Zinovev Dmitriy, Feigenbaum Jonathan, Furst Jacob, Raicu Daniela
DePaul University, Chicago, IL 60604, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:4493-8. doi: 10.1109/IEMBS.2011.6091114.
In reading Computed Tomography (CT) scans with potentially malignant lung nodules, radiologists make use of high level information (semantic characteristics) in their analysis. Computer-Aided Diagnostic Characterization (CADc) systems can assist radiologists by offering a "second opinion"--predicting these semantic characteristics for lung nodules. In this work, we propose a way of predicting the distribution of radiologists' opinions using a multiple-label classification algorithm based on belief decision trees using the National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) dataset, which includes semantic annotations by up to four human radiologists for each one of the 914 nodules. Furthermore, we evaluate our multiple-label results using a novel distance-threshold curve technique--and, measuring the area under this curve, obtain 69% performance on the validation subset. We conclude that multiple-label classification algorithms are an appropriate method of representing the diagnoses of multiple radiologists on lung CT scans when ground truth is unavailable.
在阅读具有潜在恶性肺结节的计算机断层扫描（CT）时，放射科医生在分析过程中会利用高级信息（语义特征）。计算机辅助诊断特征系统（CADc）可以通过提供“第二种意见”来协助放射科医生——预测肺结节的这些语义特征。在这项工作中，我们提出了一种使用基于信念决策树的多标签分类算法来预测放射科医生意见分布的方法，该算法使用美国国立癌症研究所（NCI）肺部图像数据库联盟（LIDC）数据集，其中包含多达四位人类放射科医生对914个结节中每个结节的语义注释。此外，我们使用一种新颖的距离阈值曲线技术评估我们的多标签结果——通过测量该曲线下的面积，在验证子集中获得了69%的性能。我们得出结论，当无法获得真实情况时，多标签分类算法是一种表示多位放射科医生对肺部CT扫描诊断的合适方法。
