Imperial Vascular Unit, Imperial College NHS Healthcare Trust, London, United Kingdom.
Department of Surgery and Cancer, Imperial College London, London, United Kingdom.
PLoS One. 2023 Jul 25;18(7):e0286952. doi: 10.1371/journal.pone.0286952. eCollection 2023.
Duplex ultrasound (DUS) is the most widely used method for surveillance of arteriovenous fistulae (AVF) created for dialysis. However, DUS is poor at predicting AVF outcomes and there is a need for novel methods that can more accurately evaluate multidirectional AVF flow. In this study we aimed to evaluate the feasibility of detecting AVF stenosis using a novel method combining tensor-decomposition of B-mode ultrasound cine loops (videos) of blood flow and machine learning classification. Classification of stenosis was based on the DUS assessment of blood flow volume, vessel diameter size, flow velocity, and spectral waveform features. Real-time B-mode cine loops of the arterial inflow, anastomosis, and venous outflow of the AVFs were analysed. Tensor decompositions were computed from both the 'full-frame' (whole-image) videos and 'cropped' videos (to include areas of blood flow only). The resulting output were labelled for the presence of stenosis, as per the DUS findings, and used as a set of features for classification using a Long Short-Term Memory (LSTM) neural network. A total of 61 out of 66 available videos were used for analysis. The whole-image classifier failed to beat random guessing, achieving a mean area under the receiver operating characteristics (AUROC) value of 0.49 (CI 0.48 to 0.50). In contrast, the 'cropped' video classifier performed better with a mean AUROC of 0.82 (CI 0.66 to 0.96), showing promising predictive power despite the small size of the dataset. The combined application of tensor decomposition and machine learning are promising for the detection of AVF stenosis and warrant further investigation.
双功能超声（DUS）是目前用于监测为透析而建立的动静脉瘘（AVF）最广泛使用的方法。然而，DUS 在预测 AVF 结果方面效果不佳，需要新的方法来更准确地评估 AVF 的多向血流。在这项研究中，我们旨在评估一种新的方法检测 AVF 狭窄的可行性，该方法结合了血流 B 型超声电影环（视频）的张量分解和机器学习分类。狭窄的分类是基于 DUS 评估的血流体积、血管直径大小、血流速度和频谱波形特征。分析了 AVF 的动脉流入、吻合和静脉流出的实时 B 型电影环。从“全帧”（全图像）视频和“裁剪”视频（仅包括血流区域）计算张量分解。根据 DUS 结果，对生成的输出进行标记，作为使用长短时记忆（LSTM）神经网络进行分类的特征集。总共分析了 66 个可用视频中的 61 个。全图像分类器未能击败随机猜测，获得的平均接收器工作特征（AUROC）值为 0.49（CI 0.48 至 0.50）。相比之下，裁剪视频分类器的表现更好，平均 AUROC 为 0.82（CI 0.66 至 0.96），尽管数据集较小，但显示出有前途的预测能力。张量分解和机器学习的结合有望用于检测 AVF 狭窄，并值得进一步研究。
