Computer-aided detection of masses in full-field digital mammography using screen-film mammograms for training

Phys Med Biol. 2008 Dec 7;53(23):6879-91. doi: 10.1088/0031-9155/53/23/015. Epub 2008 Nov 12.

Abstract

It would be of great value when available databases of screen-film mammography (SFM) images can be used to train full-field digital mammography (FFDM) computer-aided detection (CAD) systems, as compilation of new databases is costly. In this paper, we investigate this possibility. Firstly, we develop a method that converts an FFDM image into an SFM-like representation. In this conversion method, we establish a relation between exposure and optical density by simulation of an automatic exposure control unit. Secondly, we investigate the effects of using the SFM images as training samples compared to training with FFDM images. Our FFDM database consisted of 266 cases, of which 102 were biopsy-proven malignant masses and 164 normals. The images were acquired with systems of two different manufacturers. We found that, when we trained our FFDM CAD system with a small number of images, training with FFDM images, using a five-fold crossvalidation procedure, outperformed training with SFM images. However, when the full SFM database, consisting of 348 abnormal cases (including 204 priors) and 810 normal cases, was used for training, SFM training outperformed FFDMA training. These results show that an existing CAD system for detection of masses in SFM can be used for FFDM images without retraining.

MeSH terms

  • Analog-Digital Conversion
  • Artificial Intelligence
  • Breast Neoplasms / diagnostic imaging*
  • Female
  • Humans
  • Mammography / methods*
  • Pattern Recognition, Automated / methods
  • Radiographic Image Interpretation, Computer-Assisted / methods*
  • X-Ray Intensifying Screens*