Automatic hemolysis identification on aligned dual-lighting images of cultured blood agar plates

Savardi, Mattia; Ferrari, Alessandro; Signoroni, Alberto

doi:10.1016/j.cmpb.2017.12.017

Cited by 29 publications

(19 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neither, areas of clearance were obtained by hemolysis in Blood agar, indicating that there was no Hemoglobin oxidation or lysis of red blood cells. These results corroborate the non-pathogenic nature of bacteria constituting bioinoculants (Figure 2) (Ahmad et al (2013);Zendejas-Manzo et al (2014); Savardi et al (2018)).…”

Section: Phosphate Solubilizing Bacteria Selection and Identificationsupporting

confidence: 85%

“…Hemolysis can manifest itself in three different ways: alpha (˛), when there is partial lysis of the red blood cell membrane, producing a green or brown discoloration at the culture media; beta (ˇ), associated with a complete lysis of the red blood cells in which a yellow or transparent halo is produced around the colony and gamma ( ), which indicates the absence of hemolysis (Savardi et al (2018)). The bacteria in this study did not show DNAse activity, which indicates their inability to produce enzymes to hydrolyze DNA.…”

Section: Phosphate Solubilizing Bacteria Selection and Identificationmentioning

confidence: 99%

See 1 more Smart Citation

Bioinoculant production composed by Pseudomonas sp., Serratia sp., and Kosakonia sp., preliminary effect on Allium cepa L., growth at plot scale

et al. 2021

View full text Add to dashboard Cite

Phosphorus (P) is an essential nutrient for plant’s development, and its deficiency restricts crop yield. To meet P requirements in agricultural settings, a low-cost culture medium (MT11B) was designed in which a bioinoculant was produced consisting of three bacterial isolates capable of solubilizing P from phosphoric rock (PR). Pseudomonas sp., Serratia sp., and Kosakonia sp. exhibited P solubilization in SMRS1 agar modified with PR (5.0 g L-1), as source of inorganic P. Sowings by isolation were made of the three bacteria on DNAse- and Blood-agar to rule out pathogenicity. At the interaction tests, no inhibition halos were observed; demonstrating there was no antagonism among them, thus they were used to constitute a consortium. Growth curve (12 h) in MT11B demonstrated consortium grew in presence of PR, brewer’s yeast hydrolysate, and glucose at concentrations (2.5 g L-1) fourfold lower than those in SMRS1 (10.0 g L-1); obtaining phosphate solubilizing bacteria of (10.60 ± 0.08/ log10 CFUmL-1 and, at 6 h of culture, acid and alkaline phosphatase enzyme volumetric activities of 2.3 ± 0.8 and (3.80 ± 0.13) UP, respectively. The consortium, releasing phosphorus at a rate of (45.80 ± 5.17) mg L-1 at 6 h of production, was evaluated as bioinoculant in onion plots for five months. Plants receiving a treatment that included 500 mL (10 x 107 CFU mL-1) of bioinoculant plus 100 kg ha-1 of an organic mineral fertilizer exhibited the highest determined response variables (170.1 ± 22.2) mm bulb height, (49.4 ± 6.5) mm bulb diameter, (9.0 ± 1.8) g bulb dry weight, and 15.21 mg bulb-1 total phosphorus (p < 0.05).

show abstract

Section: Phosphate Solubilizing Bacteria Selection and Identificationsupporting

confidence: 85%

Section: Phosphate Solubilizing Bacteria Selection and Identificationmentioning

confidence: 99%

Bioinoculant production composed by Pseudomonas sp., Serratia sp., and Kosakonia sp., preliminary effect on Allium cepa L., growth at plot scale

et al. 2021

View full text Add to dashboard Cite

show abstract

“…There is a growing interest in applying computer vision algorithms to microbiological analyses, especially in industry and pharmaceutical branches, but many existing approaches are based on traditional image processing techniques [32][33][34][35][36] . Although deep learning methods have recently become more commonly used 17,[37][38][39][40][41] , the proposed procedures are usually not end-to-end solutions and cannot be used independently to process an image of an entire Petri plate. The lack of effective DL-based approaches for microbiological purposes possibly results from the poor availability of huge datasets needed for deep neural network training.…”

Section: Discussionmentioning

confidence: 99%

AGAR a Microbial Colony Dataset for Deep Learning Detection

Majchrowska¹,

Pawłowski²,

Guła

et al. 2021

Preprint

View full text Add to dashboard Cite

The Annotated Germs for Automated Recognition (AGAR) dataset is an image database of microbial colonies cultured on agar plates. It contains 18 000 photos of five different microorganisms as single or mixed cultures, taken under diverse lighting conditions with two different cameras. All the images are classified into countable, uncountable, and empty, with the countable class labeled by microbiologists with colony location and species identification (336 442 colonies in total). This study describes the dataset itself and the process of its development. In the second part, the performance of selected deep neural network architectures for object detection, namely Faster R-CNN and Cascade R-CNN, was evaluated on the AGAR dataset. The results confirmed the great potential of deep learning methods to automate the process of microbe localization and classification based on Petri dish photos. Moreover, AGAR is the first publicly available dataset of this kind and size and will facilitate the future development of machine learning models. The data used in these studies can be found at https://agar.neurosys.com/.

show abstract

“…The choice of outcome is a critical point influencing the clinical relevance of an ML system. We identified ML systems with outcomes such as the classification of haemolysis on bacterial cultures [91] or the identification of Leuconostoc, Fructobacillus and Lactococcus [92]. While such systems can be technically worthwhile, they do not necessarily meet a clinical need.…”

Section: For Current and Future Datamentioning

confidence: 99%

Machine learning in the clinical microbiology laboratory: has the time come for routine practice?

Peiffer-Smadja

Dellière

Rodriguez

et al. 2020

Clinical Microbiology and Infection

View full text Add to dashboard Cite

Background: Machine learning (ML) allows the analysis of complex and large data sets and has the potential to improve health care. The clinical microbiology laboratory, at the interface of clinical practice and diagnostics, is of special interest for the development of ML systems. Aims: This narrative review aims to explore the current use of ML In clinical microbiology. Sources: References for this review were identified through searches of MEDLINE/PubMed, EMBASE, Google Scholar, biorXiv, arXiV, ACM Digital Library and IEEE Xplore Digital Library up to November 2019. Content: We found 97 ML systems aiming to assist clinical microbiologists. Overall, 82 ML systems (85%) targeted bacterial infections, 11 (11%) parasitic infections, nine (9%) viral infections and three (3%) fungal infections. Forty ML systems (41%) focused on microorganism detection, identification and quantification, 36 (37%) evaluated antimicrobial susceptibility, and 21 (22%) targeted the diagnosis, disease classification and prediction of clinical outcomes. The ML systems used very diverse data sources: 21 (22%) used genomic data of microorganisms, 19 (20%) microbiota data obtained by metagenomic sequencing, 19 (20%) analysed microscopic images, 17 (18%) spectroscopy data, eight (8%) targeted gene sequencing, six (6%) volatile organic compounds, four (4%) photographs of bacterial colonies, four (4%) transcriptome data, three (3%) protein structure, and three (3%) clinical data. Most systems used data from high-income countries (n ¼ 71, 73%) but a significant number used data from low-and middle-income countries (n ¼ 36, 37%). Performance measures were reported for the 97 ML systems, but no article described their use in clinical practice or reported impact on processes or clinical outcomes. Implications: In clinical microbiology, ML has been used with various data sources and diverse practical applications. The evaluation and implementation processes represent the main gap in existing ML systems, requiring a focus on their interpretability and potential integration into real-world settings.

show abstract

Automatic hemolysis identification on aligned dual-lighting images of cultured blood agar plates

Cited by 29 publications

References 39 publications

Bioinoculant production composed by Pseudomonas sp., Serratia sp., and Kosakonia sp., preliminary effect on Allium cepa L., growth at plot scale

Bioinoculant production composed by Pseudomonas sp., Serratia sp., and Kosakonia sp., preliminary effect on Allium cepa L., growth at plot scale

AGAR a Microbial Colony Dataset for Deep Learning Detection

Machine learning in the clinical microbiology laboratory: has the time come for routine practice?

Contact Info

Product

Resources

About