Deep Learning-Based Carotid Plaque Ultrasound Image Detection and Classification Study

Abstract

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.

Keywords: artificial intelligence; carotid plaque; deep learning techniques; ischemic stroke; vulnerability.

Fig. 1.

Original ultrasound images of carotid plaque saved in DICOM format. MI, mechanical index; 2D, two dimensional; FR, frequency; DICOM, digital imaging and communications in medicine; RS, radial strain.

Fig. 2.

Automatic detection and identification of vulnerable plaque ultrasound images.

Fig. 3.

Automatic detection and identification of stable plaques in ultrasound images.

Fig. 4.

Faster RCNN (ResNet 50, Inception V3) model detection results. (A) PR curve of the Faster RCNN (ResNet 50) model; (B) PR curve of the Faster RCNN (Inception V3) model; (C) Calibration curve of the Faster RCNN (ResNet 50) model; (D) Calibration curve of the Faster RCNN (Inception V3) model; (E) ROC curve of the Faster RCNN (ResNet 50) model; (F) ROC curve of the Faster RCNN (Inception V3) model. PR, precision recall; ROC, receive operating characteristic; RCNN, Region-Based Convolutional Neural Network; AUC, area under curve.

Fig. 5.

YOLO V7 (ResNet 50, Inception V3) model detection results. (A) PR curve of YOLO V7 (ResNet 50) model; (B) PR curve of YOLO V7 (Inception V3) model; (C) calibration curve of YOLO V7 (ResNet 50) model; (D) calibration curve of YOLO V7 (Inception V3) model; (E) ROC curve of YOLO V7 (ResNet 50) model; (F) ROC curve of the YOLO V7 (Inception V3) model. PR, precision recall; ROC, receive operating characteristic; YOLO V7, You Only Look Once Version 7; AUC, area under curve.

Fig. 6.

Schematic of the Faster RCNN model. RCNN, Region-Based Convolutional Neural Network; RPN, region proposal network; ROI, region of interest.

Fig. 7.

Schematic diagram of the YOLO V7 model. YOLO, You Only Look Once; FPN, feature pyramid network; SPPCSPC, spatial pyramid pool construction statistical process control.