Automated cell analysis in 2D and 3D: A comparative study

  • Authors:

  • Michael G. Meyer;Mark Fauver;J. Richard Rahn;Thomas Neumann;Florence W. Patten;Eric J. Seibel;Alan C. Nelson

  • Affiliations:

  • VisionGate, Inc., 1509 56th Ave. Ct. NW, Gig Harbor, WA 98335, USA;Nortis, Inc. 1509 56th Ave. Ct. NW, Gig Harbor, WA 98335, USA;VisionGate, Inc., 1509 56th Ave. Ct. NW, Gig Harbor, WA 98335, USA;VisionGate, Inc., 1509 56th Ave. Ct. NW, Gig Harbor, WA 98335, USA;VisionGate, Inc., 1509 56th Ave. Ct. NW, Gig Harbor, WA 98335, USA;Department of Mechanical Engineering, University of Washington, 204 Fluke Hall, Box 352600, Seattle, WA 98195, USA;VisionGate, Inc., 1509 56th Ave. Ct. NW, Gig Harbor, WA 98335, USA

  • Venue:
  • Pattern Recognition
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

Optical projection tomographic microscopy is a technique that allows 3D analysis of individual cells. Theoretically, 3D morphometry would more accurately capture cellular features than 2D morphometry. To evaluate this thesis, classifiers based on 3D reconstructions of cell nuclei were compared with 2D images from the same nuclei. Human adenocarcinoma and normal lung epithelium cells were used. Testing demonstrated a three-fold reduction in the false negative rate for adenocarcinoma detection in 3D versus 2D at the same high specificity. We conclude that 3D imaging will potentially expand the horizon for automated cell analysis with broad applications in the biological sciences.