Key result
AI-derived semi-automatic software for measuring carotid plaque volume was accurate compared to surgical volume (mean difference 0.06 cm3) and took 43% of the time of manual planimetry (P<0.01).
Why the study?
Carotid plaque volume measured by 3D ultrasound may better predict stroke than stenosis, but clinical utility is limited by analysis time.
Does AI-derived semi-automatic software improve the speed and maintain the accuracy and reproducibility of measuring carotid plaque volume compared to manual measurement and surgical specimens in individuals with carotid disease?
Observational (n=121)
Blinded
Does AI-derived semi-automatic software improve the speed and maintain the accuracy and reproducibility of measuring carotid plaque volume compared to manual measurement and surgical specimens in individuals with carotid disease?
AI-enhanced semi-automatic measurement of carotid plaque volume using 3D ultrasound is accurate, reproducible, and significantly faster than manual methods, potentially facilitating its use in large-scale risk stratification.
May speed plaque volumetry in research; leaves open impact on risk stratification and outcomes.
Objective Carotid plaque volume (CPV) can be measured by 3D ultrasound and may be a better predictor of stroke than stenosis, but analysis time limits clinical utility. This study tested the accuracy, reproducibility and time saved of using an artificial intelligence (AI) derived semi-automatic software to measure CPV (‘auto-CPV’). Methods 3D ultrasound images for 121 individuals were analysed by two blinded operators to measure auto-CPV. Corresponding endarterectomy specimen volumes were calculated by the validated saline suspension technique. Inter- and intra-rater agreement plus accuracy compared with the volume of the endarterectomised plaque were calculated. Measurement times were compared with previous manual CPV measurement. Results The mean difference between auto-CPV and surgical volume was small at (±s.d.)[95%CI] 0.06 (0.24) [-0.41 to 0.54] cm3. The intra-class correlation (ICC) was strong at 0.91; 95%CI 0.86-0.94. Inter- and Intra-observer error was low with mean difference (±s.d.)[95%CI] 0.01 (0.26) [-0.5-0.5] cm3 and 0.03 (0.19) [-0.35 - 0.40] cm3 respectively. Both showed excellent ICC with narrow confidence intervals, ICC=0.90; 95% CI (0.85-0.94) and ICC= 0.95; 95% CI (0.92 – 0.96). Auto-CPV measurement took 43% the time of manual planimetry; median (IQR) 05:39 (01:58) minutes compared to 13:05 (04:15) minutes, Wilcoxon rank sum test, p<0.01. Conclusion Auto-CPV assessment is accurate, reproducible and significantly faster than manual planimetry. Improved feasibility means that the utility of CPV can be assessed in large population studies to stratify risk in asymptomatic carotid disease or assess response to medical treatment.
No takes yet. Share an insight, caveat, or question.
Phair et al. (2023) conducted an observational in Carotid plaque (n=121). Artificial intelligence (AI) derived semi-automatic software to measure CPV ('auto-CPV') vs. Surgical volume and manual planimetry was evaluated on Accuracy compared with the volume of the endarterectomised plaque (MD 0.06 cm3, 95% CI -0.41 to 0.54). AI-derived semi-automatic software for measuring carotid plaque volume was accurate compared to surgical volume (mean difference 0.06 cm3) and took 43% of the time of manual planimetry (P<0.01).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: