The Faster RCNN (ResNet 50) deep learning model demonstrated the best classification performance for distinguishing vulnerable from stable carotid plaques, achieving an accuracy of 0.88, sensitivity of 0.94, specificity of 0.71, and an AUC of 0.91.
Cross-Sectional (n=3,683)
Sí
Do deep learning models accurately detect and classify vulnerable versus stable carotid plaques on ultrasound images?
Deep learning models, particularly Faster RCNN with ResNet 50, can accurately classify carotid plaque vulnerability on ultrasound, offering a reliable tool to assist physicians in stroke risk assessment.
Tasa de eventos absoluta: 0.91% vs 0.85%
valor p: p=<0.001
Background: This study aimed to develop and evaluate the detection and classification performance of different deep learning models on carotid plaque ultrasound images to achieve efficient and precise ultrasound screening for carotid atherosclerotic plaques. Methods: This study collected 5611 carotid ultrasound images from 3683 patients from four hospitals between September 17, 2020, and December 17, 2022. By cropping redundant information from the images and annotating them using professional physicians, the dataset was divided into a training set (3927 images) and a test set (1684 images). Four deep learning models, You Only Look Once Version 7 (YOLO V7) and Faster Region-Based Convolutional Neural Network (Faster RCNN) were employed for image detection and classification to distinguish between vulnerable and stable carotid plaques. Model performance was evaluated using accuracy, sensitivity, specificity, F1 score, and area under curve (AUC), with p < 0.05 indicating a statistically significant difference. Results: We constructed and compared deep learning models based on different network architectures. In the test set, the Faster RCNN (ResNet 50) model exhibited the best classification performance (accuracy (ACC) = 0.88, sensitivity (SEN) = 0.94, specificity (SPE) = 0.71, AUC = 0.91), significantly outperforming the other models. The results suggest that deep learning technology has significant potential for application in detecting and classifying carotid plaque ultrasound images. Conclusions: The Faster RCNN (ResNet 50) model demonstrated high accuracy and reliability in classifying carotid atherosclerotic plaques, with diagnostic capabilities approaching that of intermediate-level physicians. It has the potential to enhance the diagnostic abilities of primary-level ultrasound physicians and assist in formulating more effective strategies for preventing ischemic stroke.
Zhang et al. (Tue,) conducted a cross-sectional in Carotid atherosclerotic plaques (n=3,683). Faster RCNN (ResNet 50) deep learning model vs. Other deep learning models (Faster RCNN Inception V3, YOLO V7) was evaluated on Area under the curve (AUC) for classifying vulnerable vs stable carotid plaques in the test set (p=<0.001). The Faster RCNN (ResNet 50) deep learning model demonstrated the best classification performance for distinguishing vulnerable from stable carotid plaques, achieving an accuracy of 0.88, sensitivity of 0.94, specificity of 0.71, and an AUC of 0.91.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: