Index by author

This study evaluates a convolutional neural network optimized for the detection and quantification of intraparenchymal, epidural/subdural, and subarachnoid hemorrhages on noncontrast CT with a 10,159-examination training cohort (512,598 images; 901/8.1% hemorrhages) and an 862-examination test cohort (23,668 images; 82/12% hemorrhages). Accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value for hemorrhage detection were 0.975, 0.983, 0.971, 0.975, 0.793, and 0.997 on training cohort cross-validation and 0.970, 0.981, 0.951, 0.973, 0.829, and 0.993 for the prospective test set.

Twenty children (30 imaging sessions, 60 MR scans) with Moyamoya disease underwent dual breath-hold hypercapnic challenge blood oxygen level–dependent MR imaging of cerebrovascular reactivity studies in the same MR imaging session. Within-day, within-subject repeatability of cerebrovascular reactivity estimates, derived from the blood oxygen level–dependent signal, was computed. Breath-hold hypercapnic challenge blood oxygen level–dependent MR imaging is a repeatable technique for the assessment of cerebrovascular reactivity in children with Moyamoya disease and is reliably interpretable for use in clinical practice.