vRad AI model achieves 95% accuracy for fully automated detection of aortic aneurysms in contrast and non-contrast CT
Published: 05/31/2022
Remote radiologist jobs with flexible schedules, equitable pay, and the most advanced reading platform. Discover teleradiology at vRad.
Radiologist well-being matters. Explore how vRad takes action to prevent burnout with expert-led, confidential support through our partnership with VITAL WorkLife. Helping radiologists thrive.
Visit the vRad blog for radiologist experiences at vRad, career resources, and more.
vRad provides radiology residents and fellows with free radiology education resources for ABR boards, noon lectures, and CME.
Teleradiology services leader since 2001. See how vRad AI is helping deliver faster, higher-quality care for 50,000+ critical patients each year.
Subspecialist care for the women in your community. 48-hour screenings. 1-hour diagnostics. Comprehensive compliance and inspection support.
vRad’s stroke protocol auto-assigns stroke cases to the top of all available radiologists’ worklists, with requirements to be read next.
vRad’s unique teleradiology workflow for trauma studies delivers consistently fast turnaround times—even during periods of high volume.
vRad’s Operations Center is the central hub that ensures imaging studies and communications are handled efficiently and swiftly.
vRad is delivering faster radiology turnaround times for 40,000+ critical patients annually, using four unique strategies, including AI.
vRad is developing and using AI to improve radiology quality assurance and reduce medical malpractice risk.
Now you can power your practice with the same fully integrated technology and support ecosystem we use. The vRad Platform.
Since developing and launching our first model in 2015, vRad has been at the forefront of AI in radiology.
Since 2010, vRad Radiology Education has provided high-quality radiology CME. Open to all radiologists, these 15-minute online modules are a convenient way to stay up to date on practical radiology topics.
Join vRad’s annual spring CME conference, featuring top speakers and practical radiology topics.
vRad provides radiology residents and fellows with free radiology education resources for ABR boards, noon lectures, and CME.
Academically oriented radiologists love practicing at vRad too. Check out the research published by vRad radiologists and team members.
Learn how vRad revolutionized radiology and has been at the forefront of innovation since 2001.
Visit the vRad blog for radiologist experiences at vRad, career resources, and more.
Ready to be part of something meaningful? Explore team member careers at vRad.
Explore our practice’s reading platform, breast imaging program, AI, and more. Plus, hear from vRad radiologists about what it’s like to practice at vRad.
Published: 05/31/2022
Published in the proceedings of the Society of Photo-Optical Instrumentation Engineers (SPIE)
EDEN PRAIRIE, Minn.—May 31, 2022—Virtual Radiologic (vRad), the leading US teleradiology practice, developed and validated a research-only deep learning (DL) based automatic algorithm to detect thoracic and abdominal aortic aneurysms on contrast and non-contrast CT images. They have compared its performance with assessments obtained from retrospective radiology reports. The DL algorithm was developed using 556 CT scans. Manual annotations of aorta centerlines and cross-sectional aorta boundaries were created to train the algorithm. Aorta segmentation and aneurysm detection performances were evaluated on 2263 retrospective CT scans (154 thoracic and 176 abdominal aneurysms).
Evaluation was performed by comparing the automatically detected aneurysm status to the aneurysm status reported in the radiology reports and the AUC was reported. In addition, a quantitative evaluation was performed to compare the automatically measured aortic diameters to manual diameters on a subset of 59 CT scans. Pearson correlation coefficient was used. For aneurysm detection, the AUC was 0.95 for thoracic aneurysm detection (95% confidence region [0.93, 0.97]) and 0.94 for abdominal aneurysm detection (95% confidence region [0.92, 0.96]). For aortic diameter measurement, the Pearson correlation coefficient was 0.973 (p<0.001).
Read more about this study: https://doi.org/10.1117/12.2607877
vRad is the nation’s leading teleradiology practice with 500 U.S. board-certified or eligible physicians, the majority of whom are subspecialty trained. Our practice delivers high-quality diagnostic imaging services to more than 2,100 facilities and radiology groups across the United States. vRad has 23 issued patents for telemedicine and radiology technologies; and is a leading innovator in the areas of artificial intelligence, machine learning, imaging data analytics, and software to improve the quality of patient care, value for our clients, and the experience of our physicians. www.www.vrad.com