Kakar Manish, Olsen Dag Rune
Department of Radiation Biology, Institute for Cancer Research, Rikshospitalet-Radiumhospitalet Medical centre, Oslo, Norway.
Comput Med Imaging Graph. 2009 Jan;33(1):72-82. doi: 10.1016/j.compmedimag.2008.10.009. Epub 2008 Dec 6.
In this study, a fully automated texture-based segmentation and recognition system for lesion and lungs from CT of thorax is presented. For the segmentation part, we have extracted texture features by Gabor filtering the images, and, then combined these features to segment the target volume by using Fuzzy C Means (FCM) clustering. Since clustering is sensitive to initialization of cluster prototypes, optimal initialization of the cluster prototypes was done by using a Genetic Algorithm. For the recognition stage, we have used cortex like mechanism for extracting statistical features in addition to shape-based features. The segmented regions showed a high degree of imbalance between positive and negative samples, so we employed over and under sampling for balancing the data. Finally, the balanced and normalized data was subjected to Support Vector Machine (SimpleSVM) for training and testing. Results reveal an accuracy of delineation to be 94.06%, 94.32% and 89.04% for left lung, right lung and lesion, respectively. Average sensitivity of the SVM classifier was seen to be 89.48%.
在本研究中，提出了一种用于从胸部CT中对病变和肺部进行基于纹理的全自动分割与识别系统。对于分割部分，我们通过对图像进行Gabor滤波来提取纹理特征，然后使用模糊C均值（FCM）聚类将这些特征组合起来以分割目标体积。由于聚类对聚类原型的初始化敏感，因此通过使用遗传算法对聚类原型进行了最优初始化。对于识别阶段，除了基于形状的特征外，我们还使用了类似皮层的机制来提取统计特征。分割区域在正样本和负样本之间表现出高度不平衡，因此我们采用过采样和欠采样来平衡数据。最后，将平衡和归一化的数据用于支持向量机（SimpleSVM）进行训练和测试。结果显示，左肺、右肺和病变的勾画准确率分别为94.06%、94.32%和89.04%。支持向量机分类器的平均灵敏度为89.48%。
