Tissue segmentation of computed tomography images using a Random Forest algorithm: a feasibility study.
Tissue segmentation of computed tomography images using a Random Forest algorithm: a feasibility study.
复制标题
DOI：
10.1088/0031-9155/61/17/6553
复制
发表时间：
2016-09-07
影响因子：
3.5
通讯作者：
Kaufman RA
中科院分区：
文献类型：
--
作者：
Polan DF;Brady SL;Kaufman RA
计算机断层摄影（CT）的当前创新集中于放射组学、患者特异性辐射剂量计算和使用迭代重建的图像质量改进，所有这些都需要对CT图像内的组织和器官系统的特定知识。本研究的目的是开发一种全自动的随机森林分类器算法，用于基于儿科和成人CT协议的颈胸盆腔CT检查的分割。七种材料被分类：背景、肺/内部空气或气体、脂肪、肌肉、实体器官实质、血液/对比增强流体和骨组织，使用Matlab和FIJI的可训练Weka分割（TWS）插件。研究了TWS的以下分类器特征滤波器：在体素半径为2n（n从0到4）的情况下评估的最小值、最大值、平均值和方差，沿着降噪和边缘保留滤波器：高斯、双边、双曲和各向异性扩散。随机森林算法使用200棵树，每个节点随机选择2个特征。优化的自动分割算法产生了16个图像特征，包括来自最大值，平均值，方差高斯滤波器的特征。分析了21个患者图像切片中手动分割和随机森林算法分割图像之间的Dice相似系数（DSC）计算。自动算法产生了7种材料类别的分割，儿科患者方案的DSC中位数为0.86 ± 0.03，成人患者方案的DSC中位数为0.85 ± 0.04。此外，对100例随机选择的患者检查进行了分段和分析，证明了平均灵敏度为0.91（范围：0.82-0.98），特异性为0.89（范围：0.70-0.98），准确性为0.90（范围：0.76-0.98）。在这项研究中，我们证明了这种全自动分割工具能够在广泛的患者体质和扫描参数范围内快速准确地分割身体的颈部和躯干。
Current innovation in computed tomography (CT) is focused on radiomics, patient-specific radiation dose calculation, and image quality improvement using iterative reconstruction, all of which require specific knowledge of tissue and organ systems within a CT image. The purpose of this study was to develop a fully automated Random Forest classifier algorithm for segmentation of neck-chest-abdomen-pelvis CT examinations based on pediatric and adult CT protocols. Seven materials were classified: background, lung/internal air or gas, fat, muscle, solid organ parenchyma, blood/contrast enhanced fluid, and bone tissue using Matlab and the Trainable Weka Segmentation (TWS) plugin of FIJI. The following classifier feature filters of TWS were investigated: minimum, maximum, mean, and variance evaluated over a voxel radius of 2n, (n from 0 to 4), along with noise reduction and edge preserving filters: Gaussian, bilateral, Kuwahara, and anisotropic diffusion. The Random Forest algorithm used 200 trees with 2 features randomly selected per node. The optimized auto-segmentation algorithm resulted in 16 image features including features derived from maximum, mean, variance Gaussian and Kuwahara filters. Dice similarity coefficient (DSC) calculations between manually segmented and Random Forest algorithm segmented images from 21 patient image sections, were analyzed. The automated algorithm produced segmentation of seven material classes with a median DSC of 0.86 ± 0.03 for pediatric patient protocols, and 0.85 ± 0.04 for adult patient protocols. Additionally, 100 randomly selected patient examinations were segmented and analyzed, and a mean sensitivity of 0.91 (range: 0.82–0.98), specificity of 0.89 (range: 0.70–0.98), and accuracy of 0.90 (range: 0.76–0.98) were demonstrated. In this study, we demonstrate that this fully automated segmentation tool was able to produce fast and accurate segmentation of the neck and trunk of the body over a wide range of patient habitus and scan parameters.
登录
查看更多内容
DOI：
10.1016/0010-4809(88)90003-1
发表时间：
1988-10-01
期刊：
COMPUTERS AND BIOMEDICAL RESEARCH
影响因子：
--
作者：
KARSSEMEIJER, N;VANERNING, LJTO;EIJKMAN, EGJ
通讯作者：
EIJKMAN, EGJ
影响因子：
0.9
作者：
Sharma N;Aggarwal LM
通讯作者：
Aggarwal LM
用激光多普勒和微CT扫描来表征骨折愈合中的新血管性。
影响因子：
3.2
作者：
Macdonald, W.;Shefelbine, S. J.
通讯作者：
Shefelbine, S. J.
影响因子：
3.8
作者：
Solomon, Justin;Samei, Ehsan
通讯作者：
Samei, Ehsan
影响因子：
7.5
作者：
Wolpert, DH;Macready, WG
通讯作者：
Macready, WG