A ranking-based lung nodule image classification method using unlabeled image knowledge

Fan Zhang, Yang Song, Weidong Cai, Yun Zhou, Michael Fulham, Stefan Eberl, Shimin Shan, Dagan Feng

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

14 Scopus citations

Abstract

In this paper, we propose a novel semi-supervised classification method for four types of lung nodules, i.e., well-circumscribed, vascularized, juxta-pleural and pleural-tail, in low dose computed tomography (LDCT) scans. The proposed method focuses on classifier design by incorporating the knowledge extracted from both training and testing datasets, and contains two stages: (1) bipartite graph construction, which presents the direct similar relationship between labeled and unlabeled images, (2) ranking score calculation, which computes the possibility of unlabeled images for each of the given four types. Our proposed method is evaluated on a publicly available dataset and clearly demonstrates its promising classification performance.

Original languageEnglish
Title of host publication2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1356-1359
Number of pages4
ISBN (Electronic)9781467319591
StatePublished - Jul 29 2014
Externally publishedYes
Event2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China
Duration: Apr 29 2014May 2 2014

Publication series

Name2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

Conference

Conference2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
CountryChina
CityBeijing
Period04/29/1405/2/14

Keywords

  • Bipartite graph
  • Classification
  • Lung nodule
  • Ranking score

Fingerprint Dive into the research topics of 'A ranking-based lung nodule image classification method using unlabeled image knowledge'. Together they form a unique fingerprint.

Cite this