Building an Ensemble of Probabilistic Classifiers for Lung Nodule Interpretation

When examining Computed Tomography (CT) scans of lungs for potential abnormalities, radiologists make use of lung nodule's semantic characteristics during the analysis. Computer-Aided Diagnostic Characterization (CADc) systems can act as an aid - predicting ratings of these semantic characteristics to aid radiologists in evaluating the nodule and potentially improve the quality and consistency of diagnosis. In our work, we propose a system for predicting the distribution of radiologists' opinions using a probabilistic multi-class classification approach based on combination of belief decision trees and ADABoost ensemble learning approach. To train and test our system we use the National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) dataset, which includes semantic annotations by up to four radiologists for each one of the 914 nodules. Furthermore, we evaluate our probabilistic multi-class classifications using a novel distance-threshold curve technique intended for assessing the performance of uncertain classification systems. We conclude that for the majority of semantic characteristics there exists a set of parameters that significantly improves the performance of the ensemble over the single classifier.