In reading CT scans with potentially malignant lung nodules, radiologists make use of high level information (semantic characteristics) in their analysis. CAD systems can assist radiologists by offering a “second opinion” - predicting these semantic characteristics for lung nodules. In our previous work, we developed such a CAD system, training and testing it on the publicly available Lung Image Database Consortium (LIDC) dataset, which includes semantic annotations by up to four human radiologists for every nodule. However, due to the lack of ground truth and the uncertainty in the dataset, each nodule was viewed as four distinct instances when training the classifier. In this work, we propose a way of predicting the distribution of opinions of the four radiologists using a multiple-label classification algorithm based on belief decision trees. We evaluate our results using a distance-threshold curve and, measuring the area under this curve, obtain 69% accuracy on the testing subset. We conclude that multiple-label classification algorithms are an appropriate method of representing the diagnoses of multiple radiologists on lung CT scans when a single ground truth is not available.
Zinovev, Dmitriy; Feigenbaum, Jonathan; Raicu, Daniela; and Furst, Jacob. (2010) Predicting Panel Ratings for Semantic Characteristics of Lung Nodules.