Automated CT scoring system accurately predicts prognosis in stroke patients

Automated CT scores derived from non-contrast CT and CT perfusion exams may improve prognosis and help guide treatments in acute ischemic stroke patients, according to research published in the European Journal of Radiology

The Alberta Stroke Program Early CT Score (ASPECTS) is a scale that analyzes early ischemic changes identified in multiple portions of the middle cerebral artery. On baseline non-contrast CT (NCCT) exams on stroke patients, ASPECTS has proven to be a valuable prognostic indicator. Although some studies have uncovered inconsistencies in inter-rater agreement in ASPECTS when using NCCT, this is likely due to the reader’s experience level or specialty. 

Researchers suggest that the emergence of artificial intelligence algorithms presents a possible solution to this reproducibility issue. 

“With algorithmic advancement, automated ASPECTS becomes available and may attain equivalent or even superior performance compared to human readers,” corresponding author Ximing Wang, with the department of radiology at the First Affiliated Hospital of Soochow University in China, and coauthors explained. 

CT imaging on stroke patients is critically important to predict prognosis, as certain findings can offer clinicians insight into how patients will respond to various treatments (mechanical thrombectomy, intravenous thrombolysis, etc.). To better understand the role of CT in stroke care, researchers analyzed the agreement of ASPECTS between an automated reader versus human radiologists with varying specialties and experience levels. They also compared the role of NCCT against CT Perfusion (CTP) for prognostic value. 

From the 75 patients studied, the automated and manual interpretations yielded fair to substantial reader agreement with CTP and NCCT-based ASPECTS. Both interpretation methods also revealed a strong correlation between CTP-ASPECTS and infarct core volume, compared to a moderate association between NCCT-based ASPECTS. 

“Automated NCCT-based ASPECTS could achieve substantial agreement with reference standard and exhibited moderate correlation to CTP-defined infarct core,” the experts noted. “Combining CTP with NCCT findings may provide promising prognosis for thrombolysis-treated acute ischemic stroke patients, especially when well-trained staff resource is scarce.” 

You can view the detailed results in the European Journal of Radiology. 

Related Stroke Imaging Content:

Stroke thrombectomy outcomes similar between radiologists, fellowship-trained neurointerventionalists

New CT protocol uses scout images to expedite stroke patients' path to MRI

What decades of data tell us about stroke rates in the U.S.

Most Americans live within an hour of a stroke center

FDA warns providers about potential misuse of imaging-based software for stroke triage

Radiologists must change their approach to stroke care in the AI era

MRI findings associated with poor thrombectomy outcomes after stroke

Risk of recurrent stroke 48% higher among young marijuana users

Hannah murhphy headshot

In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She joined Innovate Healthcare in 2021 and has since put her unique expertise to use in her editorial role with Health Imaging.

Around the web

The new technology shows early potential to make a significant impact on imaging workflows and patient care. 

Richard Heller III, MD, RSNA board member and senior VP of policy at Radiology Partners, offers an overview of policies in Congress that are directly impacting imaging.
 

The two companies aim to improve patient access to high-quality MRI scans by combining their artificial intelligence capabilities.