Automated Cerebral Hemorrhage Detection Using RAPID.

BACKGROUND AND PURPOSE: Intracranial hemorrhage (ICH) is an important event that is diagnosed on head NCCT. Increased NCCT utilization in busy hospitals may limit timely identification of ICH. RAPID ICH is an automated hybrid 2D-3D convolutional neural network application designed to detect ICH that may allow for expedited ICH diagnosis. We determined the accuracy of RAPID ICH for ICH detection and ICH volumetric quantification on NCCT. MATERIALS AND METHODS: NCCT scans were evaluated for ICH by RAPID ICH. Consensus detection of ICH by 3 neuroradiology experts was used as the criterion standard for RAPID ICH comparison. ICH volume was also automatically determined by RAPID ICH in patients with intraparenchymal or intraventricular hemorrhage and compared with manually segmented ICH volumes by a single neuroradiology expert. ICH detection accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and positive and negative likelihood ratios by RAPID ICH were determined. RESULTS: We included 308 studies. RAPID ICH correctly identified 151/158 ICH cases and 143/150 ICH-negative cases, which resulted in high sensitivity (0.956, CI: 0.911-0.978), specificity (0.953, CI: 0.907-0.977), positive predictive value (0.956, CI: 0.911-0.978), and negative predictive value (0.953, CI: 0.907-0.977) for ICH detection. The positive likelihood ratio (20.479, CI 9.928-42.245) and negative likelihood ratio (0.046, CI 0.023-0.096) for ICH detection were similarly favorable. RAPID ICH volumetric quantification for intraparenchymal and intraventricular hemorrhages strongly correlated with expert manual segmentation (correlation coefficient r = 0.983); the median absolute error was 3 mL. CONCLUSIONS: RAPID ICH is highly accurate in the detection of ICH and in the volumetric quantification of intraparenchymal and intraventricular hemorrhages.

Tissue at risk in acute stroke patients treated beyond 8 h after symptom onset.

INTRODUCTION: The decision on thrombolytics administration is usually based on a generalized, rigid time-based rule rather than an individualized evaluation of the "tissue at risk of infarction" which is the target of the recanalization therapies. The goals of our article are to assess whether there is tissue at risk of infarction in a group of acute stroke patients treated beyond 8 h after symptom onset and to investigate the baseline imaging and clinical features that predict the fate of this tissue at risk. METHODS: We retrospectively reviewed a series of patients with acute ischemic stroke treated with endovascular recanalization therapies beyond 8 h after symptom onset. The tissue at risk was calculated as the difference between the infarct volumes on baseline and follow-up imaging (infarct growth). We analyzed the epidemiological distribution of infarct growth, and we performed a multivariate regression analysis to identify the baseline variables that predict infarct growth. RESULTS: Our study group included 75 patients (65 ± 13.8 years, baseline National Institutes of Health Stroke Scale 14 ± 4.9, time to treatment 15.2 ± 8.7 h). The mean infarct growth was 78.6 ± 95.0 cc (p < 0.001), and, overall, the infarct growth was greater when the baseline volume of infarct tissue was small (p < 0.001) and in the case of a unsuccessful arterial recanalization (p = 0.001). CONCLUSIONS: There is potentially salvageable ischemic tissue at risk in acute stroke patients treated beyond 8 h after symptom onset.