Index by author

This convolutional neural network was retrospectively trained on 295 brain MRIs to perform automated FLAIR lesion segmentation. Performance was evaluated on 92 validation cases using Dice scores and voxelwise sensitivity and specificity, compared with radiologists' manual segmentations. The authors' model demonstrated accurate FLAIR lesion segmentation performance (median Dice score, 0.79) on the validation dataset across a large range of lesion characteristics. Across 19 neurologic diseases, performance was significantly higher than existing methods (Dice, 0.56 and 0.41) and approached human performance (Dice, 0.81).

The authors performed a prospective safety and feasibility study in 100 consecutive patients undergoing glymphatic MR imaging from September 2015 to August 2018. Short- and long-term serious and nonserious adverse events were registered clinically and by interview after intrathecal administration of 0.5 mL of gadobutrol (1.0 mmol/mL) along with 3 mL of iodixanol (270 mg I/mL). One serious adverse event (anaphylaxis) occurred in a patient with known allergy to iodine-containing contrast agents (1%). The main nonserious adverse events during the first 1–3 days after contrast injection included severe headache (28%) and severe nausea (34%), though the frequency depended heavily on the diagnosis. They conclude that intrathecal administration of gadobutrol in conjunction with iodixanol for glymphatic MR imaging is safe and feasible.