Head-to-head comparison of commercial artificial intelligence solutions for detection of large vessel occlusion at a comprehensive stroke center.

Purpose: Despite the availability of commercial artificial intelligence (AI) tools for large vessel occlusion (LVO) detection, there is paucity of data comparing traditional machine learning and deep learning solutions in a real-world setting. The purpose of this study is to compare and validate the performance of two AI-based tools (RAPID LVO and CINA LVO) for LVO detection. Materials and methods: This was a retrospective, single center study performed at a comprehensive stroke center from December 2020 to June 2021. CT angiography (n = 263) for suspected stroke were evaluated for LVO. RAPID LVO is a traditional machine learning model which primarily relies on vessel density threshold assessment, while CINA LVO is an end-to-end deep learning tool implemented with multiple neural networks for detection and localization tasks. Reasons for errors were also recorded. Results: There were 29 positive and 224 negative LVO cases by ground truth assessment. RAPID LVO demonstrated an accuracy of 0.86, sensitivity of 0.90, specificity of 0.86, positive predictive value of 0.45, and negative predictive value of 0.98, while CINA demonstrated an accuracy of 0.96, sensitivity of 0.76, specificity of 0.98, positive predictive value of 0.85, and negative predictive value of 0.97. Conclusion: Both tools successfully detected most anterior circulation occlusions. RAPID LVO had higher sensitivity while CINA LVO had higher accuracy and specificity. Interestingly, both tools were able to detect some, but not all M2 MCA occlusions. This is the first study to compare traditional and deep learning LVO tools in the clinical setting.

EFEMP1 suppresses malignant glioma growth and exerts its action within the tumor extracellular compartment.

PURPOSE: There are conflicting reports regarding the function of EFEMP1 in different cancer types. In this study, we sought to evaluate the role of EFEMP1 in malignant glioma biology. EXPERIMENTAL DESIGN: Real-time qRT-PCR was used to quantify EFEMP1 expression in 95 glioblastoma multiforme (GBM). Human high-grade glioma cell lines and primary cultures were engineered to express ectopic EFEMP1, a small hairpin RNA of EFEMP1, or treated with exogenous recombinant EFEMP1 protein. Following treatment, growth was assayed both in vitro and in vivo (subcutaneous (s.c.) and intracranial (i.c.) xenograft model systems). RESULTS: Cox regression revealed that EFEMP1 is a favorable prognostic marker for patients with GBM. Over-expression of EFEMP1 eliminated tumor development and suppressed angiogenesis, cell proliferation, and VEGFA expression, while the converse was true with knock-down of endogenous EFEMP1 expression. The EFEMP1 suppression of tumor onset time was nearly restored by ectopic VEGFA expression; however, overall tumor growth rate remained suppressed. This suggested that inhibition of angiogenesis was only partly responsible for EFEMP1's impact on glioma development. In glioma cells that were treated by exogenous EFEMP1 protein or over-expressed endogenous EFEMP1, the EGFR level was reduced and AKT signaling activity attenuated. Mixing of EFEMP1 protein with cells prior to s.c. and i.c. implantations or injection of the protein around the established s.c. xenografts, both significantly suppressed tumorigenicity. CONCLUSIONS: Overall, our data reveals that EEFEMP1 suppresses glioma growth in vivo, both by modulating the tumor extracellular microenvironment and by altering critical intracellular oncogenic signaling pathways.

Hunting increases adaptive auditory map plasticity in adult barn owls.

The optic tectum (OT) of barn owls contains topographic maps of auditory and visual space. Barn owls reared with horizontally displacing prismatic spectacles (prisms) acquire a novel auditory space map in the OT that restores alignment with the prismatically displaced visual map. Although juvenile owls readily acquire alternative maps of auditory space as a result of experience, this plasticity is reduced greatly in adults. We tested whether hunting live prey, a natural and critically important behavior for barn owls, increases auditory map plasticity in adult owls. Two groups of naive adult owls were fit with prisms. The first group was fed dead mice during 10 weeks of prism experience, while the second group was required to hunt live prey for an identical period of time. When the owls hunted live prey, auditory maps shifted substantially farther (five times farther, on average) and the consistency of tuning curve shifts within each map increased. Only a short period of time in each day, during which the two groups experienced different conditions, accounts for this effect. In addition, increased map plasticity correlated with behavioral improvements in the owls' ability to strike and capture prey. These results indicate that the experience of hunting dramatically increases adult adaptive plasticity in this pathway.