Annals of Family Medicine: Study Finds Using Artificial Intelligence To Enhance Handheld Ultrasound Images May Improve Carotid Plaque Detection in Community Screening

PROVIDENCE, R.I., Sept. 22, 2026 /PRNewswire/ -- A new study published in Annals of Family Medicine finds that an artificial intelligence (AI) super resolution model that sharpens handheld ultrasound images after they are taken may help detect more carotid plaque during community screening. The authors write the approach could support more accurate risk stratification and referral decisions in primary care.

Plaque buildup in the carotid arteries—the vessels in the neck that carry blood to the brain—is a major and modifiable risk factor for ischemic stroke. Conventional ultrasound machines are often unavailable in community clinics because of cost, infrastructure, and maintenance demands. Handheld ultrasound devices are a subset of portable ultrasound systems, yet their lower image quality can make small or faint plaques hard to see.

Researchers at the Affiliated Changsha Central Hospital, University of South China, with colleagues at Macao Polytechnic University, built a super-resolution reconstruction model called Hyper-CycleGAN, which runs on static images after they have been exported from a handheld ultrasound device. The model does not diagnose plaque. It sharpens the image so that the person reading the scan can see the boundary between plaque and the open channel of the artery more clearly. They first tested the model on images from 127 hospital patients, then applied it in community screening. Of 450 adults 40 and older screened across seven communities, 117 participants with 153 plaques had complete, good-quality images and were included in the analysis. AI-enhanced images from the handheld ultrasound were then compared with portable ultrasound images as the reference standard.

The authors describe the AI-enhanced handheld ultrasound as a support tool rather than a stand-alone test for judging whether a plaque is unstable, writing that it "is intended to support triage and prevention in primary care, not to replace guideline-based clinical decision making."

In an accompanying editorial on AI point-of-care ultrasound by Daria Szkwarko, DO, MPH, and colleagues, the authors say the technology works well enough to move things like carotid screening into primary care, but warn that health systems must be prepared to act on what it finds. They argue that referral pathways, quality assurance and workload infrastructure must catch up or the diagnoses may not lead to improved patient care.

AI-Enhanced Super-Resolution Handheld Ultrasound for Carotid Plaque Detection in Community Screening

Jie Lan, MMed; Shun Liu, MD; Haoming Chen, PhD; Tingyu Zhang, MMed; Penghui Zeng, MMed; Jun Li, MS; Linyuan Jin, MMed; Tao Tan, PhD; Meng Du, MD; and Zhiyi Chen, MD

The AI-POCUS Revolution is Here—Are Family Physicians and Our Health Systems Ready?

Daria Szkwarko, DO, MPH; Hussein Elias, MD, MMed; Mena Ramos, MD; and Kevin Bergman, MD

Annals of Family Medicine is an open access, peer-reviewed, indexed research journal that provides a cross-disciplinary forum for new, evidence-based information affecting the primary care disciplines. Launched in May 2003, Annals of Family Medicine is sponsored by six family medical organizations, including the American Academy of Family Physicians, the American Board of Family Medicine, the Society of Teachers of Family Medicine, the Association of Departments of Family Medicine, the Association of Family Medicine Residency Directors, and the North American Primary Care Research Group. Annals of Family Medicine is published online six times each year, charges no fee for publication, and contains original research from the clinical, biomedical, social, and health services areas, as well as contributions on methodology and theory, selected reviews, essays, and editorials. Complete editorial content and interactive discussion groups for each published article can be accessed for free on the journal's website, www.AnnFamMed.org.

SOURCE Annals of Family Medicine