Optimization-Based Tuberculosis Image Segmentation by Ant Colony Heuristic Method

Abstract

Tuberculosis (TB) is a worldwide health crisis and is the second primary infectious disease that causes death next to human immunodeficiency virus. In this work, an attempt has been made to detect the presence of bacilli in sputum smears. The smear images recorded under standard image acquisition protocol are subjected to hybrid Ant Colony Optimization (ACO)-morphological based segmentation procedure. This method is able to retain the shape of bacilli in TB images. The segmented images are validated with ground truth using overlap, distance and probability-based measures. Significant shape-based features such as area, perimeter, compactness, shape factor and tortuosity are extracted from the segmented images. It is observed that this method preserves more edges, detects the presence of bacilli and facilitates direct segmentation with reduced number of redundant searches to generate edges. Thus this hybrid segmentation technique aid in the diagnostic relevance of TB images in identifying the objects present in them.