Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Clinical Image Processing Service, Radiology and Imaging Sciences Department, National Institutes of Health Clinical Center, Bethesda, MD 20892-1182, USA.
Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Clinical Image Processing Service, Radiology and Imaging Sciences Department, National Institutes of Health Clinical Center, Bethesda, MD 20892-1182, USA.
Med Image Anal. 2018 Apr;45:94-107. doi: 10.1016/j.media.2018.01.006. Epub 2018 Feb 1.
Accurate and automatic organ segmentation from 3D radiological scans is an important yet challenging problem for medical image analysis. Specifically, as a small, soft, and flexible abdominal organ, the pancreas demonstrates very high inter-patient anatomical variability in both its shape and volume. This inhibits traditional automated segmentation methods from achieving high accuracies, especially compared to the performance obtained for other organs, such as the liver, heart or kidneys. To fill this gap, we present an automated system from 3D computed tomography (CT) volumes that is based on a two-stage cascaded approach-pancreas localization and pancreas segmentation. For the first step, we localize the pancreas from the entire 3D CT scan, providing a reliable bounding box for the more refined segmentation step. We introduce a fully deep-learning approach, based on an efficient application of holistically-nested convolutional networks (HNNs) on the three orthogonal axial, sagittal, and coronal views. The resulting HNN per-pixel probability maps are then fused using pooling to reliably produce a 3D bounding box of the pancreas that maximizes the recall. We show that our introduced localizer compares favorably to both a conventional non-deep-learning method and a recent hybrid approach based on spatial aggregation of superpixels using random forest classification. The second, segmentation, phase operates within the computed bounding box and integrates semantic mid-level cues of deeply-learned organ interior and boundary maps, obtained by two additional and separate realizations of HNNs. By integrating these two mid-level cues, our method is capable of generating boundary-preserving pixel-wise class label maps that result in the final pancreas segmentation. Quantitative evaluation is performed on a publicly available dataset of 82 patient CT scans using 4-fold cross-validation (CV). We achieve a (mean ± std. dev.) Dice similarity coefficient (DSC) of 81.27 ± 6.27% in validation, which significantly outperforms both a previous state-of-the art method and a preliminary version of this work that report DSCs of 71.80 ± 10.70% and 78.01 ± 8.20%, respectively, using the same dataset.
从 3D 放射扫描中准确且自动地分割器官是医学图像分析中的一个重要而具有挑战性的问题。具体来说，作为一个小、软、灵活的腹部器官，胰腺在形状和体积上具有非常高的个体间解剖变异性。这使得传统的自动分割方法无法达到高精度，尤其是与肝脏、心脏或肾脏等其他器官的性能相比。为了弥补这一差距，我们提出了一种基于两阶段级联方法的自动系统，用于从 3D 计算机断层扫描（CT）体积中分割胰腺，该系统包括胰腺定位和胰腺分割。对于第一步，我们从整个 3D CT 扫描中定位胰腺，为更精细的分割步骤提供可靠的边界框。我们引入了一种完全基于深度学习的方法，该方法基于在三个正交轴位、矢状位和冠状位视图上高效应用整体嵌套卷积网络（HNN）。然后使用池化融合所得的 HNN 逐像素概率图，以可靠地生成最大化召回率的胰腺 3D 边界框。我们表明，我们提出的定位器与传统的非深度学习方法以及最近基于使用随机森林分类的超像素空间聚合的混合方法相比具有优势。第二阶段，分割阶段在计算出的边界框内运行，并整合了由两个额外的、单独的 HNN 实现获得的深度学习器官内部和边界图的语义中级线索。通过整合这两个中级线索，我们的方法能够生成保持边界的逐像素类标签图，从而实现最终的胰腺分割。在使用 4 折交叉验证（CV）的 82 名患者 CT 扫描的公共数据集上进行了定量评估。我们在验证中获得了 81.27 ± 6.27%的平均（均值 ± 标准差）Dice 相似系数（DSC），明显优于以前的最先进方法和本工作的初步版本，分别报告了使用相同数据集的 71.80 ± 10.70%和 78.01 ± 8.20%的 DSC。
