Using a headset with a portable, laptop-size console, researchers say they can identify and monitor strokes, ranging from aneurysms to arteriovenous malformations, differentiating them from each other and from normal anatomy. The findings were introduced at last week’s Society of Interventional Radiology’s 36th annual scientific meeting in Chicago.
Sonar is used in the military to detect and communicate with other ships. Now, researchers claim, sonar can be used to detect something else: strokes.
Using a headset with a portable, laptop-size console, researchers say they can identify and monitor strokes, ranging from aneurysms to arteriovenous malformations, differentiating them from each other and from normal anatomy. The findings were introduced at last week’s Society of Interventional Radiology’s 36th annual scientific meeting in Chicago.
The device, developed by retired Navy sonar experts and Kieran J. Murphy, MD, FSIR, professor and vice chair, director of research and deputy chief of radiology at the University of Toronto and University Health Network in Canada, is based on submarine warfare technology, according to Murphy. Looking like the plastic adjustable lining inside a batting helmet, the headset contains six pressure wave-measuring accelerometers, takes only few minutes to capture the data and process it for an initial diagnosis.
To validate the device’s use, researchers from the University of Toronto ran a proof-of-concept trial with 37 patients, who had a variety of cerebrovascular conditions. These included intracerebral hemorrhage, subarachnoid hemorrhage, AVMs, ischemic stroke, transient ischemic attack, and intracranial aneurysms. The researchers confirmed the diagnoses with a CT scan, MRI, or catheter angiography. The analysis team was not told the patient’s clinical history. As a control, researchers used data from 30 normal subjects.
Using an algorithm, the analysts were able to separate the normal patients from those with cerebrovascular conditions, and further identified those conditions along with the abnormality’s location.
During his presentation at SIR, Murphy noted that of the 37 stroke patients tested, there was only one false positive and one false negative. He said the specificity was 98.8 percent and the sensitivity was 97.3 percent.
Murphy envisions the device being used for stroke detection and monitoring, with it being small enough for use in field emergency medicine, ambulances, and by the military. “When a physician suspects stroke, time is of the essence, doctors could use the system to determine treatment that needs to begin immediately," he said in a statement. The system can also monitor a patient continuously, which he said is unique for neurodiagnostics, and can immediately detect changes in a patient's condition. It could potentially be used for hydrocephalus and shunt failure as well.
Using transcranial ultrasound, strokes can be diagnosed with the probes positioned at the thinner areas of the skull. This device, though, doesn’t rely on the skull thickness. It allows physicians to measure the acceleration from the pressure waves created when blood flows into the brain.
Can AI Enhance PET/MRI Assessment for Extraprostatic Tumor Extension in Patients with PCa?
December 17th 2024The use of an adjunctive machine learning model led to 17 and 21 percent improvements in the AUC and sensitivity rate, respectively, for PET/MRI in diagnosing extraprostatic tumor extension in patients with primary prostate cancer.
Can Radiomics Bolster Low-Dose CT Prognostic Assessment for High-Risk Lung Adenocarcinoma?
December 16th 2024A CT-based radiomic model offered over 10 percent higher specificity and positive predictive value for high-risk lung adenocarcinoma in comparison to a radiographic model, according to external validation testing in a recent study.