Segmentation of Pancreatic Subregions in Computed Tomography Images.
Segmentation of Pancreatic Subregions in Computed Tomography Images.
复制标题
CT图像中胰腺分区的分割。
DOI：
10.3390/jimaging8070195
复制
发表时间：
2022-07-12
影响因子：
3.2
通讯作者：
中科院分区：
文献类型：
--
作者：
CT图像中胰腺亚区域(头部、体部和尾部)的准确分割为研究胰腺局部的形态和纹理变化提供了机会。量化这些变化有助于了解胰腺的空间异质性，并有助于胰腺癌的诊断和治疗计划。手工勾画胰腺亚区是乏味、耗时的，而且容易出现主观上的不一致。本文提出了一种多阶段解剖引导框架，用于准确、自动地分割CT图像中的胰腺亚区域。使用描绘的胰腺，评估了两个用于次区域分割的软标签图--一个是通过训练完全监督的朴素贝叶斯模型，该模型根据每个次区域结构的解剖排列考虑每个次区域结构的长度和体积比例，另一个是使用传统的深度学习U-Net结构进行3D分割。然后，U网模型估计两个地图的联合概率，并对子区域进行最优分割。使用三个增强腹部CT扫描的数据集来评估模型的性能：一个健康胰腺的公共NIH数据集，以及两个数据集D1和D2(癌前和癌前胰腺各一个)。该模型在使用NIH数据集的多重交叉验证以及使用D1和D2的外部验证中表现出优异的性能。据我们所知，这是第一个用于CT图像中胰腺亚区域分割的自动模型。还建立了由NIH数据集的所有图像中的子区域的参考解剖标记组成的数据集。
The accurate segmentation of pancreatic subregions (head, body, and tail) in CT images provides an opportunity to examine the local morphological and textural changes in the pancreas. Quantifying such changes aids in understanding the spatial heterogeneity of the pancreas and assists in the diagnosis and treatment planning of pancreatic cancer. Manual outlining of pancreatic subregions is tedious, time-consuming, and prone to subjective inconsistency. This paper presents a multistage anatomy-guided framework for accurate and automatic 3D segmentation of pancreatic subregions in CT images. Using the delineated pancreas, two soft-label maps were estimated for subregional segmentation—one by training a fully supervised naïve Bayes model that considers the length and volumetric proportions of each subregional structure based on their anatomical arrangement, and the other by using the conventional deep learning U-Net architecture for 3D segmentation. The U-Net model then estimates the joint probability of the two maps and performs optimal segmentation of subregions. Model performance was assessed using three datasets of contrast-enhanced abdominal CT scans: one public NIH dataset of the healthy pancreas, and two datasets D1 and D2 (one for each of pre-cancerous and cancerous pancreas). The model demonstrated excellent performance during the multifold cross-validation using the NIH dataset, and external validation using D1 and D2. To the best of our knowledge, this is the first automated model for the segmentation of pancreatic subregions in CT images. A dataset consisting of reference anatomical labels for subregions in all images of the NIH dataset is also established.
登录
查看更多内容
影响因子：
1.3
作者：
KREEL, L;HAERTEL, M;KATZ, D
通讯作者：
KATZ, D
早期和晚期胰腺导管腺癌头体/尾部比较基因组分析
影响因子：
5.3
作者：
Zhang X;Feng S;Wang Q;Huang H;Chen R;Xie Q;Zhang W;Wang A;Zhang S;Wang L;Yao M;Ling Q
通讯作者：
Ling Q
影响因子：
2.7
作者：
Luo, Guopei;Jin, Kaizhou;Yu, Xianjun
通讯作者：
Yu, Xianjun
DOI：
10.1080/13651820500540949
发表时间：
2006-01-01
期刊：
HPB : the official journal of the International Hepato Pancreato Biliary Association
影响因子：
--
作者：
Miura, Fumihiko;Takada, Tadahiro;Takeshita, Koji
通讯作者：
Takeshita, Koji
影响因子：
4.6
作者：
Aldoj, Nader;Biavati, Federico;Dewey, Marc
通讯作者：
Dewey, Marc