Kurugol Sila, Washko George R, Estepar Raul San Jose
Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA.
Proc IEEE Int Symp Biomed Imaging. 2014 Apr;2014:1031-1034. doi: 10.1109/ISBI.2014.6868049.
Emphysema has distinct and well-defined visually apparent CT patterns called centrilobular and panlobular emphysema. Existing studies concentrated on the classification of these patterns but they have not looked at the complete evolution of this disease as the destruction of lung parenchyma progresses from normal lung tissue to mild, moderate, and severe disease with complete effacement of the lung architecture. In this paper, we discretize this continuous process into five classes of increasing disease severity and construct a training set of 1161 CT patches. We exploit three solutions to this monotonic multi-class classification problem: a global rankSVM for ranking, hierarchical SVM for classification and a combination of these two, which we call a hierarchical rankSVM. Results showed that both hierarchical approaches were computationally efficient. The classification accuracies were slightly better for hierarchical SVM. However, in addition to classification, ranking approaches also provided a ranking of patterns, which can be utilized as a continuous disease progression score. In terms of the classification accuracy and ratio of pair-wise constraints satisfied, hierarchical rankSVM outperformed the global rankSVM.
肺气肿具有明显且定义明确的、在CT上视觉上可分辨的模式，称为小叶中心型肺气肿和全小叶型肺气肿。现有研究集中于这些模式的分类，但未关注随着肺实质从正常肺组织发展到轻度、中度和重度疾病并伴有肺结构完全消失这一过程中该疾病的完整演变。在本文中，我们将这个连续过程离散为五类疾病严重程度不断增加的情况，并构建了一个包含1161个CT图像块的训练集。我们采用三种方法来解决这个单调多类分类问题：用于排序的全局秩支持向量机、用于分类的分层支持向量机以及这两者的组合，即分层秩支持向量机。结果表明，两种分层方法在计算上都很高效。分层支持向量机的分类准确率略高。然而，除了分类之外，排序方法还提供了模式的排序，可将其用作连续的疾病进展评分。在分类准确率和成对约束满足率方面，分层秩支持向量机优于全局秩支持向量机。
