Abstract
Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.95, F1-score 0.96 and the slowest prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with a low mAP of 0.83, F1-score of 0.80 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, F1-score 0.96 while the prediction speed is 10 fps. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings.
Highlights
Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality
CNNs should ensure the highest performance of real-time image processing for urgent patients who do not have time for prolonged preoperative management and should undergo percutaneous coronary intervention (PCI) immediately following the diagnostic catheterization[19,20]
We examined eight models with various architectures, network complexity, and a number of weights: SSD22, Faster-RCNN23, and RFCN24 object detectors from the Tensorflow Detection Model Zoo[25] based on MobileNet26,27, ResNet[28,29], Inception R esNet[30] and NASNet[31,32]
Summary
Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings. Neural networks used for determining the severity of atherosclerotic lesions should possess superior detection rate as their decisionmaking ability will specify the selection of treatment strategies, including life-saving procedures This situation is typical for stable patients undergoing elective coronary angiography. CNNs should ensure the highest performance of real-time image processing for urgent patients who do not have time for prolonged preoperative management and should undergo percutaneous coronary intervention (PCI) immediately following the diagnostic catheterization (ad-hoc PCI)[19,20]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have