An Early Experience Toward Developing Computer Aided Diagnosis for Gram-Stained Smears Images

Johanna Carvajal, Daniel F. Smith, Kun Zhao, Arnold Wiliem, Paul Finucane, Peter Hobson, Anthony Jennings, Rodney McDougall, Brian Lovell; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 62-68

Gram stained direct smears test is a simple and cost effective way in early identification of infections. Unfortunately, this practice is considered time consuming and labour intensive. Most existing effort in this area is to perform high-magnification analysis of images taken from manually selected areas. In this paper, we address the problem of the automated selection of candidate areas for subsequent high-magnification analysis. We explore the possibility of selecting good candidate areas based on low-magnification images where bacteria are likely to be found when viewed in high-magnification images. To this end, we develop an approach to classify the areas according to the textural information of an image patch. We explore and study the efficacy of traditional textural features such as HOG, LBP, and 2D-DCT. Experiments show that the best variant method is able to select working areas where it is likely to find bacteria in high-powered objective images in a wide-range of images.