Intravital leukocyte detection using the gradient inverse coefficient of variation

Abstract

Abstract-The problem of identifying and counting rolling leukocytes within intravital microscopy is of both theoretical and practical interest. Currently, methods exist for tracking rolling leukocytes in vivo, but these methods rely on manual detection of the cells. In this paper we propose a technique for accurately detecting rolling leukocytes based on Bayesian classification. The classification depends on a feature score, the gradient inverse coefficient of variation (GICOV), which serves to discriminate rolling leukocytes from a cluttered environment. The leukocyte detection process consists of three sequential steps: the first step utilizes an ellipse matching algorithm to coarsely identify the leukocytes by finding the ellipses with a locally maximal GICOV. In the second step, starting from each of the ellipses found in the first step, a B-spline snake is evolved to refine the leukocytes boundaries by maximizing the associated GICOV score. The third and final step retains only the extracted contours that have a GICOV score above the analytically determined threshold. Experimental results using 327 rolling leukocytes were compared to those of human experts and currently used methods. The proposed GICOV method achieves 78.6% leukocyte detection accuracy with 13.1% false alarm rate.

Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review

“…Dong et al [128] have proposed a Bayesian classification based leukocyte detection algorithm on intravital microscopy images, which is composed of three steps: 1) conduct ellipse matching to produce maximal gradient inverse coefficient of variation (GICOV), 2) refine cell contours using B-spline snake with the GICOV constraint, and 3) retain the optimal contours based on a learned Bayesian classifier. A mitotic cell detection method presented in [129] learns a discriminative dictionary with sparse representation and conducts mitosis classification based on the sparse reconstruction errors [168].…”

Smart Spotting of Pulmonary TB Cavities Using CT Images

“…By following this technique, intensity of infection would be accurately determined. The patient can be verified for complete cure, and the treatment can be suspended [9]. …”

An optical counting technique with vertical hydrodynamic focusing for biological cells

“…8 Visually counting the cells is a tedious process, requiring tens of hours for several minutes of video. Automated approaches have been developed for detecting 9 and tracking 10 B-cells in vivo and in vitro, 11 but are computationally expensive, requiring many hours for one single video. Recently, Boyer et al 12 enhanced the tracking process using a Compute…”