Related Experiment Video
Updated: Jan 23, 2026
Optimized Management of Endovascular Treatment for Acute Ischemic Stroke
Published on: January 18, 2018
Collateral Automation for Triage in Stroke: Evaluating Automated Scoring of Collaterals in Acute Stroke on Computed
Iris Q Grunwald1,2,3, Johann Kulikovski4, Wolfgang Reith4
1Neuroscience, Anglia Ruskin University, School of Medicine, Chelmsford, United Kingdom, iqgrunwald@gmail.com.
Insights
A machine learning tool, e-CTA, accurately scores collateral flow on CT angiography (CTA) for stroke patients. This automated approach improves consistency and aids in selecting patients for mechanical thrombectomy.
Area of Science:
- Neuroradiology
- Medical Imaging Analysis
- Machine Learning in Healthcare
Background:
- Computed tomography angiography (CTA) collateral scoring is crucial for identifying stroke patients who may benefit from mechanical thrombectomy.
- Current scoring methods rely on subjective interpretation by neuroradiologists, leading to variability.
- Quantifying collateral flow accurately is essential for predicting patient outcomes.
Purpose of the Study:
- To evaluate the performance of a machine learning-based automated CTA collateral scoring (e-CTA) system.
- To assess the impact of e-CTA on inter-rater reliability among neuroradiologists.
- To determine the accuracy of e-CTA in quantifying collateral flow and predicting favorable outcomes.
Main Methods:
- A machine learning algorithm was used to generate e-CTA collateral scores for 98 mechanical thrombectomy-eligible patients.
- Three neuroradiologists independently scored CTA collaterals before and after reviewing e-CTA results.
- Consensus scores were established, and agreement metrics (Intraclass Correlation Coefficient - ICC) were calculated.
Main Results:
- The addition of e-CTA significantly improved ICC between neuroradiologists from 0.58 to 0.77 (p = 0.003).
- Automated e-CTA agreed with the consensus score in 90% of cases, with 100% within 1 point (ICC 0.93).
- e-CTA demonstrated high sensitivity (0.99) and specificity (0.94) for identifying favorable collateral flow and correlated with the Alberta Stroke Programme Early CT Score (r=0.46).
Conclusions:
- Fully automated e-CTA provides a reliable and consistent method for collateral scoring in stroke patients.
- e-CTA has the potential to enhance the accuracy and efficiency of image interpretation in mechanical thrombectomy workflows.
- The system can independently quantify collateral scores, reducing reliance on expert rater input and improving patient selection for reperfusion therapies.
Abstract:
Computed tomography angiography (CTA) collateral scoring can identify patients most likely to benefit from mechanical thrombectomy and those more likely to have good outcomes and ranges from 0 (no collaterals) to 3 (complete collaterals). In this study, we used a machine learning approach to categorise the degree of collateral flow in 98 patients who were eligible for mechanical thrombectomy and generate an e-CTA collateral score (CTA-CS) for each patient (e-STROKE SUITE, Brainomix Ltd., Oxford, UK). Three experienced neuroradiologists (NRs) independently estimated the CTA-CS, first without and then with knowledge of the e-CTA output, before finally agreeing on a consensus score. Addition of the e-CTA improved the intraclass correlation coefficient (ICC) between NRs from 0.58 (0.46-0.67) to 0.77 (0.66-0.85, p = 0.003). Automated e-CTA, without NR input, agreed with the consensus score in 90% of scans with the remaining 10% within 1 point of the consensus (ICC 0.93, 0.90-0.95). Sensitivity and specificity for identifying favourable collateral flow (collateral score 2-3) were 0.99 (0.93-1.00) and 0.94 (0.70-1.00), respectively. e-CTA correlated with the Alberta Stroke Programme Early CT Score (Spearman correlation 0.46, p < 0.001) highlighting the value of good collateral flow in maintaining tissue viability prior to reperfusion. In conclusion, -e-CTA provides a real-time and fully automated approach to collateral scoring with the potential to improve consistency of image interpretation and to independently quantify collateral scores even without expert rater input.
Related Concept Videos
01:27Sympathetic Pathways: Collateral Ganglia and Adrenal Medulla
Collateral Ganglia
Sympathetic preganglionic axons reach the collateral ganglia along the route of splanchnic nerves. These nerves bypass the sympathetic trunk and communicate with sympathetic postganglionic neurons housed in the prevertebral ganglia. These ganglia supply the organs of the abdominopelvic cavity.
The greater splanchnic nerve, formed by the...
01:10Computed Tomography
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
01:27Regulation of Stroke Volume
Preload refers to the degree of stretch on the heart before it contracts. It's analogous to the stretching of a rubber band; the more it's stretched, the more forcefully it snaps back. This concept is encapsulated in the Frank-Starling law of the...
01:11Cardiac Output and Stroke Volume
In an average resting adult male, the typical cardiac...
01:25Distribution Reliability and Automation
01:27Imaging Studies III: Computed Tomography