Discriminative cue integration for medical image annotation

  • Authors:
  • Tatiana Tommasi;Francesco Orabona;Barbara Caputo

  • Affiliations:
  • IDIAP Research Institute, Centre Du Parc, Avenue des Pres-Beudin 20, P.O. Box 592, CH-1920 Martigny, Switzerland;IDIAP Research Institute, Centre Du Parc, Avenue des Pres-Beudin 20, P.O. Box 592, CH-1920 Martigny, Switzerland;IDIAP Research Institute, Centre Du Parc, Avenue des Pres-Beudin 20, P.O. Box 592, CH-1920 Martigny, Switzerland

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2008

Quantified Score

Hi-index 0.10

Visualization

Abstract

Automatic annotation of medical images is an increasingly important tool for physicians in their daily activity. Hospitals nowadays produce an increasing amount of data. Manual annotation is very costly and prone to human mistakes. This paper proposes a multi-cue approach to automatic medical image annotation. We represent images using global and local features. These cues are then combined using three alternative approaches, all based on the support vector machine algorithm. We tested our methods on the IRMA database, and with two of the three approaches proposed here we participated in the 2007 ImageCLEFmed benchmark evaluation, in the medical image annotation track. These algorithms ranked first and fifth, respectively among all submission. Experiments using the third approach also confirm the power of cue integration for this task.