Abstract
Accurate multi-organ abdominal CT segmentation is essential to many clinical applications such as computer-aided intervention. As data annotation requires massive human labor from experienced radiologists, it is common that training data are partially labeled, e.g., pancreas datasets only have the pancreas labeled while leaving the rest marked as background. However, these background labels can be misleading in multi-organ segmentation since the "background" usually contains some other organs of interest. To address the background ambiguity in these partially-labeled datasets, we propose Prior-aware Neural Network (PaNN) via explicitly incorporating anatomical priors on abdominal organ sizes, guiding the training process with domain-specific knowledge. More specifically, PaNN assumes that the average organ size distributions in the abdomen should approximate their empirical distributions, a prior statistics obtained from the fully-labeled dataset. As our training objective is difficult to be directly optimized using stochastic gradient descent [20], we propose to reformulate it in a min-max form and optimize it via the stochastic primal-dual gradient algorithm. PaNN achieves state-of-the-art performance on the MICCAI2015 challenge "Multi-Atlas Labeling Beyond the Cranial Vault", a competition on organ segmentation in the abdomen. We report an average Dice score of 84.97%, surpassing the prior art by a large margin of 3.27%.
Abstract (translated)
准确的多器官腹部CT分割对于计算机辅助介入等许多临床应用至关重要。由于数据注释需要来自经验丰富的放射科医生的大量人工,因此通常训练数据部分标记,例如,胰腺数据集只标记胰腺,而其余数据标记为背景。然而,这些背景标签在多器官分割中可能会产生误导,因为“背景”通常包含一些其他感兴趣的器官。为了解决这些部分标记的数据集中的背景模糊性,我们提出了预先感知神经网络(PANN),通过明确结合腹部器官大小的解剖学先验,以领域特定的知识指导培训过程。更具体地说,PANN假设腹部的平均器官大小分布应该近似于它们的经验分布,这是从完全标记的数据集中获得的先前统计数据。由于我们的训练目标很难用随机梯度下降法直接优化[20],因此我们建议将其重新表述为最小-最大形式,并通过随机原始双梯度算法对其进行优化。Pann在Miccai2015挑战赛“颅穹以外的多图集标记”中获得了最先进的表现,这是一项腹部器官分割的竞赛。我们报告平均骰子分数为84.97%,比现有技术高出3.27%。
URL
https://arxiv.org/abs/1904.06346