Department of Simulation and Graphics, University of Magdeburg Universitätsplatz 2, Magdeburg, 39106 Germany.
Department of Simulation and Graphics, University of Magdeburg Universitätsplatz 2, Magdeburg, 39106 Germany.
Comput Methods Programs Biomed. 2019 Aug;177:47-56. doi: 10.1016/j.cmpb.2019.05.003. Epub 2019 May 16.
We propose an automatic approach for fast vertebral body segmentation in three-dimensional magnetic resonance images of the whole spine. Previous works are limited to the lower thoracolumbar section and often take minutes to compute, which is problematic in clinical routine, for study data sets with numerous subjects or when the cervical or upper thoracic spine is to be analyzed.
We address these limitations by a novel graph cut formulation based on vertebra patches extracted along the spine. For each patch, our formulation incorporates appearance and shape information derived from a task-specific convolutional neural network as well as star-convexity constraints that ensure a topologically correct segmentation of each vertebra. When segmenting vertebrae individually, ambiguities will occur due to overlapping segmentations of adjacent vertebrae. We tackle this problem by novel non-overlap constraints between neighboring patches based on so-called encoding swaps. The latter allow us to obtain a globally optimal multi-label segmentation of all vertebrae in polynomial time.
We validated our approach on two data sets. The first contains T- and T-weighted whole spine images of 64 subjects with varying health conditions. The second comprises 23 T-weighted thoracolumbar images of young healthy adults and is publicly available. Our method yielded Dice coefficients of 93.8 ± 2.6% and 96.0 ± 1.0% for both data sets with a run time of 1.35 ± 0.08 s and 0.90 ± 0.03 s per vertebra on consumer hardware. A complete whole spine segmentation took 32.4 ± 1.92 s on average.
Our results are superior to those of previous works at a fraction of their run time, which illustrates the efficiency and effectiveness of our whole spine segmentation approach.
我们提出了一种快速的三维磁共振全脊柱椎体自动分割方法。以前的工作仅限于胸腰椎下段，并且通常需要几分钟的计算时间，这在临床常规中存在问题，例如当需要分析大量患者的研究数据集或颈椎或胸椎时。
我们通过一种新颖的基于脊柱提取的椎体补丁的图割公式来解决这些限制。对于每个补丁，我们的公式结合了来自特定任务的卷积神经网络的外观和形状信息，以及保证每个椎体拓扑正确分割的星形凸约束。当单独分割椎体时，由于相邻椎体的重叠分割，会出现歧义。我们通过基于所谓的编码交换的相邻补丁之间的新的非重叠约束来解决此问题。后者允许我们在多项式时间内获得所有椎体的全局最优多标签分割。
我们在两个数据集上验证了我们的方法。第一个数据集包含 64 名不同健康状况的 T-和 T 加权全脊柱图像。第二个数据集包含 23 名年轻健康成年人的 T 加权胸腰椎图像，可公开获得。我们的方法在两个数据集上的 Dice 系数分别为 93.8 ± 2.6%和 96.0 ± 1.0%，运行时间分别为 1.35 ± 0.08 s 和 0.90 ± 0.03 s/椎体，在消费硬件上。完整的全脊柱分割平均用时 32.4 ± 1.92 s。
与以前的工作相比，我们的结果在运行时间的一小部分上具有优势，这说明了我们的全脊柱分割方法的效率和有效性。
