Joasil Arielle S, Therien Aidan M, Hendon Christine P
Columbia University, Department of Electrical Engineering, New York, United States.
J Biomed Opt. 2025 Jan;30(1):016005. doi: 10.1117/1.JBO.30.1.016005. Epub 2025 Jan 21.
Radiofrequency ablation to treat atrial fibrillation (AF) involves isolating the pulmonary vein from the left atria to prevent AF from occurring. However, creating ablation lesions within the pulmonary veins can cause adverse complications.
We propose automated classification algorithms to classify optical coherence tomography (OCT) volumes of human venoatrial junctions.
A dataset of comprehensive OCT volumes of 26 venoatrial junctions was used for this study. Texture, statistical, and optical features were extracted from OCT patches. Patches were classified as a left atrium or pulmonary vein using random forest (RF), logistic regression (LR), and convolutional neural networks (CNNs). The features were inputs into the RF and LR classifiers. The inputs to the CNNs included: (1) patches and (2) an ensemble of patches and patch-derived features.
Utilizing a sevenfold cross-validation, the patch-only CNN balances sensitivity and specificity best, with an area under the receiver operating characteristic (AUROC) curve of across the test sets. RF is more sensitive than LR, with an AUROC curve of .
Cardiac tissues can be identified in benchtop OCT images by automated analysis. Extending this analysis to data obtained is required to tune automated analysis further. Performing this classification could aid doctors in identifying substrates of interest and treating AF.
射频消融治疗心房颤动（AF）涉及将肺静脉与左心房隔离以防止AF发生。然而，在肺静脉内形成消融损伤可能会导致不良并发症。
我们提出自动分类算法来对人类静脉心房连接的光学相干断层扫描（OCT）体积进行分类。
本研究使用了包含26个静脉心房连接的综合OCT体积数据集。从OCT斑块中提取纹理、统计和光学特征。使用随机森林（RF）、逻辑回归（LR）和卷积神经网络（CNN）将斑块分类为左心房或肺静脉。这些特征被输入到RF和LR分类器中。CNN的输入包括：（1）斑块和（2）斑块及其衍生特征的集合。
利用七重交叉验证，仅斑块的CNN在平衡敏感性和特异性方面表现最佳，在整个测试集中，受试者操作特征（AUROC）曲线下面积为 。RF比LR更敏感，AUROC曲线为 。
通过自动分析可以在台式OCT图像中识别心脏组织。需要将此分析扩展到所获得的数据，以进一步调整自动分析。进行这种分类可以帮助医生识别感兴趣的基质并治疗AF。
