Department of Radiology, MR Center, Medical University of Vienna, Vienna, Austria.
J Magn Reson Imaging. 2010 Aug;32(2):352-9. doi: 10.1002/jmri.22268.
To determine the feasibility of texture analysis for the classification of liver cysts and hemangiomas, on nonenhanced, zero-fill interpolated T1- and T2-weighted MR images.
Forty-five patients (26 women and 19 men; mean age, 58.1 +/- 16.9 years) with liver cysts or hemangiomas were enrolled in the study. After exclusion of images with artifacts, T1-weighted images of 42 patients, and T2-weighted images of 39 patients, obtained at 3.0 Tesla (T), were available for further analysis. Texture features derived from the gray-level histogram, co-occurrence and run-length matrix, gradient, autoregressive model, and wavelet transform were calculated. Fisher, probability of classification error and average correlation (POE+ACC), and mutual information coefficients were used to extract subsets of optimized texture features. Linear discriminant analysis (LDA) in combination with k nearest neighbor (k-NN) classification, and k-means clustering, were used for lesion classification.
LDA/k-NN produced misclassification rates of 16-18% on T1-weighted, and 12-18% on T2-weighted images. K-means clustering yielded misclassification rates of 15-23% on T1-weighted, and 15-25% on T2-weighted images.
Texture-based classification of liver cysts and hemangiomas is feasible on zero-fill interpolated MR images obtained at 3.0T. Further studies are warranted to investigate the value of texture-based classification of other liver lesions, such as hepatocellular and cholangiocellular carcinoma, on MRI.
在非增强、零填充插值 T1 和 T2 加权 MR 图像上，确定纹理分析用于肝囊肿和血管瘤分类的可行性。
本研究纳入了 45 例肝囊肿或血管瘤患者（26 名女性和 19 名男性；平均年龄，58.1 +/- 16.9 岁）。排除图像伪影后，可进一步分析 42 例患者的 T1 加权图像和 39 例患者的 T2 加权图像。从灰度直方图、共生矩阵和游程长度矩阵、梯度、自回归模型和小波变换中提取纹理特征。使用 Fisher、分类错误概率和平均相关系数（POE+ACC）和互信息系数来提取优化纹理特征的子集。线性判别分析（LDA）结合 k 最近邻（k-NN）分类和 k-均值聚类用于病变分类。
LDA/k-NN 在 T1 加权图像上的错误分类率为 16-18%，在 T2 加权图像上的错误分类率为 12-18%。k-均值聚类在 T1 加权图像上的错误分类率为 15-23%，在 T2 加权图像上的错误分类率为 15-25%。
在 3.0T 获得的零填充插值 MR 图像上，基于纹理的肝囊肿和血管瘤分类是可行的。需要进一步研究来探讨基于纹理的分类在其他肝脏病变（如肝细胞癌和胆管细胞癌）的 MRI 中的价值。
