VITO:使用逆拓扑优化的血管几何与血流估计
VASTO: Simultaneous reconstruction of vascular geometry and blood flow from tomographic projections via differentiable topology optimization
AI总结:
提出一种流体物理约束的重建框架,利用拓扑优化直接从时间分辨的CTA正弦图联合恢复血管几何和血流速度。
摘要:
计算机断层血管造影(CTA)广泛用于从投影测量重建血管几何,传统方法如滤波反投影(FBP)和迭代重建(IR)是临床标准。随后通过计算流体动力学(CFD)模拟估计血流,这需要预先指定血管几何和边界条件。由于几何在血流估计之前固定,无法恢复未知的解剖特征(例如,缺失的分支或狭窄)。在这项工作中,我们提出了一种流体物理约束的重建框架,利用拓扑优化(TO)直接从时间分辨的CTA正弦图联合恢复血管几何和血流速度。该公式将稳态不可压缩流模型与瞬态对流扩散对比剂传输模型耦合,通过可微投影算子映射到正弦图空间。恢复的速度场提供血流动力学信息,并可以支持下游的壁面剪切应力和流量分布估计,而无需单独的CFD流程。该方法在合成体模上针对不同的稀疏性和噪声水平进行了验证,并在代表性投影数据上进行了验证。
英文摘要:
Computed Tomography Angiography (CTA) is widely used to reconstruct vascular geometry from projection measurements, with conventional approaches such as Filtered Back-Projection (FBP) and Iterative Reconstruction (IR) forming the clinical standard. Despite recent advances, these methods remain susceptible to sparse and noisy measurement, making accurate recovery of critical anatomical features challenging. This consequently leads to poor estimation of blood flow. In this work, we present a fluid-physics-constrained reconstruction framework that leverages topology optimization (TO) to jointly recover vascular geometry and blood flow directly from time-resolved CTA sinograms. The formulation couples a steady incompressible flow model with a transient advection-diffusion contrast transport model, mapped to sinogram space through a differentiable projection operator. The velocity field is recovered as part of the reconstruction, and thus hemodynamic information can be obtained without requiring a separate computational fluid dynamics pipeline. The proposed method is demonstrated on synthetic phantoms under varying sparsity and noise levels, and on representative projection data.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。