Related Experiment Video
Updated: Jul 6, 2025
Optimized Management of Endovascular Treatment for Acute Ischemic Stroke
Published on: January 18, 2018
Performance of RAPID noncontrast CT stroke platform in large vessel occlusion and intracranial hemorrhage detection
Vivek Yedavalli1, Jeremy Josef Heit2, Seena Dehkharghani3
1The Johns Hopkins Hospital, Johns Hopkins Medicine, Baltimore, MD, United States.
Insights
AI software RAPID NCCT Stroke shows superior performance in detecting large vessel occlusions (LVOs) and intracerebral hemorrhage (ICH) on noncontrast CT scans compared to radiologists, potentially speeding up diagnosis and treatment for acute ischemic stroke patients.
Area of Science:
- Neuroradiology
- Artificial Intelligence in Medical Imaging
- Stroke Diagnostics
Background:
- Noncontrast CT (NCCT) is crucial for evaluating intracerebral hemorrhage (ICH) and ischemia in acute ischemic stroke (AIS).
- Detecting large vessel occlusions (LVOs), a primary cause of AIS, remains challenging with NCCT alone.
Purpose of the Study:
- To evaluate the diagnostic performance of the AI software RAPID NCCT Stroke.
- To compare the AI software's ability to detect ICH and LVOs against expert human readers.
Main Methods:
- A retrospective, multicenter study involving 244 patients.
- Assessed the stand-alone performance of RAPID NCCT Stroke and compared it to interpretations by 8 general radiologists and 3 neuroradiologists.
- Sensitivity and specificity were calculated for ICH and LVO detection.
Main Results:
- The AI software achieved high sensitivity and specificity for ICH (96.2% and 99.5%) and LVO detection (63.5% and 95.1%).
- RAPID NCCT Stroke demonstrated significantly higher sensitivity for LVO detection compared to both all readers (63.5% vs. 43.6%) and general radiologists (63.5% vs. 40.9%).
Conclusions:
- The RAPID NCCT Stroke AI platform outperforms radiologists in detecting LVOs on NCCT.
- This AI tool may facilitate earlier LVO detection, leading to expedited patient transfer to thrombectomy-capable centers.
Background:
Noncontrast CT (NCCT) is used to evaluate for intracerebral hemorrhage (ICH) and ischemia in acute ischemic stroke (AIS). Large vessel occlusions (LVOs) are a major cause of AIS, but challenging to detect on NCCT.
Aims:
The purpose of this study is to evaluate an AI software called RAPID NCCT Stroke (RAPID, iSchemaView, Menlo Park, CA) for ICH and LVO detection compared to expert readers.
Methods:
In this IRB approved retrospective, multicenter study, stand-alone performance of the software was assessed based on the consensus of 3 neuroradiologists and sensitivity and specificity were determined. The platform's performance was then compared to interpretation by readers comprised of eight general radiologists (GR) and three neuroradiologists (NR) in detecting ICH and hyperdense vessel sign (HVS) indicating LVO.
Results:
A total of 244 cases were included. Of the 244, 115 were LVOs and 26 were ICHs. One hundred three cases did not have LVO nor ICH. Stand-alone performance of the software demonstrated sensitivities and specificities of 96.2 and 99.5% for ICH and 63.5 and 95.1% for LVO detection. Compared to all 11 readers and eight GR readers only respectively, the software demonstrated superiority, achieving significantly higher sensitivities (63.5% versus 43.6%, p < 0.0001 and 63.5% versus 40.9%, p = 0.001).
Conclusion:
The RAPID NCCT Stroke platform demonstrates superior performance to radiologists for detecting LVO from a NCCT. Use of this software platform could lead to earlier LVO detection and expedited transfer of these patients to a thrombectomy capable center.
More Related Videos
13:10Combined Near-infrared Fluorescent Imaging and Micro-computed Tomography for Directly Visualizing Cerebral Thromboemboli
Published on: September 25, 2016
08:12A Volumetric Method for Quantification of Cerebral Vasospasm in a Murine Model of Subarachnoid Hemorrhage
Published on: July 28, 2018