|
US + Mammo vs. Mammo + AI | CrowdStrike’s Imaging Impact
July 25, 2024
|
|
|
|
|
Together with
|
|
|
|
“The world needs to up its software game massively. We need to invest in improving software reliability and methodology, not rushing out half-baked chatbots. An unregulated AI industry is a recipe for disaster.”
|
|
Scientist and author Gary Marcus, on the impact of the CrowdStrike outage.
|
|
|
|
Artificial intelligence may represent radiology’s future, but for at least one clinical application traditional imaging seems to be the present. In a new study in Radiology, ultrasound was more effective than AI for supplemental imaging of women with dense breast tissue.
Dense breast tissue has long presented problems for breast imaging specialists.
- Women with dense breasts are at higher risk of breast cancer, but traditional screening modalities like X-ray mammography don’t work very well (sensitivity of 30-48%), creating the need for supplemental imaging tools like ultrasound and MRI.
In the new study, researchers from South Korea tested the use of Lunit’s Insight MMG mammography AI algorithm in 5.7k women without symptoms who had breast tissue classified as heterogeneously (63%) or extremely dense (37%).
- AI’s performance was compared to both mammography alone as well as to mammography with ultrasound, one of the gold-standard modalities for imaging women with dense breasts.
All in all, researchers found …
- Mammography with AI had lower sensitivity than mammography with ultrasound but slightly better than mammography alone (61% vs. 97% vs. 58%)
- Mammography with AI had a lower cancer detection rate per 1k women but higher than mammography alone (3.5 vs. 5.6 vs. 3.3)
- Mammography with AI missed 12 cancers detected with mammography with ultrasound
- Mammography with AI had the highest specificity (95% vs. 78% vs. 94%)
- And the lowest abnormal interpretation rate (5% vs. 23% vs. 6%)
The results show that while AI can help radiologists interpret screening mammography for most women, at present it can’t compensate for mammography’s low sensitivity in women with dense breast tissue.
In an editorial, breast radiologists Gary Whitman, MD, and Stamatia Destounis, MD, observed that supplemental imaging of women with dense breasts is getting more attention as the FDA prepares to implement breast density notification rules in September.
- They recommended follow-up studies with other AI algorithms, more patients, and a longer follow-up period.
The Takeaway
As with a recent study on AI and teleradiology, the current research is a good step toward real-world evaluation of AI for a specific use case. While AI in this instance didn’t improve mammography’s sensitivity in women with dense breast tissue, it could carve out a role reducing false positives for these women who get mammography and ultrasound.
|
|
|
Turning Medical Imaging into Great Medicine
TeraRecon is continually innovating to bring the latest in advanced visualization capabilities to radiology. Intuition 4.7 includes a variety of new features, from structural heart workflow to the ability to trigger AI on demand. Learn more about them on this page.
|
|
Advancing Enterprise Imaging
Learn about the transformative impact of AI and cloud-based solutions for enterprise imaging in this August 1 webinar hosted by the HIMSS-SIIM Enterprise Imaging Community and supported by AGFA HealthCare. Continuing Education (CE) credit available.
|
|
- CrowdStrike’s Imaging Impact: How seriously was radiology affected by last week’s global IT outage, caused by a bad software update from cybersecurity firm CrowdStrike? Disruptions to healthcare systems definitely occurred, as documented in publications like Healthcare Brew and Healthcare Dive, but providers seemed to avoid a full breakdown like what occurred in the airline industry. Also, some hospitals were able to send studies to teleradiology firms that weren’t affected. For an inside look at the outage’s impact on radiology providers, check out the thread on RadHQ.net’s forums.
- Microsoft Partners for Radiology AI: Microsoft has signed alliances with Mass General Brigham and University of Wisconsin to use foundation models for developing radiology AI algorithms. Each partner will use foundation models running on Microsoft’s Azure cloud to develop and fine-tune AI algorithms for use cases such as more efficient chest X-ray interpretation or searching a patient’s EHR data before an MRI scan to see whether they have implanted devices. Developed algorithms can be offered over Microsoft’s Nuance Precision Imaging Network or third-party platforms.
- RSNA Narrows Gender Gap: Radiology has one of the widest gender gaps in medicine, but the chasm appears to be narrowing in terms of at least one metric: leadership positions at RSNA, the field’s largest professional organization. A new editorial in RadioGraphics notes that in 2023 compared to 2014, female representation has gone up for RSNA annual meeting speakers (43% vs. 29%), committee chairs (42% vs. 28%), and board of trustees for the RSNA Research & Education Foundation (42% vs. 17%). About 27% of active U.S. diagnostic radiologists are female.
- AbbaDox and Merge Partner on RIS: Imaging IT companies AbbaDox and Merge Healthcare Solutions have signed a partnership focusing on radiology workflow at ambulatory radiology sites. Merge for years has offered its own RIS and document management products, but under the new relationship Merge will discontinue these offerings and begin referring customers to AbbaDox immediately. The deal concerns potentially hundreds of users of Merge RIS and Unity RIS that will be referred to AbbaDox and its CareFlow cloud-native RIS.
- Variation in CT Radiation Dose: CT radiation dose varied widely between scanners in a new study in European Journal of Radiology, underscoring the need to standardize scanning protocols. Researchers analyzed radiation dose for abdominal imaging between 40 CT scanners from four different vendors at 33 Norwegian radiology departments. CTDIvol ranged from 3.5 mGy to 12 mGy (median of 5.3 mGy); image quality also varied greatly and corresponded only weakly to radiation dose. Scanners from the same vendor had the biggest variations, most likely due to technological differences.
- PAIRE AI Added to deepc Platform: AI platform company deepc is partnering with PAIRE to add its Pious whole-body PET/CT AI solution to the deepcOS platform. Pious automatically detects, segments, and quantifies hypermetabolic lesions on FDG PET/CT exams, highlighting contours and quantifying biomarkers such as total metabolic tumor volume and total lesion glycolysis.
- Del to Buy Guerbet Urology Biz: X-ray vendor Del Medical has signed an agreement to acquire Guerbet’s urological imaging business, including its L-F Hydra Vision digital imaging system. Gurbet originally acquired the business in 2015 as part of its acquisition of Mallinckrodt’s contrast division, which had been selling urology products under the Liebel-Flarsheim brand. Del sees Hydra Vision as a good fit with its own digital X-ray systems, and plans to move manufacturing to its plant in Bloomingdale, Illinois.
- Us2.ai’s LV Evidence: A new Frontiers study further supported echo AI’s potential, finding that Us2.ai’s AI solution measured left ventricular volume and function as well as human readers, and outperformed the 3D Heart Model. Among 109 patients, Us2.ai’s LV volume measurements were strongly correlated with the human operators (r=0.89 for LVEDV, r =0.92 for LVESV), producing higher correlations than between the two human readers themselves (r 0.74 and r=0.84) and the 3D Heart Model.
- Rads Rank High for Innovation Payments: Radiologists only brought in 2.8% of the nearly $13B in industry payments to physicians from 2017 to 2022, but imaging specialists ranked fourth highest in share of payments for royalties/ownership (33%) and research (9.9%) – considered a mark of innovation (consulting fees made up the third category). In a new paper in Clinical Imaging, researchers tallied industry payments to various medical disciplines, finding that radiology was outranked only by surgical specialties for royalty/ownership payments.
- Qure Scores Canadian Nod: Qure.ai is poised to enter the Canadian market after receiving a class III medical device license for its full portfolio of radiology AI solutions. The registration covers the company’s qXR tool for detecting a wide range of abnormalities on chest X-rays; qCT solution for lung nodule management on chest CT; and qER for triaging critical brain CT findings such as stroke and traumatic brain injury. The registration adds to Qure’s growing portfolio of approvals, such as FDA clearance of the qXR-LN lung nodule algorithm.
- AI for Chest CT Nodules: In other Qure.ai news, a new paper in European Radiology evaluates the company’s qCT AI-powered computer-aided detection software for detecting and characterizing lung nodules on CT scans. Researchers found that for 183 nodules, qCT’s performance was slightly lower than a radiologist’s for detection sensitivity (81% vs. 90%) with texture classification sensitivity of 77%, but the algorithm detected some lung nodules the radiologist missed and thus could improve single-reader performance by 7%. The authors recommended that AI algorithms be validated with real-world studies.
- Qatar Adopts Mammography AI: Qatar will be deploying Lunit’s Insight MMG AI solution in its national breast screening program, making it the first country in the Middle East to adopt AI for breast screening at the national level. Qatar began testing Insight MMG in March 2023 and moved to fully implement AI in its Screen for Life program last month. Under the five-year contract, two radiologists will read each mammogram while referring to Insight MMG results.
- Gleamer Added to Siemens AI Marketplace: Gleamer’s BoneView AI solution has been added to Siemens Healthineers’ Digital Marketplace, which hosts imaging apps from the multimodality OEM and its partners. BoneView analyzes X-rays to detect signs of fracture that radiologists may have missed; Gleamer has been expanding its relationships with AI marketplace and platform companies like Siemens and Ferrum Health.
- CARPL Partners with AdvaHealth: AI platform company CARPL.ai is partnering with AdvaHealth Solutions, a New Zealand-based developer of the cloud-based AdvaPACS software. The agreement will enable AdvaPACS users to seamlessly integrate CARPL’s AI platform into their workflow. CARPL has been partnering with a number of PACS companies of late, such as with Philips in Brazil.
- Materialise Acquires FEops: Major 3D technology company Materialise expanded its cardiovascular imaging capabilities with the acquisition of structural heart simulation startup FEops. The acquisition will allow Materialise to combine its Mimics Planner for Structural Heart Interventions solution (creates 3D models for segmentation and anatomical analysis) with FEops’ predictive simulation technology. This combination of anatomy-based 3D planning and AI-based simulation could improve interventionalists’ ability to predict how transcatheter structural heart devices will interact with a patient’s anatomy, allowing more personalized care decisions.
|
|
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.
|
|
Image Sharing to Improve Patient Outcomes
In this case study, learn how AdventHealth improved treatment planning and delivery because of Nuance PowerShare’s immediate connection to other sites in the network for medical image sharing.
|
|
Introducing Merge Consulting Services
How can your radiology practice manage change and expectations in healthcare with workforce flexibility? Merge by Merative is launching Merge Consulting Services to help you face the challenges of sourcing expertise and staff. Learn more about it today.
|
|
- Starting a CT Lung Cancer Screening Program: There’s no doubt CT lung cancer screening reduces lung cancer mortality. In this Imaging Wire Show, we discuss how to set up CT lung screening and the technologies available to help with Chip Gilkeson, MD, of University Hospitals Cleveland Medical Center and Steve Worrell of Riverain Technologies.
- The Radiology Report with Francis Deng, MD: In this episode of The Radiology Report podcast, Medality Co-Founder and CEO Daniel Arnold talks to Francis Deng, MD, about his decision to enter neuroradiology. Listen to this episode as well as other interviews with leaders in radiology.
- Go Virtual with Ease: Visage Imaging’s new Visage Ease VP solution makes it easy for you to take advantage of the unique clinical capabilities of the new Apple Vision Pro spatial computing environment. Learn how it can change your practice today.
- Women’s Health and AI: With new breast density reporting requirements coming in the US, there’s a need for objective density assessment and reporting. Check out this article from Blackford Analysis on the AI solutions that can help.
- Are You Getting the Most Out of Your Image Exchange Solution? On this page from PocketHealth, ask yourself these 5 questions to find out whether your enterprise image exchange solution is maximizing patient satisfaction, efficiency, and driving revenue.
- Data Quality Issues in Healthcare: Data quality issues in healthcare are common challenges that can impact patient care, research, and overall healthcare management. Learn how data standardization solutions like Enlitic’s ENDEX can help by ensuring complete, accurate information.
- Break Down Boundaries in Healthcare: Break down boundaries in healthcare with Intelerad’s InteleShare image sharing solution. InteleShare brings you enhanced access that bridges the gap between care teams and patients to ensure that distance is no barrier to quality care.
- 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.
- AI Improves Hand and Wrist Fracture Detection: Learn how Gleamer’s BoneView AI algorithm for detecting fractures in the hand and wrist on X-ray improved radiologist performance in a recent paper in European Radiology.
- Driving the Future of PET/CT: Learn about the future of PET/CT with Biograph Trinion with myExam Companion from Siemens Healthineers. Read insights from the first customers and see how they have transformed their PET/CT workflow, giving them more time for patient care.
- Re-Examining Radiology: A Look to the Future: What will the future of radiology look like? In this downloadable white paper from Optum, learn how a constellation of challenges and pressures have come together to change healthcare – and radiology.
- What is Cloud Computing? What do you know about cloud computing and its role in healthcare? Check out this article by Sham Sokka, PhD, of DeepHealth to learn how cloud computing is helping hospitals adopt new AI technologies that enhance patient care.
- Presenting Unboxing AI: Check out CARPL’s video series, Unboxing AI, featuring experts discussing AI and its future in radiology. The next episode on July 26 features Ryan Lee, MD, of Thomas Jefferson Univeristy – reserve your seat today.
|
|
|
|
|
