FEops, Technologiepark- Zwijnaarde 122, Ghent 9052, Belgium.
Department of Electronics and Information Systems, UGent-imec, Technologiepark-Zwijnaarde 126, Ghent 9052, Belgium.
J Interv Cardiol. 2020 May 28;2020:9843275. doi: 10.1155/2020/9843275. eCollection 2020.
Anatomic landmark detection is crucial during preoperative planning of transcatheter aortic valve implantation (TAVI) to select the proper device size and assess the risk of complications. The detection is currently a time-consuming manual process influenced by the image quality and subject to operator variability. In this work, we propose a novel automatic method to detect the relevant aortic landmarks from MDCT images using deep learning techniques. We trained three convolutional neural networks (CNNs) with 344 multidetector computed tomography (MDCT) acquisitions to detect five anatomical landmarks relevant for TAVI planning: the three basal attachment points of the aortic valve leaflets and the left and right coronary ostia. The detection strategy used these three CNN models to analyse a single MDCT image and yield three segmentation volumes as output. These segmentation volumes were averaged into one final segmentation volume, and the final predicted landmarks were obtained during a postprocessing step. Finally, we constructed the aortic annular plane, defined by the three predicted hinge points, and measured the distances from this plane to the predicted coronary ostia (i.e., coronary height). The methodology was validated on 100 patients. The automatic landmark detection was able to detect all the landmarks and showed high accuracy as the median distance between the ground truth and predictions is lower than the interobserver variations (1.5 mm [1.1-2.1], 2.0 mm [1.3-2.8] with a paired difference -0.5 ± 1.3 mm and value <0.001). Furthermore, a high correlation is observed between predicted and manually measured coronary heights (for both = 0.8). The image analysis time per patient was below one second. The proposed method is accurate, fast, and reproducible. Embedding this tool based on deep learning in the preoperative planning routine may have an impact in the TAVI environments by reducing the time and cost and improving accuracy.
解剖标志点检测在经导管主动脉瓣植入术（TAVI）的术前规划中至关重要，可用于选择合适的器械尺寸并评估并发症风险。目前，该检测是一个耗时的手动过程，受到图像质量和操作人员变异性的影响。在这项工作中，我们提出了一种使用深度学习技术从 MDCT 图像中自动检测相关主动脉标志点的新方法。我们使用 344 次多排 CT（MDCT）采集训练了三个卷积神经网络（CNN），以检测与 TAVI 规划相关的五个解剖标志点：主动脉瓣叶的三个基底附着点以及左、右冠状动脉口。该检测策略使用这三个 CNN 模型来分析单个 MDCT 图像，并输出三个分割体积。这些分割体积被平均为一个最终的分割体积，最终预测的标志点是在一个后处理步骤中获得的。最后，我们构建了主动脉环面，由三个预测的铰链点定义，并测量从该平面到预测的冠状动脉口（即冠状动脉高度）的距离。该方法在 100 名患者中进行了验证。自动标志点检测能够检测到所有标志点，并且具有很高的准确性，因为地面真实值和预测值之间的中位数距离小于观察者之间的差异（1.5mm [1.1-2.1]，2.0mm [1.3-2.8]，配对差值为-0.5mm±1.3mm，p 值<0.001）。此外，预测的和手动测量的冠状动脉高度之间存在高度相关性（两者的 r 值均为 0.8）。每位患者的图像分析时间不到一秒。该方法准确、快速且可重复。在 TAVI 环境中，将基于深度学习的这种工具嵌入术前规划常规中，可能会通过减少时间和成本以及提高准确性产生影响。
