Geometric Total Plaque Area Is an Equally Powerful Phenotype Compared With Carotid Intima-Media Thickness for Stroke Risk Assessment: A Deep Learning Approach

Abstract

Currently, carotid intima-media thickness (cIMT) and geometric total plaque area (gTPA) are computed manually and thus are tedious and prone to interobserver and intraobserver variabilities. This study presents an intelligence-based automated deep learning (DL)-based technique for carotid wall interface detection, cIMT, and lumen diameter (LD) measurements, followed by a 3D cylindrical approach for TPA measurement. The observers were used for manual tracings of which were then used for the design of two DL-based systems. The DL boundaries for inner lumen wall and outer interadventitial borders were used for computing the cIMT and LD. Using cylindrical approach, we computed the gTPA. Furthermore, we compute the 10-year image-based cIMT and gTPA, using the progression rates. A total of 396 B-mode ultrasound right and left common carotid artery images were taken from 203 patients. The mean cIMT and gTPA using DL1 and DL2 is 0.91 mm, 20.52 mm 2 and 0.88 mm, 19.44 mm 2 , respectively. The coefficient of correlation between gTPA and cIMT using DL1 and DL2 is 0.92 (P < .001) and 0.94 (P < .001), respectively. The area under the curve (AUC) for gTPA showed an improvement over cIMT by 14.36% and 12.57% for DL1 and DL2, respectively. The corresponding 10-year risk improvements were 9.09% and 6.26%. Our statistical significance tests successfully passed t test, Mann-Whitney, Wilcoxon, Kolmogorov-Smirnov, and Friedman. The study shows gTPA as an equally powerful carotid risk biomarker like cIMT. Given the cIMT and LD, cylindrical fitting is a fast method for gTPA measurements.

Vascular Implications of COVID-19: Role of Radiological Imaging, Artificial Intelligence, and Tissue Characterization: A Special Report

“…Biswas et al [ 210 ] developed a single-stage DL model for segmenting plaques with significantly lower bias concerning contemporary methods in the same domain. Guadrado et al [ 211 ] used a similar strategy to compute the TPA. In 2020, Biswas et al [ 212 ] developed a two-stage DL model for cIMT and TPA measurement, with even better results.…”

Low-cost preventive screening using carotid ultrasound in patients with diabetes

“…In such cases, the measurement of LI and MA throughout the length of an ultrasound scan, so-called a full-length measurement, may prove to be beneficial (95-100). A recent group by Suri et al has proposed several such full-length automated measurements of CUSIP (41,(95)(96)(97)(98)(99)(100)(101)(102). Furthermore, in order to assess the 10year risk of patients, a similar group has also proposed the automated measurement of 10-year CUSIP that combines the effect of conventional risk factors and the baseline automated CUSIP (13,67).…”

Attention-Based UNet Deep Learning Model for Plaque Segmentation in Carotid Ultrasound for Stroke Risk Stratification: An Artificial Intelligence Paradigm

“…Cardiovascular imaging has widely used supervised learning-based methods. Cuadrado-Godia et al [ 64 ] presented a two-stage model for cIMT and plaque measurement. Zhou et al presented UNet and Unet++ models for plaque segmentation on multi-institutional databases [ 65 , 66 ].…”