Abstract
Artificial intelligence (AI) has been increasingly applied to carotid ultrasound, but most approaches emphasize post-acquisition image analysis rather than real-time acquisition guidance. For inexperienced operators, the main barrier is often not image interpretation, but obtaining standardized views and completing the scanning workflow correctly. This preliminary comparative feasibility study evaluated an AIguided user interface for carotid ultrasound acquisition in zero-experience operators. Thirty operators were included in each condition, with 60 carotid side-level scans per group. The AI-guided workflow provided realtime assistance for vessel localization, centering, segmentation, segmental prompts, bifurcation recognition, probe rotation, longitudinal-view confirmation, intima-media thickness(IMT) measurement, and Doppler velocity acquisition. The manual group performed the same workflow after brief instruction without AI prompts. AI guidance reduced the overall human intervention rate from 70.0% to 20.0% and reduced mean scan time from approximately 147 to 54 seconds per side. In the AI-guided group, transverse-plane common carotid artery localization succeeded in all scans, and bifurcation recognition with longitudinal-view transition and diagnostic-quality pulsed-wave Doppler acquisition each succeeded in 58/60 scans (96.7%). These findings suggest that AI-guided scanning may help zero-experience operators complete carotid ultrasound acquisition more independently and consistently, supporting broader use in training, primary care, community screening, and other non-specialist settings.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/CREATE_011.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=M3AzaCLyv3
BibTex
@InProceedings{LiuRan_AIGuided_MICCAISAT2026,
author = { Liu, Ran AND Chen, Mingcong AND Fan, Siqi AND Xing, Yingqi AND Liu, Hongbin},
title = { { AI-Guided User Interface Enables Standardized Carotid Ultrasound Scanning After Minimal Training: A Comparative Experimental Study } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17275},
month = {pending},
page = {pending}
}