基于SVM的腹部CT序列图像肝脏自动分割

Automatical Liver Segmentation From Abdominal CT Volumes Based on SVM

针对腹部CT序列图像因邻近器官对比度低以及肝脏形状不一致等造成的肝脏分割困难等问题,提出一种基于SVM的腹部CT序列图像肝脏自动分割方法。首先,选择初始切片并通过阈值法分割初始切片肝脏;其次,提取初始切片肝脏图像的7个有效训练特征作为SVM的输入层,训练分类器并分割相邻切片;最后,在后处理阶段对SVM分割结果进行形态学操作,得到最终的CT序列肝脏分割结果。在真实病例数据集上的测试结果表明,该算法在腹部CT序列肝脏分割上有较好表现。

In order to solve the problem of liver segmentation for abdominal computed tomography（CT） sequence image caused by low contrast of adjacent organs and different liver shapes, an automatic liver segmentation method based on SVM is proposed. First, segment the liver in the initial slice by a threshold method. Then, seven effective training features are extracted from the initial slice liver image as the input of SVM classifier, after this, train the classifier and the segment the adjacent slices; finally, the results of the SVM segmentation are operated in the post-processing stage, and the final result of the liver segmentation is obtained. The test results on real case dataset show that the algorithm performs well in liver segmentation of abdominal CT sequences.