Liu David, Zhou S Kevin
Siemens Corporation, Corporate Research and Technology, Princeton, NJ, USA.
Med Image Comput Comput Assist Interv. 2012;15(Pt 3):393-401. doi: 10.1007/978-3-642-33454-2_49.
We present a two-stage method for effective and efficient detection of one or multiple anatomical landmarks in an arbitrary 3D volume. The first stage of nearest neighbor matching is to roughly estimate the landmark locations. It searches out of 100,000 volumes for the closest to an input volume and then transfers landmark annotations to the input. The second stage of submodular optimization is to refine the landmark locations by running discriminative landmark detectors within the search ranges constrained by the first stage results. Further it coordinates multiple detectors with a search strategy optimized on the fly to reduce the overall computation cost arising in a submodular formulation. We validate the accuracy, speed and robustness of our approach by detecting body regions and landmarks in a dataset of 2500 CT scans.
我们提出了一种两阶段方法，用于在任意3D体积中有效且高效地检测一个或多个解剖标志点。最近邻匹配的第一阶段是粗略估计标志点位置。它在100,000个体积中搜索与输入体积最接近的体积，然后将标志点注释转移到输入上。子模优化的第二阶段是通过在第一阶段结果所限定的搜索范围内运行判别式标志点检测器来细化标志点位置。此外，它通过动态优化的搜索策略来协调多个检测器，以降低子模公式中产生的总体计算成本。我们通过在包含2500例CT扫描的数据集上检测身体区域和标志点，验证了我们方法的准确性、速度和鲁棒性。
