Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept

Abstract

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.

Keywords: Automation; Bacteriology; Diagnostic; Expert; Growth; Imaging.

Fig. 1

Global agreement between human readers to report growth semi-quantification. The global agreement to report semi-quantification was calculated with a tolerance of 0 (strict quantification), 1 log or 2 log difference as compared to the “final truth”. Solid line: estimated value, dashed lines: 95% CI.

Fig. E.1

Images of false positives (FP) on COL agar. Each image contains at the bottom left a bar graph representing the classification probabilities generated by the algorithms to classify the growth into 5 buckets: (1) <10² (no growth), (2) 10²–10³, (3) 10³–10⁴, (4)10⁴–10⁵ and (5) ≥10⁵. The algorithms selected the bucket with the highest probability to report growth semi-quantification.

Fig. F.1

Images of false positives (FP) on MAC agar. Each image contains at the bottom left a bar graph representing the classification probabilities generated by the algorithms to classify the growth into 5 buckets: (1) <10² (no growth), (2) 10²–10³, (3) 10³–10⁴, (4) 10⁴–10⁵ and (5) ≥10⁵. The algorithms selected the bucket with the highest probability to report growth semi-quantification.

Fig. G.1

Images of false negatives (FN) on CHROM agar. Each image contains at the bottom left a bar graph representing the classification probabilities generated by the algorithms to classify the growth into 5 buckets: (1) <10² (no growth), (2) 10²–10³, (3) 10³–10⁴, (4) 10⁴–10⁵ and (5) ≥10⁵. The algorithms selected the bucket with the highest probability to report growth semi-quantification.

Fig. H.1

Images of false negatives (FN) on COL agar. Each image contains at the bottom left a bar graph representing the classification probabilities generated by the algorithms to classify the growth into 5 buckets: (1) <10² (no growth), (2) 10²–10³, (3) 10³–10⁴, (4) 10⁴–10⁵ and (5) ≥10⁵. The algorithms selected the bucket with the highest probability to report growth semi-quantification.

Fig. I.1

. Images of false negatives (FN) on MAC agar. Each image contains at the bottom left a bar graph representing the classification probabilities generated by the algorithms to classify the growth into 5 buckets: (1) <10² (no growth), (2) 10²–10³, (3) 10³–10⁴, (4) 10⁴–10⁵ and (5) ≥10⁵. The algorithms selected the bucket with the highest probability to report growth semi-quantification.

Fig. J.1

Classification of microbial species and groups that can be definitely or presumptively identified on CHROM agar according to the product information of the BD CHROMagar™ Orientation medium. Esc col: Escherichia coli, Sta sap: Staphylococcus saprophyticus, Stc aga: Streptococcus agalactiae, Sta aur: Staphylococcus aureus, KPN: Klebsiella pneumonia, CKO: Citrobacter koseri, CFR: Citrobacter freundii, ECL: Enterobacter cloacae group, EAE: Enterobacter aerogenes, SMA: Serratia marcescens, MMO: Morganella morganii, PMI: Proteus mirabilis, PVU: Proteus vulgaris.