Datasheet2_Radiomics and artificial neural networks modelling for identification of high-risk carotid plaques.docx

ObjectiveIn this study, we aimed to investigate the classification of symptomatic plaques by evaluating the models generated via two different approaches, a radiomics-based machine learning (ML) approach, and an end-to-end learning approach which utilized deep learning (DL) techniques with several representative model frameworks.
MethodsWe collected high-resolution magnetic resonance imaging (HRMRI) data from 104 patients with carotid artery stenosis, who were diagnosed with either symptomatic plaques (SPs) or asymptomatic plaques (ASPs), in two medical centers. 74 patients were diagnosed with SPs and 30 patients were ASPs. Sampling Perfection with Application-optimized Contrasts (SPACE) by using different flip angle Evolutions was used for MRI imaging. Repeated stratified five-fold cross-validation was used to evaluate the accuracy and receiver operating characteristic (ROC) of the trained classifier. The two proposed approaches were investigated to train the models separately. The difference in the model performance of the two proposed methods was quantitatively evaluated to find a better model to differentiate between SPs and ASPs.
Results3D-SE-Densenet-121 model showed the best performance among all prediction models (AUC, accuracy, precision, sensitivity, and F1-score of 0.9300, 0.9308, 0.9008, 0.8588, and 0.8614, respectively), which were 0.0689, 0.1119, 0.1043, 0.0805, and 0.1089 higher than the best radiomics-based ML model (MLP). Decision curve analysis showed that the 3D-SE-Densenet-121 model delivered more net benefit than the best radiomics-based ML model (MLP) with a wider threshold probability.
ConclusionThe DL models were able to accurately differentiate between symptomatic and asymptomatic carotid plaques with limited data, which outperformed radiomics-based ML models in identifying symptomatic plaques.

**研究目的**：本研究旨在通过评估两种不同方法构建的模型，对症状性斑块开展分类识别研究；两种方法分别为基于放射组学的机器学习（Machine Learning, ML）方法，以及采用深度学习（Deep Learning, DL）技术与多种典型模型架构的端到端学习方法。
**研究方法**：本研究于两家医学中心收集了104例颈动脉狭窄患者的高分辨率磁共振成像（high-resolution magnetic resonance imaging, HRMRI）数据，所有患者均经诊断为症状性斑块（symptomatic plaques, SPs）或无症状性斑块（asymptomatic plaques, ASPs），其中74例确诊为症状性斑块，30例为无症状性斑块。MRI成像采用基于不同翻转角演化的应用优化对比度采样完美化（Sampling Perfection with Application-optimized Contrasts, SPACE）序列。采用重复分层五折交叉验证评估训练后分类器的准确率与受试者工作特征（receiver operating characteristic, ROC）曲线。分别基于两种所提出的方法训练模型，并定量评估两种方法的模型性能差异，以筛选出更优的症状性与无症状性斑块鉴别模型。
**研究结果**：在所有预测模型中，3D-SE-Densenet-121模型表现最优，其受试者工作特征曲线下面积（AUC）、准确率、精确率、灵敏度与F1分数分别为0.9300、0.9308、0.9008、0.8588与0.8614，较表现最佳的基于放射组学的机器学习模型（MLP）分别高出0.0689、0.1119、0.1043、0.0805与0.1089。决策曲线分析显示，在更宽的阈值概率范围内，3D-SE-Densenet-121模型较最佳放射组学机器学习模型（MLP）可获得更多净获益。
**研究结论**：在有限数据条件下，深度学习模型可准确鉴别症状性与无症状性颈动脉斑块，且在识别症状性斑块方面优于基于放射组学的机器学习模型。