Kaba Şerife, Haci Huseyin, Isin Ali, Ilhan Ahmet, Conkbayir Cenk
Department of Biomedical Engineering, Near East University, TRNC Mersin 10, Nicosia 99138, Turkey.
Department of Electrical-Electronic Engineering, Near East University, TRNC Mersin 10, Nicosia 99138, Turkey.
Diagnostics (Basel). 2023 Jul 5;13(13):2274. doi: 10.3390/diagnostics13132274.
In recent years, the prevalence of coronary artery disease (CAD) has become one of the leading causes of death around the world. Accurate stenosis detection of coronary arteries is crucial for timely treatment. Cardiologists use visual estimations when reading coronary angiography images to diagnose stenosis. As a result, they face various challenges which include high workloads, long processing times and human error. Computer-aided segmentation and classification of coronary arteries, as to whether stenosis is present or not, significantly reduces the workload of cardiologists and human errors caused by manual processes. Moreover, deep learning techniques have been shown to aid medical experts in diagnosing diseases using biomedical imaging. Thus, this study proposes the use of automatic segmentation of coronary arteries using U-Net, ResUNet-a, UNet++, models and classification using DenseNet201, EfficientNet-B0, Mobilenet-v2, ResNet101 and Xception models. In the case of segmentation, the comparative analysis of the three models has shown that U-Net achieved the highest score with a 0.8467 Dice score and 0.7454 Jaccard Index in comparison with UNet++ and ResUnet-a. Evaluation of the classification model's performances has shown that DenseNet201 performed better than other pretrained models with 0.9000 accuracy, 0.9833 specificity, 0.9556 PPV, 0.7746 Cohen's Kappa and 0.9694 Area Under the Curve (AUC).
近年来，冠状动脉疾病（CAD）的患病率已成为全球主要死因之一。准确检测冠状动脉狭窄对于及时治疗至关重要。心脏病专家在解读冠状动脉造影图像以诊断狭窄时使用视觉估计。因此，他们面临各种挑战，包括工作量大、处理时间长和人为误差。冠状动脉的计算机辅助分割和分类，即判断是否存在狭窄，可显著减少心脏病专家的工作量以及手动流程导致的人为误差。此外，深度学习技术已被证明有助于医学专家利用生物医学成像诊断疾病。因此，本研究提出使用U-Net、ResUNet-a、UNet++模型对冠状动脉进行自动分割，并使用DenseNet201、EfficientNet-B0、Mobilenet-v2、ResNet101和Xception模型进行分类。在分割方面，对这三种模型的比较分析表明，与UNet++和ResUnet-a相比，U-Net取得了最高分，其Dice分数为0.8467，Jaccard指数为0.7454。对分类模型性能的评估表明，DenseNet201的表现优于其他预训练模型，准确率为0.9000，特异性为0.9833，阳性预测值为0.9556，Cohen's Kappa为0.7746，曲线下面积（AUC）为0.9694。
