Joshua Miller, CEO of Gradient Health, on foundation models for training AI algorithms.

Imaging Wire Sponsors

Bayer  •  Blackford  •  CARPL.ai  •  Change Healthcare  •  Clearpath  •  Enlitic  •  GE HealthCare  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  PocketHealth  •  Riverain Technologies  •  Siemens Healthineers  •  Subtle Medical  •  Tempus Radiology  •  United Imaging  •  Us2.ai  •  Visage Imaging

Lung Cancer Screening

CT Lung Screening Saves Women

October may be Breast Cancer Awareness Month, but a new study has great news for women when it comes to another life-threatening disease: lung cancer. 

Italian researchers in Lung Cancer found that CT lung cancer screening delivered survival benefits that were particularly dramatic for women – and could address cardiovascular disease as well. 

• They found that in addition to much higher survival rates, women who got CT lung screening after 12 years of follow-up had lower all-cause mortality than men. 

Of all the cancer screening tests, lung screening is the new kid on the block.

• Although randomized clinical trials have shown it to deliver lung cancer mortality benefits of 20% and higher, uptake of lung screening has been relatively slow compared to other tests.

In the current study, researchers from the Fondazione IRCCS Istituto Nazionale dei Tumori in Milan analyzed data from 6.5k heavy smokers in the MILD and BioMILD trials who got low-dose CT screening from 2005 to 2016. 

In addition to cancer incidence and mortality, they also used Coreline Soft’s AVIEW software to calculate coronary artery calcium (CAC) scores acquired with the screening exams to see if they predicted lung cancer mortality. Researchers found that after 12 years of follow-up …

• There was no statistically significant difference in lung cancer incidence between women and men (4.4% vs. 4.7%)
• But women had lower lung cancer mortality than men (1% vs. 1.9%) as well as lower all-cause mortality (4.1% vs. 7.7%), both statistically significant
• Women had higher lung cancer survival than men (72% vs. 52%)
• 15% of participants had CAC scores between 101-400, and all-cause mortality increased with higher scores
• Women had lower CAC scores, which could play a role in lower all-cause mortality due to less cardiovascular disease

The Takeaway

This is a fascinating study on several levels. First, it shows that lung cancer screening produces a statistically significant decline in all-cause mortality for women compared to men.

Second, it shows that CT lung cancer screening can also serve as a screening test for cardiovascular disease, helping direct those with high CAC scores to treatment such as statin therapy. This type of opportunistic screening could change the cost-benefit dynamic when it comes to analyzing lung screening’s value – especially for women.

Improving Access and Efficiency at William Osler Health

Watch how PocketHealth helped William Osler Health System improve access and efficiency through patient-driven image exchange in this video interview with Aimee Langan, Director, Diagnostic Imaging, Laboratory, Neurodiagnostics.

Going Mobile with MRI Just Got Easier

Mobile MRI can help you deliver healthcare to your patients wherever they are. Find out in this article how the new Magnetom Viato.Mobile scanner from Siemens Healthineers makes going mobile with MRI easier than ever.

The Wire

• AI Predicts Lung Cancer Risk: While we’re discussing lung cancer screening, researchers in PLOS Medicine tested an AI model to predict who should get screened based on risk. The model uses three variables – age, smoking duration, and pack-years – and was developed from NLST and UK Biobank patient data and validated with data from the PLCO trial. The model predicted lung cancer death (AUC=0.80) and incidence (AUC=0.78), and had higher sensitivity than the USPSTF’s lung screening criteria for predicting both mortality (+7.9%) and incidence (+6.2%). 

• Mixed Results for AI of PE: A real-world study in Radiology of Aidoc’s algorithm for triaging pulmonary embolism (PE) on CT pulmonary angiography exams in 1.5k patients failed to show a benefit for improving radiologist accuracy, miss rate, or report turnaround times. On the positive side, patient wait times for positive PE studies fell 50% (11 vs. 22 minutes). The mixed results could have to do with how AI was deployed: researchers used it with a standalone widget interface rather than integrated into the worklist. 

• Blowback to Chest X-Ray AI Study: Reverberations from last month’s paper in Radiology on chest X-ray AI continue to ripple through medical imaging. The study claimed that four commercially available AI algorithms underperformed radiologists for reading chest X-rays. But the study design put AI at a disadvantage, said Annalise.ai Chief Medical Officer Rick Abramson, MD, in a LinkedIn post, by giving radiologists access to prior images and clinical data, while the AI algorithms were only given chest X-rays. 

• Rise of the (AI) Transformers: A new type of AI model called transformer-based neural networks could improve AI performance by combining both imaging and non-imaging data like lab tests. In a Radiology study, researchers from the UK and Germany describe how their transformer model performed better in analyzing chest X-rays for a wide range of pathologies in 36.5k patients. The transformer model’s mean AUC was higher than that of AI with just imaging or just clinical data (0.77 vs. 0.70 and 0.72).     

• Will Foundation Models Deliver? Foundation models are another type of relatively new AI technology that offers the promise of training algorithms more quickly using unlabeled clinical data. But a study last month cast some doubt on foundation models, a position echoed this week in a blog post by Joshua Miller, CEO of data sourcing provider Gradient Health. Gradient has seen demand for large unlabeled datasets skyrocket in the last three months. But raw foundation models are not likely to deliver the generalizability AI developers need and will require fine-tuning with well-labeled data. 

• Contrast Risk Overblown? Is the risk of acute kidney injury from intravenous contrast media overstated? In a review article in AJR, researchers explained that over the years, estimates of the rate of contrast injury incidence have fallen among the general population (5% to 0-2%) and in those with severe renal dysfunction (30% to 0-17%). But even these estimates may be too high, and evidence shows that intravenous contrast is safe for 95% of patients, especially those with adequate kidney function (eGFR >45 ml/min/1.73 m²).

• Nanox Strikes Deal with Varex: Israeli digital imaging developer Nanox has signed an agreement with Varex Imaging in which Varex will supply X-ray tubes with Nanox’s digital cathode X-ray source for the Nanox.ARC multisource digital X-ray system. Varex will receive a revenue share from the sale of Nanox.ARC units using Varex tubes in Nanox’s pay-per-scan program. Nanox got FDA clearance for Nanox.ARC in April, and in August settled an SEC probe into statements the company made on development and manufacturing costs for the systems.

• FDA Approves Technegas for V/Q Scans: Good things come to those who wait. The FDA has approved Cyclopharm’s Technegas agent for performing ventilation-perfusion (V/Q) nuclear medicine studies of pulmonary embolism and other respiratory problems. Cyclopharm developed Technegas in 1986, and the agent is already widely used around the world. The approval comes some two-and-a-half years after SNMMI urged FDA to start a fast-track review of Technegas, once again demonstrating that the FDA moves at its own pace. 

• Simpler CT Simulation: Radiation therapy planning could be made faster by using previously acquired diagnostic CT images rather than CT simulation scans. In a study presented at ASTRO 2023, Canadian researchers showed how planning for palliative radiation therapy can be completed before the patient arrives, rather than making them wait for CT simulation scans. In 33 patients who got conventional or accelerated planning, the faster workflow cut wait times from five hours to 30 minutes, while the dose distribution for the faster treatments was rated as acceptable.

• Siemens Launches Wide-Angle DBT: Siemens Healthineers has launched Mammomat B.brilliant, a new wide-angle digital breast tomosynthesis (DBT) system. The new system’s tube moves in a 50° sweep around the breast in five seconds, which Siemens claims is a wider arc with a 35% faster acquisition than other DBT systems. The systems’ ComfortMove function adapts to patient anatomy, while PlatinumTomo combines wide-angle imaging, a new detector, flying focal spot technology, and Premia AI reconstruction for better image quality. The system is currently targeted at the European market.  

• Forchette Retires as Delphinus CEO: Mark Forchette has retired as president and CEO of Delphinus Medical Technologies. Stepping into his position is Scott White, who was hired as Delphinus’ chief commercial officer in February 2023 after serving in a similar role at portable MRI developer Hyperfine. Delphinus makes the SoftVue 3D whole-breast ultrasound tomography system, which got FDA approval in 2021 as a supplement to screening mammography. Delphinus raised $12M earlier this year.

Keeping Patients at the Center of Breast Imaging

Join Merge on October 19 for a conversation on how to provide better patient outcomes and user experiences in mammography. Hear from thought leaders on the development and deployment of breast imaging solutions driven by patient needs.

Resource Hub for Radiology and IT Professionals

Looking for a single page to rule them all with articles, news, case studies, and webinars for radiology and IT professionals? Check out Enlitic’s new Resource Hub!

Streamlining AI Adoption and Workflow

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.

The Resource Wire

• Teleradiology can be a force multiplier in radiology. Watch this Medality webinar recording with Daniel Corbett of Radiology Business Solutions to learn the pros, cons, and essential factors for private-practice leaders considering teleradiology integration.

• We talk a lot about radiology practices’ AI adoption, but usually don’t have much evidence to back it up. That changes with this Tempus Radiology report detailing how and why 30 US radiology groups became imaging AI adopters.

• 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. 

• See how 2-meter total body PET gives molecular imaging teams a diagnostic advantage compared to other “eyes to thighs” PET options in this editorial by United Imaging CEO Jeffrey M. Bundy.

• A new platform from Clearpath now enables healthcare providers to delight their patients by sharing images and medical records digitally. Find out how it integrates simply into your practice.

• When Sao Paolo’s Diagnosticos da America SA (DASA, the world’s fourth largest diagnostics company) set out to evaluate Qure.ai’s QXR solution for their pediatric chest X-ray workflows, they leveraged CARPL.ai’s platform to streamline their evaluation. See how it worked here.

• Is your organization ready to move enterprise imaging to the cloud? Check out this Change Healthcare and ACHE webinar detailing cloud-native imaging’s benefits, best practices, and ROI.

• New results from the OPERA study show how Us2.ai’s echo AI solution improved heart failure screening in the NHS, reducing echo waiting times from 12 months to under 6 weeks. Find out more in this article.

• What is Clear Visual Intelligence (CVI) from Riverain Technologies? CVI uses deep learning to remove interfering normal structures within the chest like bones, vessels, and machine noise to help you focus on actionable data. Learn more and book a demo today.

• Lung cancer causes more deaths globally than colon, breast, and colon cancer combined. But technologies like AI and low-dose CT screening can help. Learn more in this Q&A with Ankur Sharma, MD, head medical affairs digital radiology at Bayer. 

• How important is image quality in molecular imaging? Improvements in PET/CT and SPECT/CT are addressing historical challenges and empowering clinicians with more accurate and detailed information. Learn more in this white paper from GE HealthCare. 

• With burnout and staffing shortages on the rise, and the increasing volume of imaging, radiology teams are searching for solutions. This interactive guide from Nuance can help you create an environment where radiologists thrive by building a powerful imaging strategy with AI-driven, real-time intelligence.

• What are some of the major innovations happening now in the medical image acquisition chain? In the latest edition of The Imaging Wire Show, we talked to Josh Gurewitz and Ajit Shankaranarayanan of Subtle Medical about new developments in image acquisition and enhancement.

• When it comes to the cloud for healthcare providers, one size does not fit all. Healthcare organizations are adopting a mix of hybrid and multicloud operating models; learn more about this emerging trend in this article by Intelerad Chief Product Officer AJ Watson.

id: 2023-10-04-18:32:06:295t