|
AI for PE Detection, FDA Turmoil, and Late-Stage Breast Cancer Rises
May 14, 2026
|
|
|
|
|
Together with
|
|
|
|
“Radiologists should avoid overreliance on AI, remain vigilant in search patterns, and scrutinize AI-positive results. The clinical value of the AI tool is maximized under discerning, radiologist-led oversight.”
|
|
Goldberg-Stein S et al, in a new study of real-world AI for PE detection.
|
|
|
Happy Thursday! The departure of Marty Makary, MD, as FDA commissioner this week was widely expected. But what’s less certain is the direction the agency will take in months and years to come. Makary was sunk by political cross-currents that aren’t going to subside any time soon. The question is how the turbulence will affect the agency’s ability to oversee medical drugs and devices – especially new marketing authorizations. Stay tuned. – Brian Casey, Managing Editor
|
|
|
|
AI made a “selective but meaningful” contribution to radiologist interpretations of CT pulmonary angiography scans for pulmonary embolism. The study, published in Radiology: Artificial Intelligence, offers valuable insights into real-world implementation of AI on a large scale.
One of the major criticisms of AI is that algorithms used in real-world clinical situations don’t perform as well as they do in the controlled environments that vendors use to acquire data for regulatory submissions.
- AI performance can drop off as much as 20 to 30 percentage points for important metrics like sensitivity and specificity.
The new study sought to investigate this phenomenon by analyzing a real-world implementation of Aidoc’s AI algorithm for PE detection.
- Researchers assessed the algorithm’s performance for analyzing CTPA exams across a variety of clinical environments in an integrated health network, including the emergency department and inpatient and outpatient settings.
Scans of 29.5k patients acquired from 2021 to 2023 were included. AI analyzed images in real time, after which exams were interpreted by radiologists who knew the AI findings. Researchers found…
- Radiologists using AI had higher sensitivity than the algorithm on its own (99% vs. 85%).
- Specificity was more or less the same (99.8% vs. 99.5%).
- Agreement between radiologists and AI was high (98%).
- Agreement was higher when AI assessed cases as negative rather than positive (98% vs. 94%).
- Radiologists disagreed with AI in 2.2% of cases. The final determination by a panel of expert thoracic radiologists strongly favored radiologists (89%).
- Of the 3.3k cases positive for PE, 0.81% were detected only by AI – or 26 cases.
In analyzing the results, the researchers characterized AI’s contribution as “selective but meaningful.”
- AI-positive results meant scans might require more scrutiny from radiologists, while an AI-negative call might be supportive – but not definitive – for negative PE.
The Takeaway
The new study of AI for PE detection is a fascinating look at real-world AI deployment. While the sensitivity, specificity, and agreement numbers are interesting, what draws our attention is the 26 PE cases caught only by AI over 18 months of use. That boils down to 26 patients whose clinical condition wasn’t missed, and 26 potential malpractice lawsuits that were never filed.
|
|
Visit Quibim at ASCO 2026
Stop by Quibim’s booth at ASCO 2026 to learn how they are redefining the future of oncology through their innovative AI-based diagnostic and predictive imaging biomarkers. Book a meeting today or drop by at booth #27149.
|
|
Bring Your Radiology AI into Your Clinical Workflows
CARPL enables healthcare providers and researchers to develop, test, and deploy their own AI models within existing clinical infrastructure. From seamless data ingestion and de-identification to model training, packaging, and live deployment, CARPL provides an end-to-end environment tailored for radiology.
|
|
Radiology Case Report
A man in his 40s presented with a known metastasis within his abdomen. Learn how contrast-enhanced MRI helped to diagnose the extent of his disease.
|
|
- FDA Turmoil Continues: Turmoil at the FDA continued this week with the departure of Commissioner Marty Makary, MD. Makary’s departure had been rumored for weeks as he was caught between the FDA’s traditional role in regulating the food and medical industries and demands for more rapid change by the Make America Healthy Again movement. Makary also presided over a year of personnel cuts that slashed the FDA’s workforce up to 21%, resulting in plummeting morale among the staffers remaining.
- Rise in Late-Stage Breast Cancer: The incidence rate of late-stage breast cancer rose over the last 15 years in the U.S. A paper in JAMA Network Open tracked the changes in 761.5k breast cancer cases, finding stage IV incidence per 100k women was 18% higher in 2021 compared to 2010 (11.2 vs. 9.5 cases). It’s worth noting that the USPSTF in 2009 removed its recommendation that women in their 40s undergo routine breast screening, which has been associated with lower utilization of screening mammography.
- AI for Brain MRI Helps Diagnose Stroke: Researchers used AI software from RapidAI to help assess the extent of damage on MRI scans of 291 patients with large-vessel occlusion ischemic strokes. In a new study in Stroke, RapidAI generated scores for core blood-brain barrier disruption, a measure of the number of “leaky” voxels in the ischemic core. For every 1% increase in cBBB, a patient’s odds of having a poor functional outcome increased by 16%.
- Philips Launches Titanion 3T MRI at ISMRM: Philips debuted a new 3T MRI scanner with ultra-high-gradient performance at this week’s ISMRM 2026. Called Titanion, the system features gradients rated at a strength of 150 mT/m and a slew rate of 250 T/m/s and is designed for both clinical and research use. The powerful gradients, when combined with AI analysis, improve visibility of microstructural tissue and will improve research into areas like quantitative analysis of biomarkers that reflect tissue function and can be early hallmarks of disease.
- CT Lung Screening Still Saves Lives: CT lung cancer screening is still a life-saving test. New research in JACR found that people who had lung cancer not found on screening had 3X the mortality as those with cancers found through screening. In 141 people diagnosed with lung cancer, those without screen-detected cancer had a higher mortality risk (HR = 3.16) after five years. But as with another recent study, lung cancer-specific mortality per 100k patients was higher than in the landmark NLST trial (317 vs. 247 deaths).
- Program Achieves High Lung Screening Adherence: A program using low-dose CT to screen nuclear weapons workers for lung cancer achieved an eye-popping 89% year-to-year adherence rate. Researchers describe in a paper in Clinical Lung Cancer how they screened 1.5k high-risk workers under a program sponsored by labor unions and the U.S. Department of Energy. Eligible participants underwent eight screening rounds over 10 years, with 31% completing all eight rounds. Authors said including occupational risk in screening criteria can improve eligibility and may boost adherence.
- Supplemental Breast Ultrasound for Recurrence: Supplemental breast ultrasound turned in mixed results when added to mammography for screening women with a personal history of breast cancer. Researchers in European Journal of Radiology added ultrasound to surveillance mammography of 992 women, some who had previously received breast-conserving surgery and some mastectomy. Ultrasound did not detect any additional breast cancers but found three recurrences in the axillary lymph nodes, while leading to a higher biopsy rate and more follow-up studies. Other studies have found a higher cancer detection rate for supplemental ultrasound.
- Enlitic Enters New Global Market: Data standardization software developer Enlitic is entering a new global market, with the company scoring its first installation in New Zealand. RHCNZ Medical Imaging Group went live with Enlitic’s Ensight software this week, with an initial focus on using the application to improve hanging protocols by standardizing how medical images are presented to radiologists. RHCNZ is the largest private radiology provider in the country, operating over 65 clinics.
- Tracking Plaque with Serial CCTA Scans: Coronary CT angiography is an ideal way to measure coronary plaque, but what’s the best way to follow it over time? In a new paper in European Radiology, researchers present a novel technique using AI to analyze serial CCTA scans reviewed side-by-side to quantify and track plaque changes. In a proof-of-concept study with 30 patients, they found high scan reproducibility for quantifying plaque burden and volume, suggesting the technique could track the effectiveness of plaque-reduction interventions.
- Brainomix Expands Pharma Relationship: Imaging companies continue to make inroads with pharmaceutical developers. Brainomix is the latest firm to get in on the trend, expanding its agreement to provide its e-Lung software to Boehringer Ingelheim, which makes treatments for interstitial lung disease in patients with progressive pulmonary fibrosis. In the PROGRESS-PPF study, researchers will test whether e-Lung can help clinicians diagnose PPF earlier, enabling more rapid treatment with Boehringer Ingelheim therapies.
- MARS to Supply Bracco with PCCT: In another example of the growing synergy between imaging and drug development, contrast company Bracco Imaging acquired a mobile photon-counting CT scanner from MARS Bioimaging. The scanner will be installed at a Bracco R&D center in Italy and will be used on a research project to investigate how AI and advanced imaging technologies like PCCT can improve contrast characterization. MARS received FDA clearance for the scanner in March.
- NVision Raises $55M for Quantum Computing: German quantum technologies developer NVision raised $55M in a Series B round to expand its focus from quantum sensing into quantum computing. The company’s POLARIS technology boosts MRI signals to enable real-time metabolism measurement, and during R&D studies the company discovered a new class of organic molecule-based qubits – atom-scale units – that could be used with POLARIS to design and validate drug candidates.
|
|
Building Bridges Across Imaging Informatics
Visit Medicom at booth #615 at SIIM 2026 to see how their automated workflows move every image to where it needs to go, connecting patients, providers, EHRs, and research teams without manual workarounds. Book your demo today.
|
|
Experience Dynamic Simplicity in Fluoroscopy
Introducing LUMINOS Q.namix R and LUMINOS Q.namix T from Siemens Healthineers – truly multifunctional imaging systems designed to simplify your daily work routines and amplify your capabilities. Learn from your peers what makes LUMINOS Q.namix systems so special.
|
|
A New Solution for Radiology Reporting
Sectra Reporting delivers a fully built-in, AI-enhanced reporting experience that seamlessly connects PACS imaging data and measurements through intuitive templates. Discover how it can meet your needs today.
|
|
- AI Echo Tracks Progression of Cardiac Amyloidosis: A recent study evaluated over 750 echocardiograms from patients with transthyretin cardiac amyloidosis (ATTR-CM) using Us2.ai software to track structural and functional heart changes over time. Find out how well it worked on this page.
- Meet Merge at SIIM 2026: Built with clinical and technical expertise, guided by customer insights, and personalized to your needs, Merge imaging solutions deliver reliable imaging, less complexity, and better care. Learn more by booking a meeting at SIIM 2026, or stop by booth #204-206.
- AI-Powered Referral Automation: Radiology teams are drowning in referrals, and a huge chunk of that burden is purely administrative. Kailo Medical built a solution to fix that: An AI-powered referral automation workflow that handles the full intake process. Find out how it works today.
- An AI-Powered Solution for Fracture Detection: Gleamer’s BoneView provides radiologists and clinicians with an instant and automatic second reading of trauma bone X-rays, fully integrated into the reading workflow.
- Connect Imaging Across Every Care Setting: Join Intelerad at SIIM 2026 to learn how you can connect imaging across every care setting, eliminate disks, and accelerate diagnosis with a network clinicians trust. Book a demo today or drop by booth #305.
- From Radiology Resident to Company Founder: In this episode of Medality’s The Radiology Report Podcast, Dor Shoshan, MD, founder and CEO of ContrastConnect, shares how he went from radiology resident to founder of a platform for virtual contrast supervision now used by hundreds of imaging centers nationwide.
- Making AI Work for Radiology: Watch this webinar from Philips to learn practical strategies, real‑world results, and what it takes to successfully scale AI for radiology at your hospital or health system.
- Accelerating Imaging Workflows in Radiology and Cardiology: Radiology and cardiology are turning to enterprise imaging platforms to break out of silos and benefit from shared medical image management. Join AGFA HealthCare to discover what this looks like in a live discussion on Tuesday, May 19 at 12 pm ET.
- Cutting-Edge PET/CT to Support Theranostics: Theranostics is an exciting new field that combines diagnostics and therapy. Discover how Florida Theranostics is using United Imaging’s uMI Panorama PET/CT scanner to establish a high-quality level of patient care.
- Opportunistic Detection of CAC and Pulmonary Nodules: Achieve a newfound certainty of search for thoracic CT when using ClearRead CT from Riverain Technologies. It’s a natural addition for opportunistic CAC scoring and nodule detection, or as part of a CT lung cancer screening program.
- Unlock Next-Level Diagnostic Possibilities: Photonova Spectra from GE HealthCare is designed to realize the full potential of photon-counting CT in oncology, cardiology, neurology, and more. Learn more about the difference its Deep Silicon technology makes on this page.
- This Is a Reporting Reset Moment: A forced reporting transition isn’t just a replacement — it’s a chance to rethink workflow, efficiency, and the radiologist experience. See how modern reporting from Rad AI supports the reading room without disruption. Book a demo.
- Transforming Radiography with Automation Intelligence: FDR Visionary Suite from Fujifilm Healthcare Americas is an innovative digital radiography solution designed to enhance the experience for both technologists and patients. It delivers impressive speed and repeatability for efficient, faster workflow, with automated positioning and optional, fully automated advanced applications.
- Your PACS Wasn’t Built for Enterprise Imaging: Replace fragmented imaging workflows with a vendor-neutral enterprise imaging operating system from Mach7 Technologies that’s designed for interoperability, speed, and long-term flexibility. Learn more.
- The Power of a Smooth Go-Live: Don’t gamble on your healthcare institution’s go-live: take control of your PACS migration with ENDEX from Enlitic. Discover how ENDEX uses AI to standardize, normalize, and cleanse your imaging metadata before migration.
- Tackling Radiology’s Capacity Issue: Healthcare providers are under pressure from rising costs, care delays, and growing cybersecurity risks. Watch this video to discover how Mosaic Clinical Technologies delivers a future-ready imaging solution that improves continuity of care and accelerates detection for faster, more appropriate interventions.
- One Viewer for All: Achieve ultrafast image interpretation with greater efficiency and precision with Visage 7 from Visage Imaging. Visage’s one-viewer philosophy enables all end users – from radiologists to clinicians – to access powerful tools based on clinical need.
- Elevating Breast Cancer Detection: Breast Suite from DeepHealth is a new package of AI-powered solutions delivering increased breast cancer detection rates, risk stratification tools, and viewing and reporting workflow acceleration. Find out how it can benefit your practice today.
|
|
|
|
|
