A new scheme for computer-aided defection of CT lung nodules designed in consideration of ground-glass opacity

Sumiaki Matsumoto, Yoshiharu Ohno, Hitoshi Yamagata, Hiroshi Asahina, Kazuro Sugimura

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

Localized ground-glass opacity (GGO) is an important manifestation of lung cancer in CT images We have developed a new CAD scheme designed to detect both solid nodules and nodules with GGO whose key process is adaptive threshold selection. The scheme was tested with multi-detector row CT images from 50 patients. A total of 129 nodules (consisting of 107 solid nodules and 22 nodules with GGO) of 3 mm or larger in diameter were used as a reference standard. The scheme showed a reasonable performance with 5.8 false positives per case at the sensitivity of 88% (90% for solid nodules and 77% for nodules with GGO).

Original languageEnglish
Pages (from-to)352-354
Number of pages3
JournalInternational Journal of Computer Assisted Radiology and Surgery
Volume1
Issue numberSUPPL. 7
Publication statusPublished - 06-2006

All Science Journal Classification (ASJC) codes

  • Surgery
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'A new scheme for computer-aided defection of CT lung nodules designed in consideration of ground-glass opacity'. Together they form a unique fingerprint.

Cite this