PURPOSE: CT angiography (CTA) is the imaging standard for large vessel occlusion (LVO) detection in patients with acute ischemic stroke. StrokeSENS LVO is an automated tool that utilizes a machine learning algorithm to identify anterior large vessel occlusions (LVO) on CTA. The aim of this study was to test the algorithm's performance in LVO detection in an independent dataset. METHODS: A total of 400 studies (217 LVO, 183 other/no occlusion) read by expert consensus were used for retrospective analysis. The LVO was defined as intracranial internal carotid artery (ICA) occlusion and M1 middle cerebral artery (MCA) occlusion. Software performance in detecting anterior LVO was evaluated using receiver operator characteristics (ROC) analysis, reporting area under the curve (AUC), sensitivity, and specificity. Subgroup analyses were performed to evaluate if performance in detecting LVO differed by subgroups, namely M1 MCA and ICA occlusion sites, and in data stratified by patient age, sex, and CTA acquisition characteristics (slice thickness, kilovoltage tube peak, and scanner manufacturer). RESULTS: AUC, sensitivity, and specificity overall were as follows: 0.939, 0.894, and 0.874, respectively, in the full cohort; 0.927, 0.857, and 0.874, respectively, in the ICA occlusion cohort; 0.945, 0.914, and 0.874, respectively, in the M1 MCA occlusion cohort. Performance did not differ significantly by patient age, sex, or CTA acquisition characteristics. CONCLUSION: The StrokeSENS LVO machine learning algorithm detects anterior LVO with high accuracy from a range of scans in a large dataset.
- MeSH
- arteriální okluzní nemoci * MeSH
- cévní mozková příhoda * diagnostické zobrazování MeSH
- CT angiografie metody MeSH
- infarkt arteria cerebri media diagnostické zobrazování MeSH
- ischemická cévní mozková příhoda * MeSH
- ischemie mozku * MeSH
- lidé MeSH
- retrospektivní studie MeSH
- software MeSH
- strojové učení MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND: Successful reperfusion determines the treatment effect of endovascular thrombectomy. We evaluated stent-retriever characteristics and their relation to reperfusion in the ESCAPE-NA1 trial. METHODS: Independent re-scoring of reperfusion grade for each attempt was conducted. The following characteristics were evaluated: stent-retriever length and diameter, thrombus position within stent-retriever, bypass effect, deployment in the superior or inferior MCA trunk, use of balloon guide catheter and distal access catheter. Primary outcome was successful reperfusion defined as expanded thrombolysis in cerebral infarction (eTICI) 2b-3 per attempt. The secondary outcome was successful reperfusion eTICI 2b-3 after the first attempt. Separate regression models for each stent-retriever characteristic and an exploratory multivariable modeling to test the impact of all characteristics on successful reperfusion were built. RESULTS: Of 1105 patients in the trial, 809 with the stent-retriever use (1241 attempts) were included in the primary analysis. The stent-retriever was used as the first-line approach in 751 attempts. A successful attempt was associated with thrombus position within the proximal or middle third of the stent (OR 2.06; 95% CI: 1.24-3.40 and OR 1.92; 95% CI: 1.16-3.15 compared to the distal third respectively) and with bypass effect (OR 1.7; 95% CI: 1.07-2.72). Thrombus position within the proximal or middle third (OR 2.80; 95% CI: 1.47-5.35 and OR 2.05; 95% CI: 1.09-3.84, respectively) was associated with first-pass eTICI 2b-3 reperfusion. In the exploratory analysis accounting for all characteristics, bypass effect was the only independent predictor of eTICI 2b-3 reperfusion (OR 1.95; 95% CI: 1.10-3.46). CONCLUSION: The presence of bypass effect and thrombus positioning within the proximal and middle third of the stent-retriever were strongly associated with successful reperfusion.
