Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept
Background: Automation in microbiology laboratories impacts management, workflow, productivity and quality. Further improvements will be driven by the development of intelligent image analysis allowing automated detection of microbial growth, release of sterile samples, identification and quantifica...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2017-12-01
|
Series: | Biomedical Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2319417017302834 |
_version_ | 1811186890694459392 |
---|---|
author | Antony Croxatto Raphaël Marcelpoil Cédrick Orny Didier Morel Guy Prod'hom Gilbert Greub |
author_facet | Antony Croxatto Raphaël Marcelpoil Cédrick Orny Didier Morel Guy Prod'hom Gilbert Greub |
author_sort | Antony Croxatto |
collection | DOAJ |
description | Background: Automation in microbiology laboratories impacts management, workflow, productivity and quality. Further improvements will be driven by the development of intelligent image analysis allowing automated detection of microbial growth, release of sterile samples, identification and quantification of bacterial colonies and reading of AST disk diffusion assays. We investigated the potential benefit of intelligent imaging analysis by developing algorithms allowing automated detection, semi-quantification and identification of bacterial colonies.
Methods: Defined monomicrobial and clinical urine samples were inoculated by the BD Kiestra™ InoqulA™ BT module. Image acquisition of plates was performed with the BD Kiestra™ ImagA BT digital imaging module using the BD Kiestra™ Optis™ imaging software. The algorithms were developed and trained using defined data sets and their performance evaluated on both defined and clinical samples.
Results: The detection algorithms exhibited 97.1% sensitivity and 93.6% specificity for microbial growth detection. Moreover, quantification accuracy of 80.2% and of 98.6% when accepting a 1 log tolerance was obtained with both defined monomicrobial and clinical urine samples, despite the presence of multiple species in the clinical samples. Automated identification accuracy of microbial colonies growing on chromogenic agar from defined isolates or clinical urine samples ranged from 98.3% to 99.7%, depending on the bacterial species tested.
Conclusion: The development of intelligent algorithm represents a major innovation that has the potential to significantly increase laboratory quality and productivity while reducing turn-around-times. Further development and validation with larger numbers of defined and clinical samples should be performed before transferring intelligent imaging analysis into diagnostic laboratories. |
first_indexed | 2024-04-11T13:52:56Z |
format | Article |
id | doaj.art-8e846b9a48d74ac895923dc36e3f6490 |
institution | Directory Open Access Journal |
issn | 2319-4170 |
language | English |
last_indexed | 2024-04-11T13:52:56Z |
publishDate | 2017-12-01 |
publisher | Elsevier |
record_format | Article |
series | Biomedical Journal |
spelling | doaj.art-8e846b9a48d74ac895923dc36e3f64902022-12-22T04:20:29ZengElsevierBiomedical Journal2319-41702017-12-0140631732810.1016/j.bj.2017.09.001Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of conceptAntony Croxatto0Raphaël Marcelpoil1Cédrick Orny2Didier Morel3Guy Prod'hom4Gilbert Greub5Institute of Microbiology, University Hospital of Lausanne, Institute of Microbiology, Lausanne, SwitzerlandBecton Dickinson Kiestra, Le Pont-de-Claix, FranceBecton Dickinson Kiestra, Le Pont-de-Claix, FranceBecton Dickinson Corporate Clinical Development, Office of Science, Medicine and Technology, Le Pont-de-Claix, FranceInstitute of Microbiology, University Hospital of Lausanne, Institute of Microbiology, Lausanne, SwitzerlandInstitute of Microbiology, University Hospital of Lausanne, Institute of Microbiology, Lausanne, SwitzerlandBackground: Automation in microbiology laboratories impacts management, workflow, productivity and quality. Further improvements will be driven by the development of intelligent image analysis allowing automated detection of microbial growth, release of sterile samples, identification and quantification of bacterial colonies and reading of AST disk diffusion assays. We investigated the potential benefit of intelligent imaging analysis by developing algorithms allowing automated detection, semi-quantification and identification of bacterial colonies. Methods: Defined monomicrobial and clinical urine samples were inoculated by the BD Kiestra™ InoqulA™ BT module. Image acquisition of plates was performed with the BD Kiestra™ ImagA BT digital imaging module using the BD Kiestra™ Optis™ imaging software. The algorithms were developed and trained using defined data sets and their performance evaluated on both defined and clinical samples. Results: The detection algorithms exhibited 97.1% sensitivity and 93.6% specificity for microbial growth detection. Moreover, quantification accuracy of 80.2% and of 98.6% when accepting a 1 log tolerance was obtained with both defined monomicrobial and clinical urine samples, despite the presence of multiple species in the clinical samples. Automated identification accuracy of microbial colonies growing on chromogenic agar from defined isolates or clinical urine samples ranged from 98.3% to 99.7%, depending on the bacterial species tested. Conclusion: The development of intelligent algorithm represents a major innovation that has the potential to significantly increase laboratory quality and productivity while reducing turn-around-times. Further development and validation with larger numbers of defined and clinical samples should be performed before transferring intelligent imaging analysis into diagnostic laboratories.http://www.sciencedirect.com/science/article/pii/S2319417017302834AutomationDiagnosticBacteriologyImagingGrowthExpert |
spellingShingle | Antony Croxatto Raphaël Marcelpoil Cédrick Orny Didier Morel Guy Prod'hom Gilbert Greub Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept Biomedical Journal Automation Diagnostic Bacteriology Imaging Growth Expert |
title | Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept |
title_full | Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept |
title_fullStr | Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept |
title_full_unstemmed | Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept |
title_short | Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept |
title_sort | towards automated detection semi quantification and identification of microbial growth in clinical bacteriology a proof of concept |
topic | Automation Diagnostic Bacteriology Imaging Growth Expert |
url | http://www.sciencedirect.com/science/article/pii/S2319417017302834 |
work_keys_str_mv | AT antonycroxatto towardsautomateddetectionsemiquantificationandidentificationofmicrobialgrowthinclinicalbacteriologyaproofofconcept AT raphaelmarcelpoil towardsautomateddetectionsemiquantificationandidentificationofmicrobialgrowthinclinicalbacteriologyaproofofconcept AT cedrickorny towardsautomateddetectionsemiquantificationandidentificationofmicrobialgrowthinclinicalbacteriologyaproofofconcept AT didiermorel towardsautomateddetectionsemiquantificationandidentificationofmicrobialgrowthinclinicalbacteriologyaproofofconcept AT guyprodhom towardsautomateddetectionsemiquantificationandidentificationofmicrobialgrowthinclinicalbacteriologyaproofofconcept AT gilbertgreub towardsautomateddetectionsemiquantificationandidentificationofmicrobialgrowthinclinicalbacteriologyaproofofconcept |