|
Low-Dose CT in Kids | Hinton Nabs Nobel, Cancels MRI
October 10, 2024
|
|
|
|
|
Together with
|
|
|
|
|
When it comes to pediatric CT scans, clinicians should make every effort to reduce dose as much as possible. But a new study in AJR indicates that lower CT radiation dose can affect the performance of software tools like computer-aided detection.
Initiatives like the Image Wisely and Image Gently projects have succeeded in raising awareness of radiation dose and have helped radiologists find ways to reduce it.
But every little bit counts in pediatric dose reduction, especially given that one CT exam can raise the risk of developing cancer by 0.35%.
- Imaging tools like AI and CAD could help, but there have been few studies examining the performance of pulmonary CAD software developed for adults in analyzing scans of children.
To address that gap, researchers including radiologists from Cincinnati Children’s Hospital Medical Center investigated the performance of two open-source CAD algorithms trained on adults for detecting lung nodules in 73 patients with a mean age of 14.7 years.
- The algorithms included FlyerScan, a CAD developed by the authors, and MONAI, an open-source project for deep learning in medical imaging.
Scans were acquired at standard-dose (mean effective dose=1.77 mSv) and low-dose (mean effective dose=0.32 mSv) levels, with the results showing that both algorithms turned in lower performance at lower radiation dose for nodules 3-30 mm …
- FlyerScan saw its sensitivity decline (77% vs. 67%) and detected fewer 3mm lung nodules (33 vs. 24).
- MONAI also saw lower sensitivity (68% vs. 62%) and detected fewer 3mm lung nodules (16 vs. 13).
- Reduced sensitivity was more pronounced for nodules less than 5 mm.
The findings should be taken with a grain of salt, as the open-source algorithms were not originally trained on pediatric data.
- But the results do underscore the challenge in developing image analysis software optimized for pediatric applications.
The Takeaway
With respect to low radiation dose and high AI accuracy in CT scans of kids, radiologists may not be able to have their cake and eat it too – yet. More work will be needed before AI solutions developed for adults can be used in children.
|
|
|
Get the 2024 Radiology Practice Development Report
Medality surveyed more than 3,300 radiologists and discovered the most critical training gaps and growth opportunities in radiology for its 2024 Radiology Practice Development Report. Download your complimentary report today.
|
|
AI for Lung Cancer Diagnosis and Screening
Check out this comprehensive new eBook from Calantic by Bayer on the role of AI in lung cancer diagnosis and screening. It explores AI’s potential role in improving lung cancer screening strategies, identifying high-risk individuals, and enhancing diagnostic accuracy. Download it today.
|
|
- Hinton Gets Nobel Prize for Physics: AI pioneer Geoffrey Hinton, PhD – who once said AI would replace radiologists by 2021 – was awarded the Nobel Prize for physics this week. The award was made to Hinton and fellow AI visionary John Hopfield, PhD, to recognize their early “foundational discoveries and inventions that enable machine learning with artificial neural networks.” Hinton’s comments on radiology in 2016 contributed to a sharp drop in radiology residency applications for the next several years before rebounding. Hinton later walked them back (slightly).
- Blackford Partners with GE: AI platform company Blackford has landed a big fish: GE HealthCare. The companies signed a partnership in which Blackford’s AI platform will be integrated with GE’s True PACS and Centricity PACS enterprise image management offerings. GE customers will get access to a wide range of third-party AI applications available on the Blackford Platform, and are expected to benefit from Blackford’s AI workflow orchestration. The deal represents a huge boost for Blackford, which has been aggressively adding AI algorithms to its platform.
- Heart Disease Linked to Dementia: A landmark new statement published in Stroke by the American Heart Association explains the ways in which the three major cardiovascular diseases – heart failure, atrial fibrillation, and coronary artery disease – are linked to dementia. Cardiovascular health and brain health are inextricably linked, as reduced blood flow can cause mini-strokes or silent brain injuries. Likewise, the risk of cognitive impairment has been shown to be higher in patients with atrial fibrillation (39%) and coronary artery disease (27%). AHA suggested physicians promote earlier attention to heart health in patients.
- Density-Based Mammo Reading: Reading screening mammograms based on breast density could be more efficient than just tackling cases randomly. In a study in Radiology, researchers used Volpara Health software to calculate volumetric breast density in 150 mammograms and had radiologists interpret low-density images first before moving to high-density mammograms. Compared to reading cases randomly, they read images faster (24 vs. 28 seconds) with slightly higher performance by AUC (0.93 vs. 0.92). Meanwhile, using an AI algorithm to group similar mammograms together before reading produced no effect.
- HAP Lands Radiology Group: Healthcare Administrative Partners continues to build its roster of clients in the Mid-Atlantic region. The revenue cycle management company signed a contract with Annapolis Radiology Associates, a private-practice radiology group serving the Annapolis, Baltimore-Washington, and Chesapeake Bay regions. HAP will perform all core revenue cycle management services, including billing, coding, carrier credentialing, business intelligence, and MIPS measure assurance services.
- Final Push for ‘Find it Early’ Bill: Proponents of legislation that would require reimbursement for diagnostic mammography work-up exams – the Find it Early Act – are making a final push to get the bill passed before Congress adjourns in January 2025. The bill was introduced in the House in May 2023 and the Senate in September, but time is running out, especially in a busy presidential election year. The legislation would require commercial and public insurers to cover imaging such as ultrasound and MRI without patient out-of-pocket costs.
- Lung Nodule Follow-Up Is Low: The CHEST 2024 meeting just wrapped up in Boston, and improving CT lung cancer screening was a major topic. Inadequate follow-up of incidental lung nodules is one challenge, and researchers from Mount Sinai Health System presented data for 364 patients with incidental nodules, finding that only 44% received appropriate, documented follow-up. Of the patients who got adequate workup, 4.2% were diagnosed with lung cancer, highlighting the importance of dedicated follow-up for incidental nodules.
- Software for Lung Nodule Tracking: Several presentations at CHEST 2024 suggested that software could help with lung nodule management. In one talk, researchers used Eon Health’s Eon Patient Management application to track incidental pulmonary nodules found on CT scans to see if it could catch lung cancer. Only 35% of the 274 patients diagnosed with lung cancer would have qualified for screening under USPSTF 2021 guidelines, indicating that better nodule tracking could detect cancer in people who fall outside established screening programs.
- AI Characterizes Lung Nodules: In another software-oriented CHEST 2024 presentation, the use of RevealDx’s machine learning classification software led to earlier diagnosis of patients with lung nodules. Researchers used RevealDx’s malignancy Similarity Index to triage and characterize nodules found on CT in 1.5k patients as either malignant or benign. They found it led to an earlier diagnosis in 40% of cancer cases and reduced false positives by 22%.
- Technology Boosts Lung Screening: One hospital using technology to boost CT lung cancer screening is Baton Rouge’s Our Lady of the Lake Regional Medical Center, which reported on its success at CHEST 2024. The hospital emphasizes outreach to referring providers and uses lung nodule tracking software integrated with existing EMRs; they began tracking incidental pulmonary nodules in 2021. Since starting in 2018, the program has seen a 14X increase in volume, with 70% of malignant lesions diagnosed at stage I, giving patients a better chance at survival.
- GE Touts Manganese Contrast: GE HealthCare is highlighting new clinical results from an MRI contrast agent based on manganese rather than gadolinium. Phase I data were presented at the Contrast Media Research symposium in Norway and show that the macrocyclic agent was well-tolerated by patients with no side effects. Contrast developers see manganese MRI contrast as an alternative to gadolinium-based contrast agents, which can have side effects and also can leave residual gadolinium in the body. GE first disclosed its research on manganese contrast in 2023.
- AI of Muscle MRI Gets Clearance: Springbok Analytics received FDA 510(k) clearance for MuscleView, the company’s AI-based software for analyzing muscle on MRI scans. The solution automates what had been a manual process for visualizing the musculature and produces 3D visualizations of muscle health including muscle volume, left-right muscle symmetry, bone volume, and intramuscular fat percentage. With clearance in hand, Springbok will target applications in sports medicine, orthopedics, and therapeutics.
- CARPL Gets CE Mark: AI platform company CARPL.ai received the CE Mark for its software, which in March also received 510(k) clearance in the U.S. CARPL highlighted the accomplishment as a major milestone in its efforts to penetrate the European market and as an advancement in patient safety. It’s still open to debate whether AI platform companies need market authorizations given that AI point-source applications typically have their own approvals, but CARPL sees the authorizations as a differentiating factor.
- ChatGPT Orders Too Many X-Rays: Maybe ChatGPT behaves more like humans than we thought. A new study in Nature Communications found that the large language model ordered too many X-rays and antibiotics and suggested hospitalization for too many patients seen in the emergency department. Researchers asked two versions of ChatGPT to make clinical decisions for 1k sample ED visits and compared their answers to resident physicians, finding that ChatGPT-4 was 8% less accurate and ChatGPT-3.5 was 24% less accurate.
|
|
AI for Limb Fractures on X-Ray
AI can recognize limb fractures on X-rays and reduce interpretation discrepancies between radiology and emergency departments. Learn how Gleamer’s BoneView AI algorithm performed in this new research study.
|
|
Leave No Breast Cancer Patient Behind
Breast cancer is the second leading cause of cancer death among women, but catching it early greatly improves the survival rate. Leave no patient behind with the help of Intelerad’s InteleScreen and IntelePACS for breast imaging organizations.
|
|
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 Healthcare with the Cloud: Discover how Optum’s cloud-based medical imaging solutions can slash costs and streamline radiology operations. Visit their website today to unlock a wealth of healthcare insights and resources tailored just for professionals like you.
- Fully Automated AI for Mitral Regurgitation Grading: Echo AI can help address challenges with mitral regurgitation assessment quality and efficiency. Find out how researchers used Us2.ai’s fully automated echo workflow for grading MR severity and predicting one-year mortality.
- The Importance of Architecture in Healthcare: Technology is pivotal in providing efficient, secure, and scalable solutions in healthcare. At the core of this digital transformation is the architecture of healthcare software. Learn how software architecture and containerization are revolutionizing healthcare in this blog from Enlitic.
- Revolutionizing Quality in Remote Mammography: Subspecialty radiology platform DocPanel embraced the zero-footprint capabilities of Mach7’s eUnity Diagnostic Viewer to boost productivity, save resources, and bridge coverage gaps in remote areas. Find out how they did it in this case study.
- Simplifying Complex Image Exchange Workflows: Guadalupe Regional Medical Center (GRMC) 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.
- 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.
- A Cloud-Native Foundation for Your Imaging Needs: Merge by Merative’s Merge Imaging Suite is built on a cloud-native foundation to address your imaging needs today, providing an intuitive, feature-rich array of solutions thoughtfully designed to help you enjoy a seamless and frictionless workflow experience. Learn more about it today.
- 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.
- How to Help Radiologists Thrive: With burnout and staffing shortages on the rise, and the increasing volume of imaging, radiology teams are searching for solutions. This interactive guide from Nuance can help you create an environment where radiologists thrive by building a powerful imaging strategy with AI-driven, real-time intelligence.
- Connect with United Imaging at RSNA 2024: United Imaging will be celebrating the theme of Building Intelligent Connections at RSNA 2024. Come visit the company at booth #1929 to learn about their imaging solutions and how they connect to United’s mission of Equal Healthcare for All.
- Reach New Heights with Enterprise Imaging Cloud: Embrace the potential of AGFA HealthCare’s Enterprise Imaging Cloud, a fully managed Software-as-a-Service (SaaS) solution that will transform the handling, storage, and accessibility of medical imaging data. Learn how EI Cloud can help you today.
- Request an RSNA Meeting with TeraRecon: RSNA 2024 will be here before you know it. Come explore TeraRecon’s latest updates and find out why the company is an award-winning solution provider for AI-empowered radiology, oncology, cardiology, neurology, and vascular surgery.
- Creating a Theranostics Center of Excellence: See how Siemens Healthineers can work with you to create a radiopharmaceutical therapy center of excellence that’s built around your needs by providing consulting and design services that put you on the path to success.
|
|
|
|
|
