|
AI Helps Rads Read Prostate MRI | Doc Fix Nixed
March 13, 2025
|
|
|
|
|
Together with
|
|
|
|
“The permanent fix we really need is to tie doc payments to the same automatic inflation adjustment factor as hospitals or [ambulatory surgery centers].”
|
|
Denali, in a post on RadHQ.net on the omission of a Medicare physician payment fix in 2025 budget legislation.
|
|
|
|
MRI is changing how prostate cancer is detected, diagnosed, and followed up. But even a technology as powerful as MRI could use a little help, as evidenced by a new study in Radiology showing that a commercially available AI algorithm could help radiologists diagnose clinically significant prostate cancer.
Workup of suspicious prostate lesions is being reshaped by MRI in meaningful ways.
- For example, MRI-guided biopsy is replacing systemic prostate biopsy without guidance, especially for patients with low to intermediate risk of prostate cancer.
But prostate MRI isn’t perfect – yet. Radiologist performance can vary due to differences in experience, as well as variations in MRI acquisitions, tumor location, and cancer prevalence. Could AI help even out these variations?
- To find out, researchers from South Korea tested Siemens Healthineers’ syngo.via Prostate MR algorithm in 205 patients suspected of prostate cancer who were scheduled for biopsy based on clinical information (including previous MRI scans).
The AI algorithm’s performance was compared to that of experienced radiologists, and researchers also estimated its impact on radiologist interpretation if used as a reading aid, finding that for clinically significant prostate cancer…
- AI had lower sensitivity versus radiologists (80% vs. 93%).
- But higher positive predictive value (58% vs. 48%).
- Adding AI to radiologists’ interpretation more than doubled specificity (44% vs. 21%).
- There were no cancer cases among lesions rated by both the algorithm and radiologists as not likely to be cancer (PI-RADS 1 or 2).
AI’s higher PPV indicates that it could help reduce unnecessary prostate biopsies, while also detecting clinically significant cancer that might have been missed by radiologists.
The Takeaway
The new findings echo previous studies that demonstrate the value of AI for MRI of prostate cancer, but differ in that they investigate a commercially available algorithm – indicating that tools for better prostate MRI are becoming accessible to radiologists.
|
|
|
Presenting Unboxing AI
Check out CARPL’s video series, Unboxing AI, featuring experts discussing AI and its future in radiology. The next episode on March 20 features Namita Gandhi, MD, of Cleveland Clinic – reserve your seat today.
|
|
Patient Attitudes Towards AI-Echo
The medical imaging field is rapidly accepting AI, but how are patients feeling about the shift? Get the scoop on patients’ positive opinions toward Us2.ai’s software that supports task-shifting from conventional echo to AI-echo.
|
|
- Doc Fix Nixed: U.S. healthcare providers may have to wait longer for a fix to a 2.8% cut in Medicare reimbursement that went to effect in January. Language that would have implemented a “doc fix” was not included in budget legislation passed by the House of Representatives this week, raising the ire of physician groups already stung by failure of a fix late last year. Republican representatives, however, say they expect to work a fix into the reconciliation package by the time it’s finished.
- Mammo AI Improves Rads’ Performance: Radiologists using Lunit’s Insight MMG algorithm for single reading of screening mammograms had better performance than those reading without AI. In results published in Nature Communications from the AI-STREAM study in South Korea, researchers used Insight MMG with 24.5k women, finding that AI-aided radiologists had a 14% higher cancer detection rate (5.7% vs. 5.01%) with no statistically significant difference in recall rates. The study adds to the growing body of evidence supporting AI for breast screening.
- FDA Clears Siemens’ Photon-Counting CT: The FDA cleared Siemens Healthineers’ Naeotom Alpha class of photon-counting CT scanners, which Siemens launched last year to create lower price points in its photon-counting CT line. The Alpha class includes the Alpha.Pro dual-source photon-counting scanner and Alpha.Prime single-source system. Siemens’ flagship Naeotom Alpha dual-source scanner, which FDA cleared in 2021, has been rebranded as Alpha.Peak and remains at the top of the company’s photon-counting product line.
- AI-Generated Reports Speed Turnaround: A generative AI algorithm developed by South Korean startup Soombit.ai sped up radiology report turnaround for chest X-rays in a new study published in Radiology. Radiologists read 758 chest radiographs in sessions four weeks apart, first without and then with Soombit’s AIRead model, which generates preliminary reports for radiologist review. Average reading times for AI-generated reports fell (20 vs. 34 seconds), and sensitivity improved for some conditions like pleural effusion (87% vs. 78%) and widened mediastinal silhouettes (91% vs. 84%).
- Gleamer Moves into MRI with Acquisitions: Gleamer expanded out of its core business in musculoskeletal AI and into MRI, this week announcing its acquisition of two companies, Pixyl and Caerus Medical. Pixyl developed the Pixyl.Neuro application for MRI brain analysis to detect neurodegenerative conditions like Alzheimer’s disease, while Caerus develops AI algorithms for analyzing MRI scans for lumbar spine conditions like disc herniation, stenosis, and spondylolisthesis. With the acquisitions, Gleamer’s workforce now surpasses 100 employees across seven countries.
- ASRT Elects New Officers: Members of ASRT elected new officers for the 2025-2026 term in a special election. Leading the radiologic technologist organization as president will be Brandon Smith, a clinical instructor at GE HealthCare, while Marissa Mangrum of the University of Oklahoma Health Sciences Center was chosen as president-elect. Rounding out the organization’s slate are Shellie Pike of Radiology Consultants of Iowa, Amanda Grocott of Sanford Medical Center Fargo in North Dakota, and Emily Cash of Atrium Health Wake Forest Baptist in North Carolina.
- Blackford Partners with ACR’s AI Registry: Blackford is working with ACR to incorporate assessment results from ACR’s Assess-AI project into its AI orchestration platform. ACR launched Assess-AI last year to provide a central data registry to monitor AI algorithm performance in real-world clinical settings, and Blackford demonstrated its integration with the project at RSNA 2024. The collaboration will give clinicians practical insight into AI algorithm performance.
- Ontario Hospital Deploys Kailo Software: Niagara Health in Ontario, Canada deployed KailoFlow software from Kailo Medical for reporting obstetrical ultrasound scans. KailoFlow automates the process for OB ultrasound image acquisition, automatically capturing measurements and feeding them directly into the radiologist’s report. Niagara Health is the first hospital in Ontario to deploy the software.
- FDA Clears Caristo Plaque AI: The FDA cleared Caristo Diagnostics’ CaRi-Plaque AI algorithm for detecting coronary plaque to aid in the diagnosis of coronary artery disease. CaRi-Plaque detects markers of CAD progression to aid in predicting heart attacks, with clinicians sending CT data to Caristo via the cloud for processing. Caristo personnel review results and generate reports that are returned to users. Caristo noted that CaRi-Plaque users will be able to adopt its CaRi-Heart algorithm for coronary inflammation when it gets FDA clearance. Caristo raised $16.3M in 2023.
- Football for Heart Failure Outreach: Healthcare professionals are using the popularity of U.K. football to address heart failure underdiagnosis, underscoring the potential of combining point-of-care and AI-enabled tools. As part of Everton FC’s BEAT Breathlessness program, providers screened roughly 1k patients using the BEAT-HF questionnaire, NT-proBNP testing, vital sign readings, and a 30-second 6-lead ECG (Kardia). People with elevated NT-proBNP levels then underwent clinical exams and AI-interpreted echocardiography (Kosmos; EchoNous plus Us2.ai), which led to HF diagnosis in 3% of participants and potentially life-saving early care.
- 4DMedical Extends with Cleveland Clinic: 4DMedical extended its contract to provide its pulmonary function software to the Cleveland Clinic for another three years. In a contract with a minimum value of $143k, Cleveland Clinic will use 4DMedical’s software on a SaaS basis, and is also looking at expanding its relationship with the company to include other products.
- Avandra Raises $18M: Data aggregator Avandra raised $17.8M, just a few months after emerging from stealth in October. Avandra is building a federated network of de-identified medical imaging data and is pitching its services to biopharma and medical researchers as well as AI developers that need access to large, multimodality datasets that have been annotated and standardized.
- HIMSS Doubles Down on Vegas for 2026: HIMSS plans to hold the 2026 edition of its annual meeting in Las Vegas, one of the first times in recent memory it has held back-to-back conferences in the same city. HIMSS is so large it can usually only be held in one of the three U.S. cities with adequate conference space (Las Vegas, Orlando, and Chicago). HIMSS reported total attendance of over 28k people at HIMSS 2025, down slightly from about 30k at HIMSS 2024 in Orlando.
- Robots Impersonating Humans: A state bill introduced in California could prevent AI agents from passing themselves off as human healthcare providers. If signed into law, the legislation would extend regulators’ ability to enforce title protections, which reserve the use of professional job titles for people actually holding those titles (i.e. “nurse” or “doctor”). The bill’s author, Democratic CA State Representative Mia Bonta, said that “generative AI systems are not licensed health professionals, and they shouldn’t be allowed to present themselves as such. It’s a no-brainer to me.”
|
|
AI and Cancer Screening
Cancer screening saves lives, but right now screening is limited to a few cancer types. That could change with AI, which opens new possibilities for earlier disease detection. Learn more in this article by DeepHealth clinical AI leader Greg Sorensen, MD.
|
|
Preparing for the Future of Enterprise Imaging
What do health IT and imaging leaders need to know about moving medical images to the cloud? Find out how to prepare for enterprise imaging’s future in this downloadable e-book from Optum.
|
|
Join Clearpath at RBMA 2025 in Nashville
Discover why RBMA attendees trust Clearpath to streamline access to images and documents for legal requestors, patients, and healthcare providers. Don’t miss the chance to learn how they can help your organization – schedule a meeting or visit them at booth #211.
|
|
- Bayer’s ECR 2025 Highlights: What were the hot topics in Bayer’s booth at ECR 2025? We talked to company executives Nelson Ambrogio and Rich Dewit about their new innovations, from MRI contrast agents in development to Calantic Digital Solutions’ activities in AI.
- MRI That’s Lighter, Faster, and Sharper: Rise above and experience MRI excellence with Philips BlueSeal, the industry’s lightest, vent pipe-free, high-performance, helium-free 1.5T scanner. Watch this video to see how it can benefit your practice.
- AI Enables Automated Cobb Angle Measurements: Gleamer’s BoneMetrics AI solution accurately predicted the Cobb angle of scoliosis patients with high accuracy compared to manual measurements made by clinicians. Learn more in this paper.
- Helping Providers Deliver Critical Answers to Patients: Intelerad’s new InteleGence solution helps providers deliver critical answers to patients when they need them most by deploying AI tools to simplify workflows and assist in precision diagnostics. Learn more about how it works today.
- What Does Improved MRI Efficiency Mean? There’s a growing need for practical, cost-effective solutions to improve efficiency in MRI and other modalities. Read this article from Karen Holzberger of SpinTech MRI and James Backstrom, MD, to learn how the company’s STAGE software can help.
- Transform Your Practice into a Multispecialty Powerhouse: Medality is the practice development platform that helps radiologists upskill in high-growth, advanced imaging areas. Request a demo today and discover how to transform your practice into a multispecialty powerhouse.
- Powering Reporting Progress with Efficiency: Radiologists are looking to maximize their efficiency with new reporting tools that integrate easily with their PACS and RIS. Learn more about solutions from Kailo Medical in this Imaging Wire Show interview with Jason Mercieca and Dieter Smith.
- Unprecedented Insights Made Possible with AI: With the largest normative dataset of whole-body imaging in the world, Prenuvo’s AI researchers partner with the best academic minds to understand – like never before – what “normal” aging means. Learn about their work today.
- Best in KLAS for 2025: Merge Cardio and Merge Hemo from Merge by Merative have been ranked Best in KLAS for Cardiology and Hemodynamics, marking the 10th and 13th time respectively for these industry-leading solutions. Read this report to see how they compared to the competition.
- How to Standardize CT Images: The quality and appearance of CT scans can vary considerably. In this white paper from Riverain Technologies, find out how image normalization can standardize CT images, making them easier to analyze and interpret.
- AMRIC’s Multimodality Approach to Medical Imaging: AMRIC is a new premium imaging clinic on Manhattan’s Upper East Side. Learn about their multimodality approach to medical imaging and why they turned to United Imaging for cutting-edge CT, MRI, and molecular imaging technology.
- Simplifying Complex Image Exchange Workflows: Guadalupe Regional Medical Center and Methodist Hospital implemented a PocketHealth Community Gateway that saved over 1,700 staff hours. Read how they streamlined bidirectional image exchange, created operational efficiencies, and improved continuity of care for patients.
- A New Solution for Breast Density Classification: In a new research study in Clinical Imaging, see how Visage Imaging’s PACS-integrated Visage Breast Density application had high accuracy and agreement with radiologist assessments for classifying mammography exams into BI-RADS categories.
- A New Cloud-Based Viewing Solution: Mach7 Technologies has achieved a major milestone with the release of its eUnity Enterprise Diagnostic Viewer with the Amazon Web Services (AWS) HealthImaging Cloud. Learn how this solution creates simplicity for users while enabling faster diagnoses and better patient outcomes.
- Revolutionizing Medical Imaging Data Management: Enlitic has acquired Laitek, and the combination creates new possibilities to revolutionize medical imaging data management. Learn more about Laitek and how its advanced migration services can benefit your radiology practice.
|
|
|
|
|
