Pulmonary nodule classification: Size distribution issues

A. C. Jirapatnakul, A. P. Reeves, T. V. Apanasovich, A. M. Biancardi, D. F. Yankelevitz, C. I. Henschke

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

8 Scopus citations

Abstract

Automated nodule classification systems determine a model based on features extracted from documented databases of nodules. These databases cover a large size range and have an unequal distribution of malignant and benign nodules, leading to a high correlation between malignancy and size. For two recent studies in the literature, much of the reported performance of the system may be derived from size based on analysis of their size distributions. We performed experiments to determine the effect of unequal size distribution on a nodule classification system's performance. Preliminary results indicate that the performance across the entire dataset (a sensitivity/specificity of 0.85/0.80) does not generalize to a subset of nodules (0.50/0.80), but performance can be improved by specifically training on that subset (0.60/0.80). Additional testing with larger datasets needs to be performed, but results reported in this area are overly optimistic.

Original languageEnglish
Title of host publication2007 4th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro - Proceedings
Pages1248-1251
Number of pages4
DOIs
StatePublished - 2007
Externally publishedYes
Event2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07 - Arlington, VA, United States
Duration: 12 Apr 200715 Apr 2007

Publication series

Name2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings

Conference

Conference2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07
Country/TerritoryUnited States
CityArlington, VA
Period12/04/0715/04/07

Keywords

  • Biomedical image processing
  • Medical diagnosis
  • Pulmonary nodule characterization
  • Size distribution

Fingerprint

Dive into the research topics of 'Pulmonary nodule classification: Size distribution issues'. Together they form a unique fingerprint.

Cite this