Deep learning in vivo catheter tip locations for photoacoustic-guided cardiac interventions.
Deep learning in vivo catheter tip locations for photoacoustic-guided cardiac interventions.
复制标题
DOI：
10.1117/1.jbo.29.s1.s11505
复制
发表时间：
2024-01
影响因子：
3.5
通讯作者：
中科院分区：
文献类型：
--
作者：
介入心脏手术通常需要电离辐射来引导心导管到达心脏。为了减少电离辐射的相关风险，光声成像可以与机器人视觉伺服相结合，最初的演示需要对导管尖端进行分割。然而，应用于传统图像形成方法的典型分割算法容易受到有问题的反射伪影的影响，这损害了导管尖端所需的可检测性和定位。我们描述了一个卷积神经网络和相关的定制，以成功检测和定位由相控阵换能器接收的导管尖端的体内光声信号，相控阵换能器是经胸心脏成像应用的常见换能器。我们用模拟光声通道数据训练了一个网络来识别点源，该点源适当地模拟了插入心导管的光纤尖端的光声信号。该网络通过一个独立的模拟数据集进行了验证，然后对植入离体和活体猪心脏的装有光纤的心导管尖端的数据进行了测试。通过模拟数据验证，该网络在目标深度为20 ~ 100 mm的情况下，得分为98.3%，欧几里得误差（平均值±一个标准差）为。在对离体和体内数据进行测试时，该网络的得分高达100.0%。此外，在离体和体内数据中，对于40 ~ 90 mm的目标深度，相控阵传感器的轴向和横向分辨率分别比轴向和横向分辨率低86.7%和100.0%。这些结果证明了所提出的方法在未来介入心脏病学和心脏电生理学应用中识别光声源的前景。
Interventional cardiac procedures often require ionizing radiation to guide cardiac catheters to the heart. To reduce the associated risks of ionizing radiation, photoacoustic imaging can potentially be combined with robotic visual servoing, with initial demonstrations requiring segmentation of catheter tips. However, typical segmentation algorithms applied to conventional image formation methods are susceptible to problematic reflection artifacts, which compromise the required detectability and localization of the catheter tip. We describe a convolutional neural network and the associated customizations required to successfully detect and localize in vivo photoacoustic signals from a catheter tip received by a phased array transducer, which is a common transducer for transthoracic cardiac imaging applications. We trained a network with simulated photoacoustic channel data to identify point sources, which appropriately model photoacoustic signals from the tip of an optical fiber inserted in a cardiac catheter. The network was validated with an independent simulated dataset, then tested on data from the tips of cardiac catheters housing optical fibers and inserted into ex vivo and in vivo swine hearts. When validated with simulated data, the network achieved an score of 98.3% and Euclidean errors (mean ± one standard deviation) of for target depths of 20 to 100 mm. When tested on ex vivo and in vivo data, the network achieved scores as large as 100.0%. In addition, for target depths of 40 to 90 mm in the ex vivo and in vivo data, up to 86.7% of axial and 100.0% of lateral position errors were lower than the axial and lateral resolution, respectively, of the phased array transducer. These results demonstrate the promise of the proposed method to identify photoacoustic sources in future interventional cardiology and cardiac electrophysiology applications.