Automatic stenosis recognition from coronary angiography using convolutional neural networks
Automatic stenosis recognition from coronary angiography using convolutional neural networks
复制标题
DOI：
10.1016/j.cmpb.2020.105819
复制
发表时间：
2021-01-01
影响因子：
6.1
通讯作者：
Choi, Jin Ho
中科院分区：
文献类型：
--
作者：
Moon, Jong Hak;Lee, Da Young;Choi, Jin Ho
背景和目的：冠状动脉疾病主要由冠状动脉管腔的动脉粥样硬化性狭窄引起，是死亡的主要原因。冠状动脉造影是评估冠状动脉狭窄严重程度的标准方法，但经常受到观察者内和观察者间差异的限制。我们提出了一种深度学习算法，自动识别冠状动脉造影图像中的狭窄。方法：所提出的方法包括关键帧检测，用于对每个关键帧上的狭窄进行分类的深度学习模型训练，以及狭窄可能位置的可视化。首先，我们提出了一种算法，自动提取关键帧的诊断所必需的452右冠状动脉造影电影剪辑。然后，我们的深度学习模型使用图像级注释进行训练，以对缩小超过50%的区域进行分类。为了使模型集中在显著特征上，我们应用了自注意机制。狭窄的位置是可视化的使用梯度加权类activation mapping.Results的特征图的激活区域：自动检测到的关键帧是非常接近手动选择的关键帧（平均距离（1.70 +/- 0.12）帧每个剪辑）。该模型使用内部数据集上的关键帧进行训练，并使用内部和外部数据集进行验证。我们的训练方法在交叉验证评估的平均值中实现了0.971的高帧下曲线下面积，0.934的帧准确度和0.965的剪辑准确度。外部验证结果显示，在单一和集合模型中，平均帧式曲线下面积分别为（0.925和0.956）。热图可视化显示了内部和外部数据集中不同类型狭窄的位置。与自我注意机制，狭窄可以精确定位，这有助于准确分类的狭窄类型。结论：我们的自动分类算法可以识别和定位冠状动脉狭窄高度准确。我们的方法可能提供一个筛选和辅助工具的解释冠状动脉造影的基础。(C)2020作者出版社：Elsevier B. V.
Background and objective: Coronary artery disease, which is mostly caused by atherosclerotic narrowing of the coronary artery lumen, is a leading cause of death. Coronary angiography is the standard method to estimate the severity of coronary artery stenosis, but is frequently limited by intraand inter-observer variations. We propose a deep-learning algorithm that automatically recognizes stenosis in coronary angiographic images.Methods: The proposed method consists of key frame detection, deep learning model training for classification of stenosis on each key frame, and visualization of the possible location of the stenosis. Firstly, we propose an algorithm that automatically extracts key frames essential for diagnosis from 452 right coronary artery angiography movie clips. Our deep learning model is then trained with image-level annotations to classify the areas narrowed by over 50 %. To make the model focus on the salient features, we apply a self-attention mechanism. The stenotic locations are visualized using the activated area of feature maps with gradient-weighted class activation mapping.Results: The automatically detected key frame was very close to the manually selected key frame (average distance (1.70 +/- 0.12) frame per clip). The model was trained with key frames on internal datasets, and validated with internal and external datasets. Our training method achieved high frame-wise area-under the-curve of 0.971, frame-wise accuracy of 0.934, and clip-wise accuracy of 0.965 in the average values of cross-validation evaluations. The external validation results showed high performances with the mean frame-wise area-under-the-curve of (0.925 and 0.956) in the single and ensemble model, respectively. Heat map visualization shows the location for different types of stenosis in both internal and external data sets. With the self-attention mechanism, the stenosis could be precisely localized, which helps to accurately classify the stenosis by type.Conclusions: Our automated classification algorithm could recognize and localize coronary artery stenosis highly accurately. Our approach might provide the basis for a screening and assistant tool for the interpretation of coronary angiography. (C) 2020 The Authors. Published by Elsevier B.V.