Liu Chi-Kuang, Huang Hsuan-Ming
Department of Medical Imaging, Changhua Christian Hospital, 135 Nanxiao St., Changhua County 500, Taiwan.
Institute of Medical Device and Imaging, College of Medicine, Zhongzheng Dist, National Taiwan University, No.1, Sec. 1, Jen Ai Rd, Taipei City, 100, Taiwan.
J Imaging Inform Med. 2025 Aug;38(4):2102-2119. doi: 10.1007/s10278-024-01341-1. Epub 2024 Dec 4.
Dynamic computed tomography (CT)-based brain perfusion imaging is a non-invasive technique that can provide quantitative measurements of cerebral blood flow (CBF), cerebral blood volume (CBV), and mean transit time (MTT). However, due to high radiation dose, dynamic CT scan with a low tube voltage and current protocol is commonly used. Because of this reason, the increased noise degrades the quality and reliability of perfusion maps. In this study, we aim to propose and investigate the feasibility of utilizing a convolutional neural network and a bi-directional long short-term memory model with an attention mechanism to self-supervisedly yield the impulse residue function (IRF) from dynamic CT images. Then, the predicted IRF can be used to compute the perfusion parameters. We evaluated the performance of the proposed method using both simulated and real brain perfusion data and compared the results with those obtained from two existing methods: singular value decomposition and tensor total-variation. The simulation results showed that the overall performance of parameter estimation obtained from the proposed method was superior to that obtained from the other two methods. The experimental results showed that the perfusion maps calculated from the three studied methods were visually similar, but small and significant differences in perfusion parameters between the proposed method and the other two methods were found. We also observed that there were several low-CBF and low-CBV lesions (i.e., suspected infarct core) found by all comparing methods, but only the proposed method revealed longer MTT. The proposed method has the potential to self-supervisedly yield reliable perfusion maps from dynamic CT images.
基于动态计算机断层扫描（CT）的脑灌注成像是一种非侵入性技术，可提供脑血流量（CBF）、脑血容量（CBV）和平均通过时间（MTT）的定量测量。然而，由于辐射剂量高，通常采用低管电压和电流协议的动态CT扫描。因此，增加的噪声会降低灌注图的质量和可靠性。在本研究中，我们旨在提出并研究利用卷积神经网络和具有注意力机制的双向长短期记忆模型从动态CT图像中自监督生成脉冲残留函数（IRF）的可行性。然后，预测的IRF可用于计算灌注参数。我们使用模拟和真实脑灌注数据评估了所提出方法的性能，并将结果与从奇异值分解和张量全变分这两种现有方法获得的结果进行了比较。模拟结果表明，所提出方法获得的参数估计总体性能优于其他两种方法。实验结果表明，三种研究方法计算出的灌注图在视觉上相似，但在所提出方法与其他两种方法之间的灌注参数上发现了微小但显著的差异。我们还观察到，所有比较方法都发现了几个低CBF和低CBV病变（即疑似梗死核心），但只有所提出的方法显示出更长的MTT。所提出的方法有潜力从动态CT图像中自监督生成可靠的灌注图。
