The utility of MRI histogram and texture analysis for the prediction of histological diagnosis in head and neck malignancies

The utility of MRI histogram and texture analysis for the prediction of histological diagnosis in head and neck malignancies
复制标题

DOI:
10.1186/s40644-019-0193-9
复制
发表时间:
2019-02-04
期刊:
影响因子:
4.9
通讯作者:
Shirato, Hiroki
Shirato, Hiroki
中科院分区:
医学2区
文献类型:
--
作者:
Fujima, Noriyuki;Homma, Akihiro;Shirato, Hiroki

文献摘要

被引文献

相似文献

目的探讨磁共振脂肪抑制T2加权成像(Fs-T2 WI)直方图和纹理分析在头颈部鳞癌(SCC)和恶性淋巴瘤(ML)病理诊断中的应用价值。具有直方图特征的定量参数(相对平均信号、变异系数、峰度和偏度)和灰度共生矩阵(GLCM)特征(对比度、相关性、能量和均匀性)使用具有手动肿瘤感兴趣区域(ROI)的Fs-T2 WI数据来计算。相对平均信号(3.65 ± 0.86 vs. 2.61 ± 0.49)、对比度(72.9 ± 16.2 vs. 49.3 ± 8.7)和均匀性(2.22 ± 0.25x10(-1)vs. 2.53 ± 0.12x10(-1))。在SCC组织学分级的比较中,低分化SCC的相对平均信号和对比度(2.89 +/- 0.63,56.2 +/- 12.9)显著低于良好/中度SCC(3.85 +/- 0.81,77.5 +/- 13.9)。低分化鳞癌的均匀性(2.56 ± 0.15 × 10 ~(-1))高于高/中度鳞癌(2.1 ± 0.18 × 10 ~(-1))。结论Fs-T2 WI直方图和纹理分析参数可用于头颈部恶性肿瘤组织学类型和分级的无创性预测。
BackgroundTo assess the utility of histogram and texture analysis of magnetic resonance (MR) fat-suppressed T2-weighted imaging (Fs-T2WI) for the prediction of histological diagnosis of head and neck squamous cell carcinoma (SCC) and malignant lymphoma (ML).MethodsThe cases of 57 patients with SCC (45 well/moderately and 12 poorly differentiated SCC) and 10 patients with ML were retrospectively analyzed. Quantitative parameters with histogram features (relative mean signal, coefficient of variation, kurtosis and skewness) and gray-level co-occurrence matrix (GLCM) features (contrast, correlation, energy and homogeneity) were calculated using Fs-T2WI data with a manual tumor region of interest (ROI).ResultsThe following significantly different values were obtained for the total SCC versus ML groups: relative mean signal (3.650.86 vs. 2.61 +/- 0.49), contrast (72.9 +/- 16.2 vs. 49.3 +/- 8.7) and homogeneity (2.22 +/- 0.25x10(-1) vs. 2.53 +/- 0.12x10(-1)). In the comparison of the SCC histological grades, the relative mean signal and contrast were significantly lower in the poorly differentiated SCC (2.89 +/- 0.63, 56.2 +/- 12.9) compared to the well/moderately SCC (3.85 +/- 0.81, 77.5 +/- 13.9). The homogeneity in poorly differentiated SCC (2.56 +/- 0.15x10(-1)) was higher than that of the well/moderately SCC (2.1 +/- 0.18x10(-1)).Conclusions Parameters obtained by histogram and texture analysis of Fs-T2WI may be useful for noninvasive prediction of histological type and grade in head and neck malignancy.