|
Mammo AI Kicks Off RSNA 2024 | More RSNA News
December 2, 2024
|
|
|
|
|
Together with
|
|
|
|
“If you’re 5 FTEs short with a huge outpatient footprint then dropping the inpatient side makes sense … unless the hospitals throw a pile of money at you.”
|
|
Dergon, commenting on RadHQ.net on a New Jersey imaging center firm dropping its hospital contract.
|
|
|
4DMedical is highlighting its unique technology for imaging respiratory function at this week’s RSNA 2024 meeting. And the company is using a novel virtual reality environment to demonstrate its XV Scanner, as we learn in this Imaging Wire Show interview with Greg Mogel, MD, and Tom Harris.
|
|
|
|
Welcome to RSNA 2024! This year’s meeting is starting with a bang, with two important sessions highlighting the key role AI can play in breast screening.
Sunday’s presentations cap a year that’s seen the publication of several large studies demonstrating that AI can improve breast cancer screening while potentially reducing radiologist workload.
- That momentum is continuing at RSNA 2024, with morning and afternoon sessions on Sunday dedicated to mammography AI.
Some findings from yesterday’s morning session include …
- Two AI algorithms were better than one when supporting radiologists in breast screening, with cancer detection ratios relative to historic performance rising from 0.97 to 1.08 with one AI to 1.09 to 1.14 with two algorithms.
- ScreenPoint Medical’s Transpara algorithm was able to prioritize the worklist for 57% of breast screening exams by assigning risk scores to mammograms, helping reduce report turnaround times.
- iCAD’s ProFound AI software helped radiologists detect 7.8% more breast cancers on DBT exams, and cancers were detected at an earlier stage.
- Applying AI for breast screening to a racially diverse population yielded evenly distributed performance improvements.
Meanwhile, the Sunday afternoon session also included significant mammography AI presentations, such as …
- A hybrid screening strategy – with suspicious breast cancer cases only recalled if the AI exhibits high certainty – reduced workload 50%.
- Lunit’s Insight DBT AI showed potential to reduce interval cancer rates in DBT screening by identifying 27% of false-negative and 36% of interval cancers.
- In the ScreenTrustCAD trial in Sweden, using Lunit’s Insight MMG algorithm to replace a double-reading radiologist reduced workload 50% with comparable cancer detection rates.
- A German screening program found that ScreenPoint Medical’s Transpara AI boosted the cancer detection rate by 8.7% (from 0.68% to 0.74%), with 8.8% of cancers solely detected by AI.
- Researchers took a look back at abnormality scores from three commercially available AI algorithms after cancer diagnosis, finding evidence that cancers could be detected earlier.
The Takeaway
Breast screening seems to be the clinical use case where radiologists need the most help, and Sunday’s sessions show the progress AI is making toward achieving that reality.
Be sure to check back on our X, LinkedIn, and YouTube pages for more coverage of this week’s events in Chicago. And if you see us on the floor of McCormick Place, stop and say hello!
|
|
|
Feel the Freedom of Helium-Free MRI
Lift limitations and experience MRI excellence with Philips BlueSeal, the industry’s lightest, vent pipe-free, high-performance, helium-free 1.5T scanner. Save on helium and energy costs, achieve precise AI-enhanced diagnoses, enjoy faster scans, and optimized workflows. Learn more at RSNA 2024 booth #6730.
|
|
Learn about Gleamer at RSNA 2024
Visit Gleamer at booth #5144 at RSNA 2024 to learn about their novel AI solutions for musculoskeletal imaging, including measuring Cobb angles on X-ray and the beneficial impact of BoneView for fracture detection. Schedule a meeting today.
|
|
Connect with Intelerad at RSNA 2024
Connect with Intelerad at RSNA 2024 to see how they can empower your radiology team to deliver faster, more accurate diagnostics. Visit them at booth #6113 to see how they’re solving everyday radiology workflow challenges with scalable, cloud-based solutions.
|
|
- The True Cost of Engineered Countertops: An epidemic of silicosis is affecting workers who produce engineered stone countertops, and X-ray and CT can be used to detect signs of the disease. In a study presented at RSNA 2024, researchers showed that radiologists were able to detect more silicosis cases at initial patient encounters than primary care doctors (19% vs. 33%). Also, 48% of silicosis patients had atypical features on medical images, such as diffuse nodularity, multiple cavitary lesions, or crazy paving.
- Falling MRI Reimbursement: In a Sunday RSNA poster presentation, researchers documented how Medicare reimbursement for six different MRI applications fell -5.4% to -8.4% from 2020 to 2021. Brain scans showed the biggest drop, while the site of service shifted from facilities to offices – perhaps a sign of reimbursement pressure. Researchers suggested the decline showed the need to adjust reimbursement to keep pace with inflation.
- Imaging Shows Toll of Sports: Meanwhile, a pair of RSNA presentations highlights the toll sports can take on the brain. Researchers acquired diffusion MRI brain scans of 352 soccer players and compared them to 77 athletes who played non-collision sports like running, finding that soccer players who headed the ball had white-matter abnormalities. In another talk, researchers acquired magnetoencephalography data from 91 high school football players, finding differences in brain activity in the 10 players with concussion. These players also had worse cognitive symptoms and test scores.
- Visceral Fat Predicts Alzheimer’s: In another paper at RSNA 2024, researchers found that MRI measurements of visceral fat (or deep hidden fat surrounding organs) could predict the development of Alzheimer’s disease 20 years earlier. Researchers scanned 80 cognitively normal people at midlife (average age of 49), finding that visceral fat was linked to Alzheimer’s pathology like amyloid plaques on PET scans, but other types of fat wasn’t. Visceral fat could account for 77% of BMI’s effect on amyloid accumulation.
- Leaky Federated AI Privacy: Federated learning networks are all the rage as a way to enable institutions to share de-identified patient data for AI algorithm training. But a Sunday RSNA poster presentation revealed privacy risks. In an experiment with six virtual servers set up like a federated network, a malicious central server running a transformer-based large language model was able to reconstruct 36% to 42% of sentences from radiology reports that supposedly had been de-identified. Robust patient privacy measures should be taken when training LLMs on federated networks.
- De-Identification Drops Short: In the same Sunday poster session, an AI algorithm was able to re-identify patient information on supposedly de-identified X-rays – a major privacy concern. Researchers de-identified 661k radiographs by removing DICOM metadata tags with protected health information or by altering pixel values in areas containing PHI such as by covering them with black boxes. They then trained a specialized AI model that was able to re-identify X-rays with 94% accuracy – highlighting the need for more robust de-identification and anonymization techniques.
- Hologic Launches Envision DBT at RSNA: Hologic is launching a new mammography platform called Envision at RSNA 2024. The DBT platform received PMA approval in July 2024 and features an updated gantry with adjustable tilting C-arm and an X-ray source with a moving focal spot. Hologic is touting Envision’s 2.5-second scan time and tilt positioning that adapts to patients for more comfortable exams. Hologic is also highlighting Genius AI Detection PRO, the latest iteration of its AI analysis solution.
- TeraRecon Takes to the Cloud: TeraRecon is debuting a cloud-based version of advanced visualization solutions available on a SaaS basis. The launch brings together the company’s Intuition, Eureka Clinical AI, and CARAai offerings on one cloud platform, eliminating the need for customers to maintain on-premises hardware and enabling better consistency in clinical workflow. TeraRecon is highlighting the platform at RSNA 2024, where it is also touting FDA 510(k) clearance of an AI-based auto-contouring algorithm for short-axis cardiac MRI scans.
- Sirona Lands $42M Funding Round: Sirona Medical closed a $42M Series C round on the eve of RSNA 2024, an amount that puts the company in the club of imaging IT companies that have raised over $100M in capital. The company will use the funding to support the continued evolution of its Unify radiology platform, launched in 2023 to combine radiology image review, reporting, and worklist. Simultaneously, Sirona announced that medical device veteran Hooman Hakami will take over the CEO role from Cameron Andrews, who will remain president.
- Xenon MRI Finds COVID Connections: MRI with hyperpolarized xenon-129 inhaled gas found a link between reduced lung function and cognitive impairment in people with long COVID in a study presented at RSNA 2024. In a small study with 12 patients, researchers found that lower pulmonary gas exchange on xenon MRI scans correlated with cognitive dysfunction and increased cerebral blood flow, as well as lower gray and white matter volumes in those with long COVID.
- Philips Partners with icometrix: Philips and MRI software developer icometrix debuted a new partnership at RSNA 2024 to provide integrated solutions for MRI brain scans. Philips is integrating icometrix’s AI-powered reporting software into its BlueSeal MRI scanners to enable users to perform MRI-based quantification of neurological conditions like Alzheimer’s disease. icometrix will supply its icobrain dm application for differential dementia diagnosis, as well as its recently cleared icobrain aria software for analyzing amyloid-related imaging abnormalities that can result from treatment with amyloid-targeting drugs.
- GE Adds Partner for Total-Body PET: GE HealthCare has added another site to its project to develop a total-body PET/CT scanner: Peter MacCallum Cancer Centre in Australia. The partners will collaborate on GE’s development of a PET/CT scanner with a 128cm ultra-high-sensitivity detector. GE is working with Prof. Michael Hofman on the scanner, which should help drive new research and clinical applications for theranostics. GE said last month it was also working with University Medicine Essen in Germany on total-body PET.
- GE Launches Pristina Via Mammo: In other GE HealthCare news, the company is launching the Pristina Via mammography system at RSNA 2024 this week. The DBT system includes features for an easier mammography experience for both patients and technologists, with automated workflow functions like zero-click image acquisition and faster image-to-image cycle time. GE is also touting the low radiation dose used across all breast thicknesses.
- Workflow AI Firms Partner: A trio of radiology workflow AI developers are partnering to combine their solutions to improve radiologist efficiency, especially as it relates to coding. NewVue.ai, RADPAIR, and Maverick Medical.ai are joining forces to integrate AI-powered workflow, reporting, and coding and revenue cycle management technologies to make it easier for radiologists to perform all three functions from a single software package. The firms are showing the integrated solution at RSNA 2024.
- Visage Scores $214M Contract: Visage Imaging landed a massive $214M 10-year contract to provide its Visage 7 enterprise imaging platform to Trinity Health, replacing legacy systems from nine different vendors. Separately, Visage landed another deal, this one worth $16M, to upgrade the enterprise image management network at NYU Langone Health, which is upgrading its current on-premises Visage installation to the cloud-based Visage 7 Open Archive, as well as Visage 7 Viewer and Visage 7 Workflow.
- Siemens Lands Ohio State Contract: Siemens Healthineers has landed a 10-year $105M contract to supply its technology to Ohio State University’s Wexner Medical Center. The contract expands on a 15-year relationship, and will support the university’s creation of an imaging center of excellence.
- Canon Updates 3T MRI Platform: Canon Medical Systems USA is debuting an updated version of its Vantage Galan 3T MRI scanner at RSNA 2024. The scanner’s Supreme Edition features a Japanese-made magnet and Canon’s Altivity AI suite for helping clinicians improve image quality and reduce scan times. It also sports the company’s AiCE and PIQE image reconstruction techniques.
- NJ Imaging Network Drops Hospitals: New Jersey imaging services provider ImageCare Radiology said it would be dropping its hospital-based contract with Atlantic Health System to focus on its own outpatient practice. The move affects the provider’s contracts at two Atlantic Health hospitals, while ImageCare operates a network of 23 outpatient centers in northern and central New Jersey. A thread on RadHQ.net speculates the move could represent a broader shift in the power dynamic between radiology groups and hospitals – in radiology’s favor.
- Blackford Adds Quantivly to Platform: Blackford is adding solutions from Quantivly to its Blackford Platform. Blackford customers will have access to Quantivly Hub, an AI solution for optimizing radiology operations by analyzing scanner utilization and clinical workflow to create a comprehensive look at departmental performance. Quantivly positions its software as a “digital twin” that enables departments to create computer models for testing the impact of different interventions on performance.
- Google Gets into Foundation Models: Google entered the burgeoning market for AI foundation models last week by launching Health AI Developer Foundations (HAI-DEF), a suite of foundation models for developing AI algorithms. HAI-DEF’s initial release includes three models for developing medical applications: CXR Foundation for chest X-rays, Derm Foundation for skin images, and Path Foundation for digital pathology. CXR Foundation was trained on over 800k X-rays.
- Densitas Added to ACR Learning Network: Breast radiology software developer Densitas is collaborating with the ACR Learning Network to add its AI solutions to the network’s mammography quality improvement initiatives. Densitas will support the network’s ACR ImPower program, particularly as it relates to tracking and improving consistency in mammography positioning. Densitas notes that only 67% of mammography images meet ACR positioning guidelines.
- Annalise Lands Radboud: Annalise.ai is entering the Dutch healthcare market via a contract to install its CT and X-ray AI solutions at Radboud University Medical Center, one of Europe’s most prominent academic institutions. Annalise will provide its Enterprise CXR solution for chest X-rays and Enterprise CTB algorithm for non-contrast CT brain exams. Radboudmc is launching a multi-year research study on AI’s impact on Dutch healthcare as part of the installation.
- ScreenPoint Shows Cleared Software: ScreenPoint Medical is highlighting the newest version of its recently cleared Transpara solution for mammography AI at RSNA 2024. Transpara 2.1 is based on additional training and insights from users around the world. It is compatible with different options for calculating breast density like volumetric and BI-RADS techniques, and enables suspicious areas to be analyzed against up to three prior images over six years.
- Milvue Joins deepc AI Platform: AI platform company deepc has added solutions from French X-ray AI developer Milvue, including its TechCare family of algorithms. Under the alliance, deepc users will have access to TechCare Alert for detecting fractures in the appendicular skeleton and chest; TechCare Bones & Spine for musculoskeletal measurements; and TechCare Kids, which combines pathology detection with bone measurements.
- Protege Data Alliance with Segmed: In another sign of the growing importance of data for AI training, Segmed has partnered with Protege in an alliance to give AI developers and researchers easier access to data. Segmed will make its de-identified medical imaging data available to users of Protege’s AI platform for training data. Protege also signed a partnership with Gradient Health in October.
|
|
Start at the Source to Improve MRI
Looking for ways to improve MRI speed and image quality while addressing broader concerns in healthcare? The answer may lie in proven MRI physics in your existing scanner – learn how to unlock it with STAGE from SpinTech MRI.
|
|
Meet with Medality at RSNA 2024
Book a visit with Medality at RSNA 2024 to see how they are at the forefront of practice growth and training in radiology. Also be sure to sign up for their RSNA after party at Flight Club at 6 pm CT on December 3.
|
|
Discover the Power of an AI Ecosystem
Get the insights you need to fuel your AI strategy in the Bayer Visionary Theater at RSNA 2024. Preview the theater sessions today and plan to attend at booth #2514 – and don’t forget to experience the Tunnel of Innovation!
|
|
- Enlitic – South Hall, Booth #4365: Visit Enlitic at RSNA 2024 to learn how the company is revolutionizing radiology with its data standardization solutions, including data migration technology through its acquisition of Laitek. Book a demo today.
- CARPL – South Hall, Booth #5733: Explore radiology AI like never before by booking a meeting with CARPL at RSNA 2024, or drop by to tune in to any of seven research presentations across the show.
- Siemens Healthineers – South Hall, Booth #2529: Join Siemens Healthineers at RSNA 2024 to experience the future of healthcare. Explore cutting-edge innovations, connect with leading experts, and collaborate with industry professionals in live demonstrations.
- Harnessing the Power of AI to Improve Patient Care: Endeavor Health is one of the first healthcare providers in the Midwest to use AI in the echocardiography lab. Learn how they are harnessing echo AI’s tremendous potential to improve diagnostic capabilities and help patients on this page from Us2.ai.
- DeepHealth – South Hall, Booth #1340: DeepHealth is leading radiology forward through AI-powered informatics and smart technology. Book a meeting today at RSNA 2024 to learn how they can help you achieve increased staff productivity and a better experience for patients and staff.
- Clearpath – South Hall, Booth #1748: Clearpath is a simple integration that empowers digital delivery of medical records and images. Visit them today to find out how you can ditch the disc and give your patients and third parties instant access to digital data.
- Optum – North Hall, Booth #6750: Visit Optum at RSNA 2024 to learn how their cloud-based enterprise imaging solutions can enhance the potential of your imaging data for efficient, cost-effective care.
- United Imaging – South Hall, Booth #1929: United Imaging will be celebrating the theme of Building Intelligent Connections at RSNA 2024. Come visit the company to learn about their imaging solutions and how they connect to United’s mission of Equal Healthcare for All.
- AGFA HealthCare – South Hall, Booth #2565: Visit AGFA HealthCare at RSNA 2024 to learn about groundbreaking new enterprise imaging innovations. Drop by to see for yourself how to elevate productivity and efficiency while facilitating growth and collaboration across universal imaging ecosystems.
- Prenuvo – South Hall, Booth #1239: Discover how Prenuvo is advancing research and redefining the future of healthcare at RSNA 2024. Learn about their cutting-edge MRI technology first-hand and explore partnership opportunities.
- TeraRecon – North Hall, Booth #8134: Visit TeraRecon at RSNA 2024 to hear captivating presentations from radiology thought leaders every day of RSNA week. Schedule a meeting today.
- Microsoft – South Hall, Booth #1311: Visit Microsoft at RSNA 2024 to learn about their new family of cutting-edge multimodal medical imaging foundation models designed for healthcare organizations to test, fine-tune, and build tailored AI solutions specific to their needs.
- Riverain Technologies – South Hall, Booth #4523: Riverain’s ClearRead technology with Clear Visual Intelligence can improve your ability to detect lung cancer with either CT or X-ray. Book a meeting with them at RSNA 2024 to see for yourself.
- Mach7 Technologies – South Hall, #3953: Mach7 Technologies’ enterprise imaging solutions connect patients and clinicians across the globe to enable exceptional care. As modern healthcare evolves, so should your strategies. Schedule a demo at RSNA 2024 to learn more.
- PocketHealth – South Hall, Booth #2601: Join PocketHealth at RSNA 2024 to learn how they close critical gaps in patient care to modernize the healthcare experience. Stop by for a demo.
- Visage – South Hall, Booth #4329: Visage continues to lead imaging’s managed services SaaS move to the cloud with their Visage 7 CloudPACS solution. Register today for a priority demo at RSNA 2024.
- Blackford – South Hall, Booth #4729: Learn how you can boost efficiencies through enterprise AI with Blackford. Visit them at RSNA 2024 booth #4729 to find out how an experienced partner can guide you to tailored, proven AI solutions.
- Merge – North Hall, #6100: Merge is looking forward to sharing a wide range of news, innovations, and updates at RSNA 2024. Join them to explore how their imaging solutions put your workspaces, clinicians, and transformation into focus.
|
|
|
|
|
