Advances in the Application of Artificial Intelligence in the Ultrasound Diagnosis of Vulnerable Carotid Atherosclerotic Plaque: A Systematic Review

Abstract

BACKGROUND: Carotid atherosclerosis is a leading cause of stroke, and early detection via ultrasound is vital. Artificial intelligence enhances ultrasound by improving plaque detection, measurement of intima-media thickness, and risk assessment. This review explores AI's role in advancing ultrasound-based diagnosis of carotid atherosclerosis and its potential to support clinical decision-making.

METHODS: The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta- Analyses) guidelines are adhered to in this systematic review. The purpose of the study is to use Artificial Intelligence role in ultrasound diagnosis of carotid plaques related to different AI tools ascertain the prevalence of stroke and CAD. The databases of PubMed, EMBASE, Scopus, and Cochrane were thoroughly searched.

RESULTS: AI models show strong potential in assessing carotid plaques using features like cIMT and TPA, often outperforming traditional approaches. However, challenges such as limited validation and clinical application persist. Future research should emphasize real-time use and wider clinical integration.

CONCLUSION: AI improves the accuracy and efficiency of carotid ultrasound by automating plaque detection and risk assessment. Its integration into clinical practice may enhance early diagnosis and stroke prevention