality. 

• Check out this Blackford Analysis video detailing how its AI platform streamlines AI adoption and workflows, allowing radiology teams to achieve AI’s clinical benefits without operational sacrifices.

• SOIN Soluciones Integrales of Costa Rica turned to Merge enterprise imaging solutions from Merative when it wanted to modernize the imaging environments of 50 hospitals across the country. Download this PDF white paper to find out how they did it.

• Your images have the power to advance healthcare research, but removing patient PHI can be a challenge. Learn how Enlitic’s Curie|ENCOG technology can de-identify and anonymize clinical data, enabling you to put your images to work.

• Managing imaging exams brought in by patients on CDs was slowing down the workflow at Boston Children’s Hospital, the largest pediatric trauma center in New England. Find out how the hospital’s pediatric trauma service turned to Intelerad to solve the problem in this case study. 

• AI delivers value to a wide range of healthcare stakeholders, but its primary value to health systems originates 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 Arterys report.

• AI governance is emerging as a critical role in health systems adopting AI, especially in the imaging suite. If you’re attending AI Med in San Diego June 4-7, be sure to attend this roundtable moderated by Pamela Habib, head of commercial development at Bayer Digital Solutions.