Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition

Alicia Alva, Fredy Aquino, Robert H. Gilman, Carlos Olivares, David Requena, Andrés H. Gutiérrez, Luz Caviedes, Jorge Coronel, Sandra Larson, Patricia Sheen, David A.J. Moore, Mirko Zimic

Research output: Contribution to journalArticlepeer-review

Abstract

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 objectmodel 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 samples with 99.1% sensitivity and 99.7% specificity. This algorithm is a valuable tool that will enable automatic remote diagnosis using Internet or cellphone telephony. The use of this algorithm and its further implementation in a telediagnostics platform will contribute to both faster TB detection and MDR TB determination leading to an earlier initiation of appropriate treatment.

Original languageEnglish (US)
Article numbere82809
JournalPloS one
Volume8
Issue number12
DOIs
StatePublished - Dec 16 2013

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • General

Fingerprint Dive into the research topics of 'Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition'. Together they form a unique fingerprint.

Cite this