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 D...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2013-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0082809 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849331785820798976 |
|---|---|
| author | 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 |
| author_facet | 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 |
| author_sort | Alicia Alva |
| collection | DOAJ |
| description | 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 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. |
| format | Article |
| id | doaj-art-fd70cda18a684bcdb3d6d4da826b56a3 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2013-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-fd70cda18a684bcdb3d6d4da826b56a32025-08-20T03:46:24ZengPublic Library of Science (PLoS)PLoS ONE1932-62032013-01-01812e8280910.1371/journal.pone.0082809Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition.Alicia AlvaFredy AquinoRobert H GilmanCarlos OlivaresDavid RequenaAndrés H GutiérrezLuz CaviedesJorge CoronelSandra LarsonPatricia SheenDavid A J MooreMirko ZimicTuberculosis 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 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.https://doi.org/10.1371/journal.pone.0082809 |
| spellingShingle | 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 Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition. PLoS ONE |
| title | Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition. |
| title_full | Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition. |
| title_fullStr | Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition. |
| title_full_unstemmed | Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition. |
| title_short | Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition. |
| title_sort | morphological characterization of mycobacterium tuberculosis in a mods culture for an automatic diagnostics through pattern recognition |
| url | https://doi.org/10.1371/journal.pone.0082809 |
| work_keys_str_mv | AT aliciaalva morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT fredyaquino morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT roberthgilman morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT carlosolivares morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT davidrequena morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT andreshgutierrez morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT luzcaviedes morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT jorgecoronel morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT sandralarson morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT patriciasheen morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT davidajmoore morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition AT mirkozimic morphologicalcharacterizationofmycobacteriumtuberculosisinamodscultureforanautomaticdiagnosticsthroughpatternrecognition |