A multiscale Laplacian of Gaussian filtering approach to automated pulmonary nodule detection from whole-lung low-dose CT scans

  • Sergei V. Fotin
  • , Anthony P. Reeves
  • , Alberto M. Biancardi
  • , David F. Yankelevitz
  • , Claudia I. Henschke

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

22 Scopus citations

Abstract

The primary stage of a pulmonary nodule detection system is typically a candidate generator that efficiently provides the centroid location and size estimate of candidate nodules. A scale-normalized Laplacian of Gaussian (LOG) filtering method presented in this paper has been found to provide high sensitivity along with precise locality and size estimation. This approach involves a computationally efficient algorithm that is designed to identify all solid nodules in a whole lung anisotropic CT scan. This nodule candidate generator has been evaluated in conjunction with a set of discriminative features that target both isolated and attached nodules. The entire detection system was evaluated with respect to a sizeenriched dataset of 656 whole-lung low-dose CT scans containing 459 solid nodules with diameter greater than 4 mm. Using a soft margin SVM classifier, and setting false positive rate of 10 per scan, we obtained a sensitivity of 97% for isolated, 93% for attached, and 89% for both nodule types combined. Furthermore, the LOG filter was shown to have good agreement with the radiologist ground truth for size estimation

Original languageEnglish
Title of host publicationMedical Imaging 2009
Subtitle of host publicationComputer-Aided Diagnosis
DOIs
StatePublished - 2009
Externally publishedYes
EventMedical Imaging 2009: Computer-Aided Diagnosis - Lake Buena Vista, FL, United States
Duration: 10 Feb 200912 Feb 2009

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7260
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2009: Computer-Aided Diagnosis
Country/TerritoryUnited States
CityLake Buena Vista, FL
Period10/02/0912/02/09

Keywords

  • Algorithm evaluation
  • Automated pulmonary nodule detection
  • Computed tomography (CT)
  • Computer-assisted diagnosis (CAD)
  • Laplacian of Gaussian (LOG)
  • Validation

Fingerprint

Dive into the research topics of 'A multiscale Laplacian of Gaussian filtering approach to automated pulmonary nodule detection from whole-lung low-dose CT scans'. Together they form a unique fingerprint.

Cite this