Department of Anatomy, Anhui Medical University, 81 Meishan Road, Hefei 230032, China.
Department of Basic Medicine, Anhui Medical College, Hefei 230601, China.
Comput Methods Programs Biomed. 2021 Jul;206:106140. doi: 10.1016/j.cmpb.2021.106140. Epub 2021 May 3.
Early hemorrhage enlargement in hypertensive cerebral hemorrhage indicates a poor prognosis. This study aims to predict the early enlargement of cerebral hemorrhage through the intelligent texture analysis of cerebral hemorrhage after segmentation.
A total of 54 patients with hypertensive intracerebral hemorrhage were selected and divided into enlarged hematoma (enlarged group) and non-enlarged hematoma (negative group). The U-Net Neural network model and contour recognition were used to extract the brain parenchymal region, and Mazda texture analysis software was used to extract regional features. The texture features were reduced by Fisher coefficient (Fisher), classification error probability combined average correlation coefficients (POE + ACC), and mutual information (MI) to select the best feature parameters. B11 module was used to analyze the selected features. The misclassified rate of feature parameters screened by different dimensionality reduction methods was calculated.
The neural network based on U-Net can accurately identify the lesion of cerebral hemorrhage. Among the 54 patients, 18 were in the enlarged group and 36 in the negative group. The parameters of gray level co-occurrence matrix and gray level run length matrix can be used to predict the enlargement of intracerebral hemorrhage. Among the features screened by Fisher, POE + ACC and MI, the texture features of MI showed the lowest misclassified rate, which was 0.
The texture analysis based on U-Net neural network is helpful to predict the early expansion of hypertensive cerebral hemorrhage, and the parameters of gray level co-occurrence matrix and gray level run length matrix under MI dimensionality reduction have the most excellent predictive value.
高血压性脑出血早期血肿扩大提示预后不良。本研究旨在通过对脑出血分割后的智能纹理分析来预测脑出血的早期扩大。
选取 54 例高血压性脑出血患者，分为血肿扩大组（扩大组）和非血肿扩大组（阴性组）。采用 U-Net 神经网络模型和轮廓识别提取脑实质区域，Mazda 纹理分析软件提取区域特征。采用 Fisher 系数（Fisher）、分类误差概率结合平均相关系数（POE+ACC）和互信息（MI）对纹理特征进行降维，选择最佳特征参数。采用 B11 模块对筛选出的特征进行分析，计算不同降维方法筛选出的特征参数的错误分类率。
基于 U-Net 的神经网络能准确识别脑出血病灶。54 例患者中，扩大组 18 例，阴性组 36 例。灰度共生矩阵和灰度行程长度矩阵的参数可用于预测脑出血的扩大。在 Fisher、POE+ACC 和 MI 筛选出的特征中，MI 下的纹理特征错误分类率最低，为 0。
基于 U-Net 神经网络的纹理分析有助于预测高血压性脑出血的早期扩大，MI 降维下的灰度共生矩阵和灰度行程长度矩阵参数具有最佳的预测价值。
