Institute of Electronics, Lodz University of Technology, 90-924 Lodz, Poland.
Sensors (Basel). 2024 Jan 28;24(3):846. doi: 10.3390/s24030846.
Accurate geometric modeling of blood vessel lumen from 3D images is crucial for vessel quantification as part of the diagnosis, treatment, and monitoring of vascular diseases. Our method, unlike other approaches which assume a circular or elliptical vessel cross-section, employs parametric B-splines combined with image formation system equations to accurately localize the highly curved lumen boundaries. This approach avoids the need for image segmentation, which may reduce the localization accuracy due to spatial discretization. We demonstrate that the model parameters can be reliably identified by a feedforward neural network which, driven by the cross-section images, predicts the parameter values many times faster than a reference least-squares (LS) model fitting algorithm. We present and discuss two example applications, modeling the lower extremities of artery-vein complexes visualized in steady-state contrast-enhanced magnetic resonance images (MRI) and the coronary arteries pictured in computed tomography angiograms (CTA). Beyond applications in medical diagnosis, blood-flow simulation and vessel-phantom design, the method can serve as a tool for automated annotation of image datasets to train machine-learning algorithms.
从 3D 图像中准确地对血管腔进行几何建模对于血管定量分析至关重要,这是血管疾病诊断、治疗和监测的一部分。与其他假设血管横截面为圆形或椭圆形的方法不同,我们的方法使用参数 B 样条结合图像形成系统方程来精确地定位高度弯曲的管腔边界。这种方法避免了图像分割的需要,因为图像分割可能会由于空间离散化而降低定位精度。我们证明,通过前馈神经网络可以可靠地识别模型参数,该神经网络由横截面图像驱动,比参考最小二乘 (LS) 模型拟合算法更快地预测参数值。我们提出并讨论了两个示例应用,即对稳态对比增强磁共振成像 (MRI) 中可视化的动静脉复合体的下肢和计算机断层血管造影 (CTA) 中显示的冠状动脉进行建模。除了在医学诊断中的应用,血流模拟和血管模拟设计之外,该方法还可以作为自动注释图像数据集的工具,以训练机器学习算法。