Su Shan-Shan, Li Li-Ya, Wang Yi, Li Yuan-Zhe
Department of Ultrasound, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China.
Department of Computed Tomography and Magnetic Resonance Imaging (CT/MRI), The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China.
Front Neurol. 2023 Feb 14;14:1111906. doi: 10.3389/fneur.2023.1111906. eCollection 2023.
This study aims to automatically classify color Doppler images into two categories for stroke risk prediction based on the carotid plaque. The first category is high-risk carotid vulnerable plaque, and the second is stable carotid plaque.
In this research study, we used a deep learning framework based on transfer learning to classify color Doppler images into two categories: one is high-risk carotid vulnerable plaque, and the other is stable carotid plaque. The data were collected from the Second Affiliated Hospital of Fujian Medical University, including stable and vulnerable cases. A total of 87 patients with risk factors for atherosclerosis in our hospital were selected. We used 230 color Doppler ultrasound images for each category and further divided those into the training set and test set in a ratio of 70 and 30%, respectively. We have implemented Inception V3 and VGG-16 pre-trained models for this classification task.
Using the proposed framework, we implemented two transfer deep learning models: Inception V3 and VGG-16. We achieved the highest accuracy of 93.81% by using fine-tuned and adjusted hyperparameters according to our classification problem.
In this research, we classified color Doppler ultrasound images into high-risk carotid vulnerable and stable carotid plaques. We fine-tuned pre-trained deep learning models to classify color Doppler ultrasound images according to our dataset. Our suggested framework helps prevent incorrect diagnoses caused by low image quality and individual experience, among other factors.
本研究旨在基于颈动脉斑块将彩色多普勒图像自动分类为两类，用于中风风险预测。第一类是高危颈动脉易损斑块，第二类是稳定颈动脉斑块。
在本研究中，我们使用基于迁移学习的深度学习框架将彩色多普勒图像分为两类：一类是高危颈动脉易损斑块，另一类是稳定颈动脉斑块。数据收集自福建医科大学附属第二医院，包括稳定和易损病例。我们医院共选取了87例有动脉粥样硬化危险因素的患者。我们为每类使用了230幅彩色多普勒超声图像，并进一步分别以70%和30%的比例将其分为训练集和测试集。我们针对此分类任务实现了Inception V3和VGG - 16预训练模型。
使用所提出的框架，我们实现了两个迁移深度学习模型：Inception V3和VGG - 16。通过根据我们的分类问题对超参数进行微调与调整，我们取得了93.81%的最高准确率。
在本研究中，我们将彩色多普勒超声图像分类为高危颈动脉易损斑块和稳定颈动脉斑块。我们对预训练的深度学习模型进行微调，以根据我们的数据集对彩色多普勒超声图像进行分类。我们提出的框架有助于防止因图像质量低和个人经验等因素导致的误诊。
