Zeng Wanning, Li Yang, Zhang Jeff L, Chen Tong, Wu Ke, Zong Xiaopeng
School of Biomedical Engineering, ShanghaiTech University, Shanghai, People's Republic of China.
United Imaging Healthcare Group, Shanghai, People's Republic of China.
Biomed Phys Eng Express. 2025 Apr 16;11(3). doi: 10.1088/2057-1976/adc9b6.
. Computed tomography perfusion (CTP) imaging is widely used for assessing acute ischemic stroke. However, conventional methods for quantifying CTP images, such as singular value decomposition (SVD), often lead to oscillations in the estimated residue function and underestimation of tissue perfusion. In addition, the use of global arterial input function (AIF) potentially leads to erroneous parameter estimates. We aim to develop a method for accurately estimating physiological parameters from CTP images.. We introduced a Transformer-based network to learn voxel-wise temporal features of CTP images. With global AIF and concentration time curve (CTC) of brain tissue as inputs, the network estimated local AIF and flow-scaled residue function. The derived parameters, including cerebral blood flow (CBF) and bolus arrival delay (BAD), were validated on both simulated and patient data (ISLES18 dataset), and were compared with multiple SVD-based methods, including standard SVD (sSVD), block-circulant SVD (cSVD) and oscillation-index SVD (oSVD).On data simulating multiple scenarios, local AIF estimated by the proposed method correlated with true AIF with a coefficient of 0.97 ± 0.04 (P < 0.001), estimated CBF with a mean error of 4.95 ml/100 g min, and estimated BAD with a mean error of 0.51 s; the latter two errors were significantly lower than those of the SVD-based methods (P < 0.001). The CBF estimated by the SVD-based methods were underestimated by 10% ∼ 15%. For patient data, the CBF estimates of the proposed method were significantly higher than those of the sSVD method in both normally perfused and ischemic tissues, by 13.83 ml/100 g minor 39.33% and 8.55 ml/100 g minor 57.73% (P < 0.001), respectively, which was in agreement with the simulation results.. The proposed method is capable of estimating local AIF and perfusion parameters from CTP images with high accuracy, potentially improving CTP's performance and efficiency in diagnosing and treating ischemic stroke.
计算机断层扫描灌注（CTP）成像广泛用于评估急性缺血性中风。然而，传统的CTP图像量化方法，如奇异值分解（SVD），往往会导致估计的残差函数出现振荡，并低估组织灌注。此外，使用全局动脉输入函数（AIF）可能会导致错误的参数估计。我们旨在开发一种从CTP图像中准确估计生理参数的方法。我们引入了一个基于Transformer的网络来学习CTP图像的体素级时间特征。以全局AIF和脑组织的浓度-时间曲线（CTC）作为输入，该网络估计局部AIF和血流缩放残差函数。推导得到的参数，包括脑血流量（CBF）和团注到达延迟（BAD），在模拟数据和患者数据（ISLES18数据集）上进行了验证，并与多种基于SVD的方法进行了比较，包括标准SVD（sSVD）、块循环SVD（cSVD）和振荡指数SVD（oSVD）。在模拟多种情况的数据上，所提出方法估计的局部AIF与真实AIF的相关系数为0.97±0.04（P<0.001），估计的CBF平均误差为4.95 ml/100 g·min，估计的BAD平均误差为0.51 s；后两个误差显著低于基于SVD的方法（P<0.001）。基于SVD的方法估计的CBF被低估了10%至15%。对于患者数据，所提出方法在正常灌注组织和缺血组织中的CBF估计值均显著高于sSVD方法，分别高13.83 ml/100 g·min（39.33%）和8.55 ml/100 g·min（57.73%）（P<0.001），这与模拟结果一致。所提出的方法能够从CTP图像中高精度地估计局部AIF和灌注参数，有可能提高CTP在缺血性中风诊断和治疗中的性能和效率。
