- Change in Emergency Department Length of Stay following Routine Adoption of Dual-Energy CT to Differentiate Intracranial Hemorrhage from Calcification
This retrospective study compared ED LOS over a 1-year period before and after implementing automated DECT processing in the evaluation of indeterminate intracranial hyperdensities. The authors showed that with intracranial indeterminate hyperdensities, there was a larger statistically significant difference in pre-DECT versus post-DECT ED LOS. The pre-DECT ED LOS correlated with increased frequency of neurosurgical consultation and repeat head CT.
- Development and Evaluation of Automated Artificial Intelligence–Based Brain Tumor Response Assessment in Patients with Glioblastoma
The goal of this study was to compare AI-based volumetric GBM MRI response assessment with standardized radiologist response assessments. The AI-based volumetric response assessment yielded overall moderate performance for recapitulating most human response assessment categories (BT-RADS 1, 2, and 4) but demonstrated the lowest performance for predicting BT-RADS 3, which is likely related to the high variability of this assessment. In comparison to radiologist assessment, the AI-based volumetric GBM MRI response assessment showed comparable performance for overall survival.
- Stroke Thrombectomy for Large Infarcts with Limited Penumbra: Systematic Review and Meta-Analysis of Randomized Trials
This meta-analysis evaluated randomized clinical trial results to provide more definitive guidance on the role of EVT for patients with stroke with large infarcts based on perfusion metrics. The results showed that the effectiveness of thrombectomy is uncertain regarding the safety and efficacy of thrombectomy for patients with limited areas of at-risk tissue. EVT may be beneficial for those with intermediate perfusion mismatch (ratio of 1.2-1.8 or volume of 10-15 mL) but not for those with low perfusion mismatch (ratio <1.2 or volume <10 mL).
