背景:胰腺是一个复杂的腹部器官,具有许多解剖变异,因此,从医学图像自动胰腺分割是一个具有挑战性的应用。
目的:在本文中,我们提出了从三维(3D)计算机断层扫描(CT)图像中分割单个胰腺亚区域和胰管的框架。
方法:使用多主体强化学习(RL)网络来检测头部的地标,脖子,身体,和胰腺的尾巴,以及选定目标CT图像中沿着胰管的标志。使用地标检测结果,将胰腺图集非刚性地配准到目标图像上,产生胰腺亚区域和导管的解剖概率图。使用多标签3DU-Net体系结构增强了概率图,以获得最终的分割结果。
结果:为了评估我们提出的框架的性能,我们在一个数据库上计算了预测和地面实况手动分割之间的Dice相似性系数(DSC),该数据库包含82张具有手动分割胰腺亚区域的CT图像和37张具有手动分割胰管的CT图像。对于四个胰腺亚区,使用标准3DU-Net,平均DSC从0.38、0.44和0.39提高,注意U-Net,和移位窗口(Swin)U-Net架构,分别为0.51、0.47和0.49,当使用提出的基于RL的框架时。对于胰管,基于RL的框架实现了0.70的平均DSC,显著优于不同数据集上的标准方法和现有方法。
结论:所提出的基于RL的分割框架的结果准确性证明了对标准U-Net架构的分割的改进。
BACKGROUND: The pancreas is a complex abdominal organ with many anatomical variations, and therefore automated pancreas segmentation from medical images is a challenging application.
OBJECTIVE: In this paper, we present a framework for segmenting individual pancreatic subregions and the pancreatic duct from three-dimensional (3D) computed tomography (CT) images.
METHODS: A multiagent reinforcement learning (RL) network was used to detect landmarks of the head, neck, body, and tail of the pancreas, and landmarks along the pancreatic duct in a selected target CT image. Using the landmark detection results, an atlas of pancreases was nonrigidly registered to the target image, resulting in anatomical probability maps for the pancreatic subregions and duct. The probability maps were augmented with multilabel 3D U-Net architectures to obtain the final segmentation results.
RESULTS: To evaluate the performance of our proposed framework, we computed the Dice similarity coefficient (DSC) between the predicted and ground truth manual segmentations on a database of 82 CT images with manually segmented pancreatic subregions and 37 CT images with manually segmented pancreatic ducts. For the four pancreatic subregions, the mean DSC improved from 0.38, 0.44, and 0.39 with standard 3D U-Net, Attention U-Net, and shifted windowing (Swin) U-Net architectures, to 0.51, 0.47, and 0.49, respectively, when utilizing the proposed RL-based framework. For the pancreatic duct, the RL-based framework achieved a mean DSC of 0.70, significantly outperforming the standard approaches and existing methods on different datasets.
CONCLUSIONS: The resulting accuracy of the proposed RL-based segmentation framework demonstrates an improvement against segmentation with standard U-Net architectures.