CT Perfusion Study Shows Enhanced Detection of Medium Vessel Occlusions with Emerging AI Software

News
Article

The Rapid CTP AI software offered 23 percent greater detection of medium vessel occlusions in comparison to the Viz CTP AI software, according to research presented at the European Stroke (Organization) Conference (ESOC).

For radiologists interpreting computed tomography (CT) perfusion imaging, new comparative research from the European Stroke (Organization) Conference (ESOC) suggests that one artificial intelligence (AI) software provides significantly enhanced detection of medium vessel occlusions (MeVOs) over another AI software.

For the study, researchers compared the Rapid CTP AI software (RapidAI) and Viz CTP (Viz.ai) in a cohort of 1,122 consecutive code stroke patients (mean age of 69.3 years).

CT Perfusion Study Shows Enhanced Detection of Medium Vessel Occlusions with Emerging AI Software

Rapid CTP software detected 109 medium vessel occlusions (93 percent) in contrast to 82 (70 percent) with the Viz CTP software, according to comparative research involving 1,122 consecutive code stroke patients. (Images courtesy of RapidAI.)

The study authors found that the Rapid CTP software detected 109 MeVOs (93 percent) in contrast to 82 MeVOs (70 percent) detected with the Viz CTP software.

“CT perfusion is a powerful tool, but its full value is only realized when paired with high-performing software, especially in complex cases with smaller occlusions like MeVOs,” said lead study author Harmeet Sachdev, M.D., the director of the Comprehensive Stroke Center at Good Samaritan Hospital in San Jose, Calif. “RapidAI consistently identified more occlusions than (Viz.ai) in this study, echoing what we saw in the DUEL study with large vessel occlusions. The story the data tells is clear: not all imaging tools are equally equipped to interpret complex stroke cases.”

Emphasizing the substantial neurological deficits that can occur with MeVOs, which reportedly contribute to 25 to 40 percent of acute ischemic stroke cases, the study authors said timely accuracy is critical in facilitating optimal use of endovascular therapy.

“The number of MeVOs missed by the (Viz CTP) software could lead physicians to miss or delay MeVO diagnosis and treatment times,” added Sachdev and colleagues.

(Editor’s note: For related content, see “Can Multimodality AI Enhance CT Detection of Medium Vessel Occlusions?,” “Comparative AI Study Shows Merits of RapidAI LVO Software in Stroke Detection” and “Aidoc Launches AI-Powered Neuroimaging Software for Vessel Occlusion Detection on CT.”)

Reference

1. Sachdev H, Hudson A, Ong K, Marklem S, Santos M, Flores M. AI detection of medium vessel occlusions: evaluating performance of RapidAI vs. Viz.ai CT perfusion in 1,591 consecutive code strokes. Presented at the European Stroke (Organization) Conference (ESOC) 2025, May 21-23, 2025, Helsinki, Finland. Available at: https://eso-stroke.org/esoc2025/ .

Recent Videos
Improving Access to Nuclear Imaging: An Interview with SNMMI President Jean-Luc C. Urbain, MD, PhD
SNMMI: 18F-Piflufolastat PSMA PET/CT Offers High PPV for Local PCa Recurrence Regardless of PSA Level
SNMMI: NIH Researcher Discusses Potential of 18F-Fluciclovine for Multiple Myeloma Detection
SNMMI: What Tau PET Findings May Reveal About Modifiable Factors for Alzheimer’s Disease
Can Generative AI Reinvent Radiology Reporting?: An Interview with Samir Abboud, MD
Combining Advances in Computed Tomography Angiography with AI to Enhance Preventive Care
Study: MRI-Based AI Enhances Detection of Seminal Vesicle Invasion in Prostate Cancer
What New Research Reveals About the Impact of AI and DBT Screening: An Interview with Manisha Bahl, MD
Can AI Assessment of Longitudinal MRI Scans Improve Prediction for Pediatric Glioma Recurrence?
Incorporating CT Colonography into Radiology Practice
Related Content
© 2025 MJH Life Sciences

All rights reserved.