Characterization of pulmonary nodules: Effects of size and feature type on reported performance

Artit C. Jirapatnakul, Anthony P. Reeves, Tatiyana V. Apanasovich, Alberto M. Biancardi, David F. Yankelevitz, Claudia I. Henschke

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

Differences in the size distribution of malignant and benign pulmonary nodules in databases used for training and testing characterization systems have a significant impact on the measured performance. The magnitude of this effect and methods to provide more relevant performance results are explored in this paper. Two-and three-dimensional features, both including and excluding size, and two classifiers, logistic regression and distance-weighted nearest-neighbors (dwNN), were evaluated on a database of 178 pulmonary nodules. For the full database, the area under the ROC curve (AUC) of the logistic regression classifier for 2D features with and without size was 0.721 and 0.614 respectively, and for 3D features with and without size, 0.773 and 0.737 respectively. In comparison, the performance using a simple size-threshold classifier was 0.675. In the second part of the study, the performance was measured on a subset of 46 nodules from the entire subset selected to have a similar size-distribution of malignant and benign nodules. For this subset, performance of the size-threshold was 0.504. For logistic regression, the performance for 2D, with and without size, were 0.578 and 0.478, and for 3D, with and without size, 0.671 and 0.767. Over all the databases, logistic regression exhibited better performance using 3D features than 2D features. This study suggests that in systems for nodule classification, size is responsible for a large part of the reported performance. To address this, system performance should be reported with respect to the performance of a size-threshold classifier.

Original languageEnglish
Title of host publicationMedical Imaging 2008 - Computer-Aided Diagnosis
DOIs
StatePublished - 2008
Externally publishedYes
EventMedical Imaging 2008 - Computer-Aided Diagnosis - San Diego, CA, United States
Duration: 19 Feb 200821 Feb 2008

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6915
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2008 - Computer-Aided Diagnosis
Country/TerritoryUnited States
CitySan Diego, CA
Period19/02/0821/02/08

Keywords

  • Classification and classifier design
  • Pulmonary nodule characterization
  • Size distribution
  • X-ray CT

Fingerprint

Dive into the research topics of 'Characterization of pulmonary nodules: Effects of size and feature type on reported performance'. Together they form a unique fingerprint.

Cite this