A cascaded fully convolutional network framework for dilated pancreatic duct segmentation
A cascaded fully convolutional network framework for dilated pancreatic duct segmentation
复制标题
DOI：
10.1007/s11548-021-02530-x
复制
发表时间：
2021-12
影响因子：
3
通讯作者：
Chen Shen;H. Roth;Y. Hayashi;M. Oda;Tadaaki Miyamoto;Gen Sato;K. Mori
中科院分区：
文献类型：
--
作者：
Chen Shen;H. Roth;Y. Hayashi;M. Oda;Tadaaki Miyamoto;Gen Sato;K. Mori
目的胰管扩张是胰腺导管腺癌（PDAC）的早期征象.然而，很少有现有的研究集中在扩张的胰管分割作为一个潜在的筛选工具的人没有PDAC。由于缺乏现成的标记数据以及胰管区域与其他区域之间的强烈体素不平衡，扩张的胰管分割是困难的。为了克服这些挑战，我们提出了一种两步方法，使用全卷积网络（FCN）从腹部计算机断层扫描（CT）体积中分割扩张的胰管。方法我们的框架以级联方式分割胰管。胰管占据腹部CT容积的一小部分。因此，为了专注于胰腺区域，我们使用公共胰腺数据集来训练FCN以生成覆盖胰腺的ROI，并使用类似3D U-Net的FCN进行粗略的胰腺分割。为了进一步提高扩张的胰管分割，我们部署了一个跳跃连接在每个相应的分辨率水平和注意力机制的瓶颈层。此外，我们引入了基于Dice损失和Focal损失的组合损失函数。随机数据扩增通过整个实验，以提高概括性的model.ResultsWe手动创建一个扩张的胰管数据集与半自动化的注释工具。实验结果表明，我们提出的框架是实用的扩张胰管分割。平均Dice评分和敏感性分别为49.9%和51.9%。这些结果表明，我们的方法作为一个临床筛选tool.ConclusionsWe调查扩张胰管分割的自动化框架的潜力。级联策略有效地提高了胰管的分割性能。我们对FCNs的修改以及随机数据增强和建议的组合损失函数有助于自动分割。
PurposePancreatic duct dilation can be considered an early sign of pancreatic ductal adenocarcinoma (PDAC). However, there is little existing research focused on dilated pancreatic duct segmentation as a potential screening tool for people without PDAC. Dilated pancreatic duct segmentation is difficult due to the lack of readily available labeled data and strong voxel imbalance between the pancreatic duct region and other regions. To overcome these challenges, we propose a two-step approach for dilated pancreatic duct segmentation from abdominal computed tomography (CT) volumes using fully convolutional networks (FCNs).MethodsOur framework segments the pancreatic duct in a cascaded manner. The pancreatic duct occupies a tiny portion of abdominal CT volumes. Therefore, to concentrate on the pancreas regions, we use a public pancreas dataset to train an FCN to generate an ROI covering the pancreas and use a 3D U-Net-like FCN for coarse pancreas segmentation. To further improve the dilated pancreatic duct segmentation, we deploy a skip connection on each corresponding resolution level and an attention mechanism in the bottleneck layer. Moreover, we introduce a combined loss function based on Dice loss and Focal loss. Random data augmentation is adopted throughout the experiments to improve the generalizability of the model.ResultsWe manually created a dilated pancreatic duct dataset with semi-automated annotation tools. Experimental results showed that our proposed framework is practical for dilated pancreatic duct segmentation. The average Dice score and sensitivity were 49.9% and 51.9%, respectively. These results show the potential of our approach as a clinical screening tool.ConclusionsWe investigate an automated framework for dilated pancreatic duct segmentation. The cascade strategy effectively improved the segmentation performance of the pancreatic duct. Our modifications to the FCNs together with random data augmentation and the proposed combined loss function facilitate automated segmentation.