南方医科大学学报

南方医科大学学报 ›› 2024, Vol. 44 ›› Issue (2): 387-396.doi: 10.12122/j.issn.1673-4254.2024.02.22

• • 上一篇    下一篇

基于两阶段分析的多尺度颈动脉斑块检测方法

肖 慧，方威扬，林铭俊，周振忠，费洪文，陈超敏   

  1. 南方医科大学生物医学工程学院，广东 广州 510515；广州尚医网信息技术有限公司，广东 广州 510515；南方医科大学附属广东省人民医院，广东 广州 510180
  • 发布日期:2024-03-14

A multiscale carotid plaque detection method based on two-stage analysis

XIAO Hui, FANG Weiyang, LIN Mingjun, ZHOU Zhenzhong, FEI Hongwen, CHEN Chaomin   

  1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; Guangzhou Shangyi Network Information Technology Co., Ltd., Guangzhou 510515, China; Guangdong Provincial People's Hospital Affiliated to Southern Medical University, Guangzhou 510180, China
  • Published:2024-03-14

RichHTML

1

PDF

43

摘要： 目的 实现从超声图像中准确检测出多种尺度大小的颈动脉斑块。方法 本文提出一种基于深度卷积神经网络的两阶段颈动脉斑块检测方法—SM-YOLO。依次运用中值滤波、直方图均衡化、Gamma变换等算法对数据集进行预处理，提高图像质量。模型的第1阶段基于YOLOX_l目标检测网络构建候选斑块集，添加多尺度图像训练和多尺度图像预测策略，以适应不同形状大小的颈动脉斑块。在第2阶段中，提取并融合方向梯度直方图特征（HOG）和局部二值模式特征（LBP），结合支持向量机分类器（SVM）对候选斑块集进行筛选得到最终的检测结果。将本文构建的模型与多个领先的目标检测模型（YOLOX_l、SSD、EfficientDet、YOLOV5_l、Faster R-CNN）进行定量和可视化结果对比。结果 SM-YOLO在测试集上的召回率为89.44%，精确率为90.96%，F1-Score为90.19%，AP为92.70%，各项性能指标和可视化效果均优于其他几种模型。同时其检测时间比FasterR-CNN模型少3倍，基本满足实时检测的要求。结论 本文的颈动脉斑块检测方法具有较好的性能，对于在超声图像中准确识别颈动脉斑块具有一定的临床应用价值。

关键词: 深度学习；YOLOX；特征融合；SVM；颈动脉斑块

Abstract: : Objective To develop a method for accurate identification of multiscale carotid plaques in ultrasound images. Methods We proposed a two-stage carotid plaque detection method based on deep convolutional neural network (SM-YOLO). A series of algorithms such as median filtering, histogram equalization, and Gamma transformation were used to preprocess the dataset to improve image quality. In the first stage of the model construction, a candidate plaque set was built based on the YOLOX_l target detection network, using multiscale image training and multiscale image prediction strategies to accommodate carotid artery plaques of different shapes and sizes. In the second stage, the Histogram of Oriented Gradient (HOG) features and Local Binary Pattern (LBP) features were extracted and fused, and a Support Vector Machine (SVM) classifier was used to screen the candidate plaque set to obtain the final detection results. This model was compared quantitatively and visually with several target detection models (YOLOX_l, SSD, EfficientDet, YOLOV5_l, Faster R-CNN). Results SM-YOLO achieved a recall of 89.44%, an accuracy of 90.96%, a F1-Score of 90.19%, and an AP of 92.70% on the test set, outperforming other models in all performance indicators and visual effects. The constructed model had a much shorter detection time than the Faster R-CNN model (only one third of that of the latter), thus meeting the requirements of real-time detection. Conclusion The proposed carotid artery plaque detection method has good performance for accurate identification of carotid plaques in ultrasound images.

Key words: deep learning; YOLOX; feature fusion; support vector machine; carotid plaque