Wang Ruofan, Zhu Jing, Meng Yuqian, Wang Xuanhao, Chen Ruimin, Wang Kaiyue, Li Chiye, Shi Junhui
Zhejiang Lab, Hangzhou 311100, China.
Zhejiang Lab, Hangzhou 311100, China; Research Center for Humanoid Sensing, Zhejiang Lab, Hangzhou 311100, China.
Comput Methods Programs Biomed. 2023 Dec;242:107822. doi: 10.1016/j.cmpb.2023.107822. Epub 2023 Sep 21.
Photoacoustic computed tomography (PACT) is a non-invasive biomedical imaging technology that has developed rapidly in recent decades, especially has shown potential for small animal studies and early diagnosis of human diseases. To obtain high-quality images, the photoacoustic imaging system needs a high-element-density detector array. However, in practical applications, due to the cost limitation, manufacturing technology, and the system requirement in miniaturization and robustness, it is challenging to achieve sufficient elements and high-quality reconstructed images, which may even suffer from artifacts. Different from the latest machine learning methods based on removing distortions and artifacts to recover high-quality images, this paper proposes an adaptive machine learning method to firstly predict and complement the photoacoustic sensor channel data from sparse array sampling and then reconstruct images through conventional reconstruction algorithms.
We develop an adaptive machine learning method to predict and complement the photoacoustic sensor channel data. The model consists of XGBoost and a neural network named SS-net. To handle data sets of different sizes and improve the generalization, a tunable parameter is used to control the weights of XGBoost and SS-net outputs.
The proposed method achieved superior performance as demonstrated by simulation, phantom experiments, and in vivo experiment results. Compared with linear interpolation, XGBoost, CAE, and U-net, the simulation results show that the SSIM value is increased by 12.83%, 6.78%, 21.46%, and 12.33%. Moreover, the median R is increased by 34.4%, 8.1%, 28.6%, and 84.1% with the in vivo data.
This model provides a framework to predict the missed photoacoustic sensor data on a sparse ring-shaped array for PACT imaging and has achieved considerable improvements in reconstructing the objects. Compared with linear interpolation and other deep learning methods qualitatively and quantitatively, our proposed methods can effectively suppress artifacts and improve image quality. The advantage of our methods is that there is no need for preparing a large number of images as the training dataset, and the data for training is directly from the sensors. It has the potential to be applied to a wide range of photoacoustic imaging detector arrays for low-cost and user-friendly clinical applications.
光声计算机断层扫描（PACT）是一种近几十年来迅速发展的非侵入性生物医学成像技术，尤其在小动物研究和人类疾病早期诊断方面显示出潜力。为了获得高质量图像，光声成像系统需要高元素密度的探测器阵列。然而，在实际应用中，由于成本限制、制造技术以及系统对小型化和鲁棒性的要求，要实现足够数量的元素和高质量的重建图像具有挑战性，甚至可能出现伪影。与基于去除失真和伪影以恢复高质量图像的最新机器学习方法不同，本文提出一种自适应机器学习方法，首先从稀疏阵列采样中预测并补充光声传感器通道数据，然后通过传统重建算法重建图像。
我们开发了一种自适应机器学习方法来预测和补充光声传感器通道数据。该模型由XGBoost和一个名为SS-net的神经网络组成。为了处理不同大小的数据集并提高泛化能力，使用一个可调参数来控制XGBoost和SS-net输出的权重。
如模拟、体模实验和体内实验结果所示，所提出的方法取得了优异的性能。与线性插值、XGBoost、CAE和U-net相比，模拟结果表明结构相似性（SSIM）值分别提高了12.83%、6.78%、21.46%和12.33%。此外，体内数据的中位数R分别提高了34.4%、8.1%、28.6%和84.1%。
该模型提供了一个框架，用于预测PACT成像稀疏环形阵列上缺失的光声传感器数据，并在重建物体方面取得了显著改进。与线性插值和其他深度学习方法进行定性和定量比较，我们提出的方法可以有效抑制伪影并提高图像质量。我们方法的优点是无需准备大量图像作为训练数据集，训练数据直接来自传感器。它有潜力应用于广泛的光声成像探测器阵列，以实现低成本和用户友好的临床应用。
