|
AI Closes Mammo Gap, MRI Safety Petition, and Global Cancer Burden
July 27, 2026
|
|
|
|
|
Together with
|
|
|
|
“MRI is more than Teslas, or throughput metrics, or CPT codes, and we need to remember the human side of patient care, and our duty to protect the safety of both our MRI patients and caregivers.”
|
|
MRI safety expert Tobias Gilk.
|
|
|
MRI is radiology’s most powerful imaging modality, but it also has perhaps the most challenging workflow due to its complexity. That’s an issue in an era of staff shortages and rising exam volume. In this edition of The Imaging Wire Show, I talked to Holly Schaal of GE HealthCare about new technologies the company has developed to make MRI workflow smoother and more efficient. Enjoy the interview! – Brian Casey, Managing Editor
|
|
|
|
Mammography screening exams are some of the most challenging medical images to interpret, but due to staffing issues many mammograms are read by general radiologists rather than specialists. A new study in Radiology found that an AI-based workflow helped close the gap, leading to a 25% improvement in the cancer detection rate for general radiologists.
Most of the big population-based studies on mammography AI have been conducted in Europe, where breast screening is performed under a double-reader paradigm that has two radiologists interpreting exams.
- In this scenario, studies have shown that AI can eliminate the need for a second reader, cutting workforce requirements with the same or even better cancer detection rates.
But U.S. breast screening programs don’t use double-reading, leaving many to wonder where AI fits into the single-reader paradigm – especially when that reader is a general radiologist with no breast fellowship training.
- The new study offers some clarity. Researchers developed an AI-based workflow that integrated DeepHealth’s ProFound Pro 2.x deep-learning application into DBT-based screening programs.
They set up AI as a “safeguard review.” After a radiologist’s initial interpretation, AI analyzed non-recalled mammograms for suspicion of cancer. Exams that exceeded ProFound’s risk threshold were flagged and routed to an expert reviewer.
- If the reviewer agreed with AI, the original interpreting radiologist was consulted and had final authority on whether to recall the case.
The safeguard review concept was tested at 109 breast imaging facilities that saw 578k DBT mammography exams from 2021 to 2022. In particular, researchers focused on the impact the safeguard review had on interpretation accuracy of both specialists and general radiologists, finding…
- The cancer detection rate of generalists improved 25%, from 3.76 to 4.99 cancers per 1k exams.
- The CDR of specialists did not change at a statistically significant level (from 4.47 to 4.76, p = 0.33).
- There was no statistically significant difference between AI-aided generalists and specialists.
- Generalists became more efficient at cancer detection, as evidenced by 15% improvement in their positive predictive value (from 3.38% to 3.89%).
- Although generalists’ recall rates did increase with AI (from 9.06% to 10.4%).
The Takeaway
The new study offers an intriguing look at how AI can be integrated into U.S. breast screening programs without dramatically disturbing workflow. It also shows how diagnostic performance can be improved in an environment where general radiologists are being asked to fly solo in an area they didn’t train in.
|
|
3T Wide-Bore MRI Delivers Power with Purpose
Translate groundbreaking discoveries into patient care with SIGNA Bolt, GE HealthCare’s visionary 3T MRI scanner that empowers leading-edge research for real patient care.
|
|
Smoothing the Transition to Radiology Integration
Consolidation among medical imaging providers is creating challenges when it comes to managing and integrating image data from diverse sources. In this edition of The Imaging Wire Show, we discussed how solutions from Enlitic can smooth the transition.
|
|
- FDA Denies MRI Safety Petition: As MRI Safety Week begins this week, proponents of stronger MRI regulation got bad news when the FDA denied a petition to classify scanner projectile accidents as “malfunctions.” The classification would have required scanner OEMs to report the incidents, which typically occur when ferromagnetic objects are attracted by a scanner’s strong magnetic field. The petition was proposed by MRI safety advocate Tobias Gilk, but the FDA said in response it would prefer to continue classifying such incidents as “use error.”
- Gaps in Global Cancer Burden Widen: About 20.6M people were diagnosed with cancer in 2024, a nearly 7% increase from 2020, WHO estimates. The number is sobering, and while the organization’s Global Status Report on Cancer 2026 revealed progress is being made, it isn’t being made equally. High-income countries are seeing progress in reducing deaths from diseases like breast cancer that isn’t occurring in low- and middle-income countries. The report makes seven recommendations for reducing the gaps in global cancer care.
- Lower Radiation Dose with Proton Therapy: Women with breast cancer who were treated with proton therapy received lower radiation dose to the heart and cardiac substructures compared to those who got conventional photon radiation therapy. Researchers compared 1.2k breast cancer patients from the RadComp study, finding that proton therapy delivered 70% lower dose to cardiac structures (0.89 vs. 2.99 Gy). But that lower dose didn’t seem to affect short-term cardiac-related quality-of-life measurements.
- Amyloid PET Cutoffs: PET has become a useful tool for measuring brain amyloid, a hallmark of Alzheimer’s disease, but what’s the right cutoff on the 100-point Centiloid scale for a positive scan? A recent JAMA Network Open meta-analysis of 49.2k patients from 53 studies proposes anything above 26 Centiloids as the threshold. Values lower than 11 can be considered negative, while intermediate scores may merit more testing, since they could reflect early amyloid development or issues with the scan.
- CARPL Raises $10M for Expansion: Radiology AI platform company CARPL.ai raised $10M in a Series A funding round to fuel new product development and international expansion. CARPL is also developing plans to expand beyond its core market in radiology “to become the integration, utilization and procurement layer for all clinical AI that goes into healthcare organizations.” The company has its eye on pathology, genomics, and general medicine as the first new markets it is targeting.
- Cubresa Bags Brain PET Clearance: Canadian PET developer Cubresa received FDA 510(k) clearance this month for BrainPET, a removable PET insert that enables MRI scanners to perform brain PET/MRI scans. The product includes a custom MR transmit/receive coil that enables acquisition of high-resolution MR images, and it can be integrated with scanners from major MRI vendors. Cubresa signed an R&D agreement with Siemens Healthineers in 2025 that focuses on integrating BrainPET with Siemens’ Terra and Terra.X 7T MRI scanners.
- Spectrum Dynamics Updates Digital SPECT/CT: SPECT developer Spectrum Dynamics Medical updated its flagship Veriton-CT 400 SPECT/CT system to enable it to image radiopharmaceuticals at low, medium, and high energies without the need to change collimators. A Veriton-CT 400 system with the all-energy enhancement is in operation at Florida Theranostics in Jupiter, Florida, where it’s been used for whole-body imaging of indium-131 at a low diagnostic dose. Wider commercial availability is expected in Q4 2026.
- Breakthrough Device Misnomer: STAT’s freshly updated Breakthrough Device Tracker shows that most “breakthrough” devices haven’t lived up to the name. Only 198 of the nearly 1.3k devices have gone on to be authorized, and most of the remaining solutions have been sitting off the market for over four years. The FDA’s breakthrough designation was designed to expedite regulatory review for devices that could eventually prove to be “more effective” at treating or diagnosing deadly conditions, but it has no bearing on whether a device will get authorized.
- ThinkSono Scores FDA Nod for Guidance Software: One of the lucky ones is U.K. AI software developer ThinkSono, which received FDA 510(k) clearance earlier this month for ThinkSono Guidance, the company’s application for helping inexperienced ultrasound operators detect blood clots. ThinkSono Guidance was reviewed under the FDA’s breakthrough device program, and received EU approval in 2024. The FDA nod paves the way for ThinkSono to enter the lucrative U.S. market, where as many as 900k people a year are affected by deep vein thrombosis.
- Provect Scores 3D C-Arm Clearance: Startup Provect AI received FDA 510(k) clearance for software that enables standard mobile C-arms to acquire intraoperative 3D images for spine and orthopedic procedures. Provect’s software is designed to capitalize on CMS’ addition of spine CPT codes that mirror the migration of surgical procedures to ambulatory surgery centers, where advanced 3D imaging with CT scanners often isn’t available. Simultaneously, the company announced a $7M funding round to fuel further commercialization of its technology.
- SimBioSys Syncs Up with Ferrum: Precision medicine company SimBioSys partnered with Ferrum Health to expand access to its AI tool that turns breast MR images into 3D visualizations. TumorSight Viz will now be available across Ferrum’s Model Hub, a platform of >60 clinical AI applications. The partnership comes nearly two years after SimBioSys’ second FDA clearance for new functionality with TumorSight Viz, which has impressive stats of its own: >70% of physicians who’ve used the system rate it valuable or very valuable.
|
|
Built for Today’s Demanding ORs
The Persona C HR mobile C-arm from Fujifilm Healthcare Americas combines high-power performance, ultra-low-dose imaging, and surgeon-friendly control – all in a lightweight, spacious design. Discover its advantages today.
|
|
Don’t Just Replace Reporting. Reimagine It
A reporting transition is a rare opportunity to improve workflow, reduce friction, and build for what’s next. See why health systems like Yale and Emory are choosing Rad AI’s modern reporting platform. Book a demo.
|
|
Interpretation Efficiency in Radiology – A Critical Strategy
Healthcare institutions are at a critical stage, where an emphasis on interpretation efficiency needs to be a priority. Check out this white paper from Visage Imaging and Signify Research on strategies to optimize your interpretation efficiency.
|
|
- Scaling Innovation in Radiology: In this episode of Medality’s The Radiology Report Podcast, host Daniel Arnold sat down with Subtle Medical CEO Ohad Arazi to discuss evolution of radiology AI and why improving image acquisition is an impactful way to improve patient care.
- AI-Assisted Radiology Reporting: Move beyond legacy radiology reporting with AI-assisted reporting from Mosaic Technologies. See how Mosaic Reporting can help your organization move faster today while building for tomorrow.
- Leveraging AI-Powered Discovery for Image Exchange: Southwest Medical Imaging, a premier physician-owned radiology practice in the southwestern U.S., partnered with Medicom to streamline their workflow. Discover how they utilize Medicom’s AI-powered Smart Search, which leverages an LLM to automatically detect and surface imaging data, to eliminate manual searching and accelerate patient care.
- How to Choose Between Tableside and Remote Fluoroscopy: Need help deciding whether tableside or universal remote fluoroscopy is right for you? This whitepaper from Siemens Healthineers may be able to put things in perspective.
- The Path to Digital Pathology: Hospital for Special Surgery in New York City had a vision: digital pathology coupled with fully integrated radiology, all in one enterprise imaging system. Learn how they turned this vision into reality on this page from Sectra.
- A Next-Generation Oncology Ecosystem: Quibim has launched their next-generation oncology ecosystem platform. Find out how QP-Prostate provides a comprehensive, end-to-end management workflow for prostate cancer care, supporting clinicians from the earliest stages of image acquisition through diagnosis, patient management, and follow-up.
- Singapore’s National AI Imaging Platform: AimSG, Singapore’s national radiology AI platform, is powered by CARPL to support third-party and in-house AI through a single, secure pipeline. See how CARPL powers healthcare across Singapore.
- Can You Meet Conditional MRI Requirements? How confident are you that your MR practice can meet the MR Conditional requirements? Philips has developed ScanWise Implant to simplify scanning patients with MR Conditional implants. Learn more on this page.
- Next-Generation DICOM SR Workflow Engine Messaging: The accelerating adoption of AI-powered radiology reporting has propelled replacement of legacy speech recognition integration technology. Discover how Altamont Software’s Passport SR can help you manage the shift with a modern DICOM SR engine.
- Adding AI Automation to Radiology Reporting: Reporting Pro from DeepHealth is a next-generation AI-powered solution designed to transform the way radiologists generate clinical reports and findings. Discover how it can transform your practice.
- Top Health Systems Are Providing Patient-Friendly Reports: Scanslated is the digital patient experience platform trusted at scale by Duke Health, Lumexa Imaging, and other patient-centric healthcare providers. Find out how Scanslated can work for you today.
- The Economics of AI-Assisted Heart Failure Diagnosis: An AI-assisted diagnostic pathway for diagnosing heart failure saved $1.4k per patient – without compromising diagnostic accuracy. Read the white paper from Us2.ai.
- Elevating Outpatient Imaging in Texas: River Oaks MRI & Diagnostic in Texas was founded on a simple but powerful idea: to bring high-quality, accessible imaging to the local community. Learn how they turned to United Imaging to help realize their vision.
- Connected Imaging. Empowered Flow: Know those rare and indescribable moments at work when distractions melt away? AGFA HealthCare’s Enterprise Imaging Platform is designed to keep you in that hyper-focused state of mind all day long. Learn more about their solutions today.
- Fewer Biopsies, Better Accuracy: AI is converging with TI-RADS and BI-RADS in ways that go beyond automation. Read this article from Kailo Medical to learn how structured reporting is reducing unnecessary biopsies, improving consistency, and reclaiming clinical time.
- Driving Advances in Lung Health Through Early Detection: Earlier detection of chest conditions leads to more effective treatments and patient outcomes. Learn more about lung diseases, the impact of early detection, and tools from Riverain Technologies to improve detection accuracy and efficiency.
- 8 Ways Merge Meets Enterprise Imaging Requirements: Merge enterprise imaging solutions deliver measurable value through continued innovation, thoughtful design, and flexible deployment. Learn how they can benefit your organization today.
- Remote Reading Is Essential for Enterprise Imaging: Remote reading has become essential to enterprise imaging operations because healthcare organizations need scalable, flexible solutions. Discover how cloud-based solutions from Intelerad can help solve remote reading challenges.
|
|
|
|
|
