Assessment of an Artificial Intelligence Algorithm for Detection of Intracranial Hemorrhage

But is it faster and better than one of these? You don't even specify your timeframe. Time is Brain, you know.

Hats off to Helmet of Hope - stroke diagnosis in 30 seconds   February 2017

 

Microwave Imaging for Brain Stroke Detection and Monitoring using High Performance Computing in 94 seconds March 2017

 

New Device Quickly Assesses Brain Bleeding in Head Injuries - 5-10 minutes April 2017

Ski-Mask Design AIR Coil Offers Whole-Brain Imaging Without Claustrophobia

 The latest here:

Assessment of an Artificial Intelligence Algorithm for Detection of Intracranial Hemorrhage

Author links open overlay panelRyan A.RavaMS¹²

Samantha E.SeymourHSD¹²Meredith E.LaQueHSD¹²Blake A.PetersonBS³Kenneth V.SnyderMD, PhD²³⁴MaximMokinMD, PhD⁵MuhammadWaqasMBBS²⁴YiemengHoiPhD⁶Jason M.DaviesMD, PhD²³⁴⁷Elad I.LevyMD, MBA²³⁴Adnan H.SiddiquiMD, PhD²³⁴Ciprian N.IonitaPhD¹²³⁴

¹

Department of Biomedical Engineering, University at Buffalo, Buffalo, NY 14260, US

²

Canon Stroke and Vascular Research Center, Buffalo, NY, 14203, US

³

Jacobs School of Medicine and Biomedical Sciences, Buffalo, NY, 14203, US

⁴

Department of Neurosurgery, University at Buffalo, Buffalo, NY 14203, US

⁵

Department of Neurosurgery, University of South Florida, Tampa, FL, 33606, US

⁶

Canon Medical Systems USA Inc., Tustin, CA 92780, US

⁷

Department of Bioinformatics, University at Buffalo, Buffalo, NY 14214, US

Received 18 January 2021, Revised 26 February 2021, Accepted 27 February 2021, Available online 5 March 2021.

https://doi.org/10.1016/j.wneu.2021.02.134Get rights and content

ABSTRACT

Background

Immediate and accurate detection of intracranial hemorrhages (ICHs) is essential to provide a good clinical outcome for ICH patients. Artificial intelligence has the potential to provide this, but assessment of these methods needs to be investigated in depth. This study aimed to assess the ability of Canon’s ^AUTOStroke Solution ICH detection algorithm to accurately identify patients both with and without ICHs present.

Methods

Data from 200 ICH and 102 non-ICH patients who presented with stroke-like symptoms between August 2016 and December 2019 were collected retrospectively. ICH patients had at least one of the following hemorrhage types: intraparenchymal (n=181), intraventricular (n=45), subdural (n=13), or subarachnoid (n=19). Non-contrast computed tomography scans were analyzed for each patient using Canon’s ^AUTOStroke Solution ICH algorithm to determine which slices contained hemorrhage. The algorithm’s ability to detect ICHs was assessed using sensitivity, specificity, positive predictive value, and negative predictive value. Percentages of cases correctly identified as ICH positive and negative were additionally calculated.

Results

Automated analysis demonstrated the following metrics for identifying hemorrhage slices within all 200 ICH patients (95% confidence intervals): sensitivity=0.93±0.03, specificity=0.93±0.01, positive predictive value=0.85±0.02, and negative predictive value=0.98±0.01. 95% (245/258) of ICH volumes were correctly triaged while 88.2% (90/102) of non-ICH cases were correctly classified as ICH negative.

Conclusions

Canon’s ^AUTOStroke Solution ICH detection algorithm was able to accurately detect intraparenchymal, intraventricular, subdural, and subarachnoid hemorrhages in addition to accurately determine when an ICH was not present. Having this automated ICH detection method could drastically improve treatment times for ICH patients.(By how much?)

 

Verapamil eluting stents as a possible treatment for vasospasm after subarachnoid hemorrhage

No idea what time frame we are talking about here. 
http://www.docguide.com/verapamil-eluting-stents-possible-treatment-vasospasm-after-subarachnoid-hemorrhage

Bhambri P, Sarvi A, Wong J, Sundararaj U, Mitha A; Journal of Neurointerventional Surgery 9 (9), 875-879 (Sep 2017)

Tags:

• chloroform
• Interventional Radiology
• nimodipine

Read/Add Comments | Email This | Print This | PubMed | Get Full Text

OBJECTIVE The only pharmacologic prophylaxis for cerebral vasospasm after subarachnoid hemorrhage is oral nimodipine. A novel way to mitigate this risk may be to design a drug eluting stent that elutes verapamil over the time period typically associated with vasospasm. In this study, we explore different methods of coating nitinol stents with a bioabsorbable polymer and determine the release profile of various verapamil coated stents for the potential treatment of vasospasm.
METHODS Nitinol stents were coated with different concentrations of poly(lactic acid-co-glycolic acid) (PLGA) in chloroform solution and using three coating techniques: dip coating, spin coating, and electrospinning. Morphology of the coatings were studied with scanning electron microscopy. 12 verapamil eluting stents were then prepared using different verapamil concentrations and coatings with different numbers of layers. Drug release behaviors were studied using UV spectroscopy for 21 days.
RESULTS Electrospinning at 20% w/v resulted in a smooth uniform coating without significant surface irregularities, and may be the most effective technique to coat stents. Stents with a single layer of PLGA/verapamil coating showed a two phase release profile (initial burst release followed by a slow rate of release) whereas stents with a bilayer coating showed a lower level of initial release followed by a slower sustained release phase.
CONCLUSIONS Development of verapamil eluting stents that elute drug over the time course typical of cerebral vasospasm, and for either immediate or prophylactic treatment, is technically feasible. Further in vitro and in vivo studies are required to determine whether this can improve the outcome of patients after subarachnoid hemorrhage.