IEEE Trans Med Imaging. 2021 Sep;40(9):2367-2379. doi: 10.1109/TMI.2021.3077187. Epub 2021 Aug 31.
A significant research problem of recent interest is the localization of targets like vessels, surgical needles, and tumors in photoacoustic (PA) images.To achieve accurate localization, a high photoacoustic signal-to-noise ratio (SNR) is required. However, this is not guaranteed for deep targets, as optical scattering causes an exponential decay in optical fluence with respect to tissue depth. To address this, we develop a novel deep learning method designed to explicitly exhibit robustness to noise present in photoacoustic radio-frequency (RF) data. More precisely, we describe and evaluate a deep neural network architecture consisting of a shared encoder and two parallel decoders. One decoder extracts the target coordinates from the input RF data while the other boosts the SNR and estimates clean RF data. The joint optimization of the shared encoder and dual decoders lends significant noise robustness to the features extracted by the encoder, which in turn enables the network to contain detailed information about deep targets that may be obscured by noise. Additional custom layers and newly proposed regularizers in the training loss function (designed based on observed RF data signal and noise behavior) serve to increase the SNR in the cleaned RF output and improve model performance. To account for depth-dependent strong optical scattering, our network was trained with simulated photoacoustic datasets of targets embedded at different depths inside tissue media of different scattering levels. The network trained on this novel dataset accurately locates targets in experimental PA data that is clinically relevant with respect to the localization of vessels, needles, or brachytherapy seeds. We verify the merits of the proposed architecture by outperforming the state of the art on both simulated and experimental datasets.
最近，一个备受关注的重要研究问题是在光声（PA）图像中定位目标，如血管、手术针和肿瘤。为了实现精确的定位，需要高的光声信号-噪声比（SNR）。然而，对于深层目标，由于光散射导致光通量随组织深度呈指数衰减，这一点无法保证。为了解决这个问题，我们开发了一种新的深度学习方法，旨在明确表现出对光声射频（RF）数据中噪声的鲁棒性。更准确地说，我们描述并评估了一种由共享编码器和两个并行解码器组成的深度神经网络架构。一个解码器从输入的 RF 数据中提取目标坐标，而另一个则提高 SNR 并估计干净的 RF 数据。共享编码器和双解码器的联合优化赋予了编码器提取的特征显著的噪声鲁棒性，这反过来又使网络能够包含可能被噪声掩盖的深层目标的详细信息。在训练损失函数中添加的新的自定义层和新提出的正则化器（基于观察到的 RF 数据信号和噪声行为设计）用于增加清洁 RF 输出中的 SNR 并提高模型性能。为了考虑到与深度相关的强光散射，我们的网络是用不同散射水平的组织介质中不同深度嵌入的目标的模拟光声数据集进行训练的。该网络在与血管、针或近距离放射治疗种子的定位相关的临床相关实验 PA 数据中准确地定位了目标。我们通过在模拟和实验数据集上都优于最先进的方法来验证所提出架构的优点。
