Morphological Characterization of Mycobacterium tuberculosis in a MODS Culture for an Automatic Diagnostics through Pattern Recognition

Tuberculosis control efforts are hampered by a mismatch in diagnostic technology: modern optimal diagnostic tests are least available in poor areas where they are needed most. Lack of adequate early diagnostics and MDR detection is a critical problem in control efforts. The Microscopic Observation Drug Susceptibility (MODS) assay uses visual recognition of cording patterns from Mycobacterium tuberculosis (MTB) to diagnose tuberculosis infection and drug susceptibility directly from a sputum sample in 7–10 days with a low cost. An important limitation that laboratories in the developing world face in MODS implementation is the presence of permanent technical staff with expertise in reading MODS. We developed a pattern recognition algorithm to automatically interpret MODS results from digital images. The algorithm using image processing, feature extraction and pattern recognition determined geometrical and illumination features used in an object-model and a photo-model to classify TB-positive images. 765 MODS digital photos were processed. The single-object model identified MTB (96.9 % sensitivity and 96.3 % specificity) and was able to discriminate non-tuberculous mycobacteria with a high specificity (97.1 % M. avium, 99.1 % M. chelonae, and 93.8 % M. kansasii). The photo model identified TB-positive sample