Diffusion-weighted imaging of the abdomen: Impact of b-values on texture analysis features
Diffusion-weighted imaging of the abdomen: Impact of b-values on texture analysis features
复制标题
DOI：
10.1002/nbm.3669
复制
发表时间：
2017-01-01
影响因子：
2.9
通讯作者：
Boss, Andreas
中科院分区：
文献类型：
--
作者：
Becker, Anton S.;Wagner, Matthias W.;Boss, Andreas
这项工作的目的是系统地评估 b 值对腹部 MR 扩散加权成像 (DWI) 纹理分析的影响。在 8 名健康男性志愿者中，在 3 T 下采集了 16 个 b 值范围在 0 到 1000 s/mm(2) 的平面回波 DWI 序列。计算了三种不同的表观扩散系数 (ADC) 图（0、 750/100、390、750 s/mm(2)/所有 b 值）。在 DW 图像和 ADC 图上对肝脏、肾脏、脾脏、胰腺、椎旁肌肉和皮下脂肪中感兴趣的矩形区域进行纹理分析，应用根据直方图、灰度共生矩阵 (GLCM) 和灰度游程矩阵 (GLRLM) 计算的 19 个特征。使用线性和指数模型测试b值和纹理特征之间的相关性；最佳拟合由最小残差平方和确定。通过方差分析评估 ADC 图之间的差异。 Bonferroni 校正的 p 值小于 0.008 (=0.05/6) 被认为具有统计显着性。大多数 GLCM 和 GLRLM 衍生的纹理特征（每个器官 12-18）显示与 b 值显着相关。四种纹理特征与所有器官中 b 值的变化显着相关 (p < 0.008)。相关系数在 0.7 和 1.0 之间变化。不同结构的最佳拟合效果各不相同，脂肪主要表现出指数变化（17 个特征），肌肉主要表现出线性变化（12 个特征），而实质器官则表现出混合特征变化。两个 GLCM 特征在不同的 ADC 图谱中显示出显着的变异性。健康组织中的几种纹理特征在不同 b 值下系统地变化，如果分析具有不同 b 值的 DWI 数据，则需要考虑到这一点。直方图和 GLRLM 导出的纹理特征在根据不同 b 值计算的 ADC 地图上是稳定的。
The purpose of this work was to systematically assess the impact of the b-value on texture analysis in MR diffusion-weighted imaging (DWI) of the abdomen.In eight healthy male volunteers, echo-planar DWI sequences at 16 b-values ranging between 0 and 1000 s/mm(2) were acquired at 3 T. Three different apparent diffusion coefficient (ADC) maps were computed (0, 750/100, 390, 750 s/mm(2)/all b-values). Texture analysis of rectangular regions of interest in the liver, kidney, spleen, pancreas, paraspinal muscle and subcutaneous fat was performed on DW images and the ADC maps, applying 19 features computed from the histogram, grey-level co-occurrence matrix (GLCM) and grey-level run-length matrix (GLRLM). Correlations between b-values and texture features were tested with a linear and an exponential model; the best fit was determined by the smallest sum of squared residuals. Differences between the ADC maps were assessed with an analysis of variance. A Bonferroni-corrected p-value less than 0.008 (=0.05/6) was considered statistically significant.Most GLCM and GLRLM-derived texture features (12-18 per organ) showed significant correlations with the b-value. Four texture features correlated significantly with changing b-values in all organs (p < 0.008). Correlation coefficients varied between 0.7 and 1.0. The best fit varied across different structures, with fat exhibiting mostly exponential (17 features), muscle mostly linear (12 features) and the parenchymatous organs mixed feature alterations. Two GLCM features showed significant variability in the different ADC maps.Several texture features vary systematically in healthy tissues at different b-values, which needs to be taken into account if DWI data with different b-values are analyzed. Histogram and GLRLM-derived texture features are stable on ADC maps computed from different b-values.