24 March 2016 Pulmonary nodule detection using a cascaded SVM classifier
Author Affiliations +
Abstract
Automatic detection of lung nodules from chest CT has been researched intensively over the last decades resulting also in several commercial products. However, solutions are adopted only slowly into daily clinical routine as many current CAD systems still potentially miss true nodules while at the same time generating too many false positives (FP). While many earlier approaches had to rely on rather few cases for development, larger databases become now available and can be used for algorithmic development. In this paper, we address the problem of lung nodule detection via a cascaded SVM classifier. The idea is to sequentially perform two classification tasks in order to select from an extremely large pool of potential candidates the few most likely ones. As the initial pool is allowed to contain thousands of candidates, very loose criteria could be applied during this pre-selection. In this way, the chances that a true nodule is falsely rejected as a candidate are reduced significantly. The final algorithm is trained and tested on the full LIDC/IDRI database. Comparison is done against two previously published CAD systems. Overall, the algorithm achieved sensitivity of 0.859 at 2.5 FP/volume where the other two achieved sensitivity values of 0.321 and 0.625, respectively. On low dose data sets, only slight increase in the number of FP/volume was observed, while the sensitivity was not affected.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Martin Bergtholdt, Rafael Wiemker, Tobias Klinder, "Pulmonary nodule detection using a cascaded SVM classifier", Proc. SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 978513 (24 March 2016); doi: 10.1117/12.2216747; https://doi.org/10.1117/12.2216747
PROCEEDINGS
11 PAGES


SHARE
Back to Top