Sciweavers

Share
BIOTECHNO
2008
IEEE

Combining Boundaries and Ratings from Multiple Observers for Predicting Lung Nodule Characteristics

9 years 5 months ago
Combining Boundaries and Ratings from Multiple Observers for Predicting Lung Nodule Characteristics
We use the data collected by the Lung Image Database Consortium (LIDC) for modeling the radiologists’ nodule interpretations based on image content of the nodule by using decision trees. Up to 4 radiologists delineated nodule boundaries and provided ratings for nine nodule characteristics (lobulation, margin, sphericity, etc). Therefore, there can be up to 4 instances per nodule in our data set. However, to learn a good predictive model, the data set should have only one instance per nodule. In this study, we investigate several approaches to combine delineated boundaries and ratings from multiple observers. From our experimental results, we learned that the thresholded p-map analysis approach with the probability threshold Pr>=0.75 provides the best predictive accuracies for the nodule characteristics. In the long run, we expect that the predictive model will improve radiologists’ efficiency and reduce interreader variability.
Ekarin Varutbangkul, Vesna Mitrovic, Daniela Stan
Added 29 May 2010
Updated 29 May 2010
Type Conference
Year 2008
Where BIOTECHNO
Authors Ekarin Varutbangkul, Vesna Mitrovic, Daniela Stan Raicu, Jacob D. Furst
Comments (0)
books