IEEE Trans Med Imaging. 2018 Dec;37(12):2695-2703. doi: 10.1109/TMI.2018.2849959. Epub 2018 Jun 25.
Temporal enhanced ultrasound (TeUS), comprising the analysis of variations in backscattered signals from a tissue over a sequence of ultrasound frames, has been previously proposed as a new paradigm for tissue characterization. In this paper, we propose to use deep recurrent neural networks (RNN) to explicitly model the temporal information in TeUS. By investigating several RNN models, we demonstrate that long short-term memory (LSTM) networks achieve the highest accuracy in separating cancer from benign tissue in the prostate. We also present algorithms for in-depth analysis of LSTM networks. Our in vivo study includes data from 255 prostate biopsy cores of 157 patients. We achieve area under the curve, sensitivity, specificity, and accuracy of 0.96, 0.76, 0.98, and 0.93, respectively. Our result suggests that temporal modeling of TeUS using RNN can significantly improve cancer detection accuracy over previously presented works.
时频超声（TeUS），包括对一系列超声帧中来自组织的背向散射信号变化的分析，之前已被提出作为一种新的组织特征化范例。在本文中，我们提出使用深度递归神经网络（RNN）来明确地对 TeUS 中的时间信息进行建模。通过研究几种 RNN 模型，我们证明长短期记忆（LSTM）网络在区分前列腺中的癌症与良性组织方面实现了最高的准确性。我们还提出了用于深入分析 LSTM 网络的算法。我们的体内研究包括来自 157 名患者的 255 个前列腺活检样本的数据。我们分别实现了 0.96、0.76、0.98 和 0.93 的曲线下面积、敏感性、特异性和准确性。我们的结果表明，使用 RNN 对 TeUS 进行时间建模可以显著提高癌症检测的准确性，优于之前提出的方法。
