Subscribe to our Newsletter!

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

Copan’s Artificial Intelligence on Nature Communications

Digital Microbiology at its finest!

Last month, the paper “Hierarchical AI Enables Global Interpretation of Culture Plates in the Era of Digital Microbiology” was published in Nature Communications Journal. This study introduced DeepColony, a groundbreaking algorithm at the core of what today we call Copan’s PhenoMATRIX™.

The study design 

Alberto Signoroni and Colleagues designed DeepColony to take advantage of deep learning to address the complex bacterial culture plate interpretation task. They tackled the task with a multi-faceted architecture in four stages: in the initial stages (levels 0 to 2), a deep learning-based colony counting method was employed for quantifying bacterial growth single colony recognition. Subsequently, a refinement step (level 3) was introduced, considering the global plate context to enhance identification consistency, especially in mixed cultures. DeepColony’s key strength was its ability to integrate the structured information from levels 0-3 into a rule-based decision system (level 4): this system informs clinical culture interpretations, offering a detailed understanding of the observed morphologies of grown organisms and facilitating species-level identification and quantitation across a diverse range of clinically relevant pathogens. “Thanks to this multi-step approach, we have developed an AI able to follow the microbiologist’s reasoning process, which is, due to the intrinsic nature of microbiology, often very subjective and very hard to describe,” says Stefano Oliani, Imaging Analysis Manager of Copan WASP.

The outcome 

To evaluate DeepColony’s performance, the researchers used a large labeled clinical dataset comprising more than five thousand urine culture samples to demonstrate a high overall agreement between DeepColony and human interpretations, with a surprisingly accurate agreement for negative cultures. According to Stefano Lombardi, Copan WASP Software Development Expert and co-author of the article, “There is no equivalent precedent in literature: until now, studies resembling this one could only achieve identification of bacterial colonies within a significantly limited range of species. By incorporating adapted guidelines from Microbiology Laboratories, we have achieved a plate-level interpretation with a notable agreement between AI and human evaluation.

Copan Group
Copan Wasp imaging and machine learning team! Stefano Lombardi and Stefano Oliani are respectively the first and the third from the left.

Future perspectives

In conclusion, DeepColony (and thus PhenoMATRIX™) represents a significant advancement in clinical microbiology by automating the interpretation of bacterial culture plates and enhancing the efficiency and quality of microbiological laboratory workflows. Its integration of decision support at multiple levels holds excellent promise for refining and reinforcing the critical role of microbiologists in clinical decision-making processes. “In the rapidly evolving landscape of Microbiology Laboratories automation, this will streamline a great number of processes, enhancing the capability to describe and monitor the occurrence and progression of pathological conditions from individual patients to the community,” says Stefano Lombardi.

Read the full paper now!

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

Microbiology Time – November 2023

Microbiology Time

October was a fruitful month! Read here the best three papers we selected:

  • The first study conducted in the US compared the performance of Colibrí™ with standard manual spotting for identifying bacteria in colonies grown from over 400 different samples, including urine, wound, respiratory, and positive blood cultures. The results showed that the two methods agreed 99.54% of the time, indicating that the use of Colibrí™ can help save time for technologists and ensure complete traceability from plating to organism identification.
  • The vaginal microbiome plays a crucial role in maintaining reproductive and overall women’s health. In this paper, Sara Leeber and her colleagues analyzed the self-collected vaginal microbiome of 3,345 Belgian women performing 16S amplicon sequencing and conducting questionnaires. The researchers found that the microbiome composition was strongly associated with age, childbirth, and menstrual cycle, and Lactobacillus species were dominant in 78% of the vaginal samples. Moreover, a network correlation analysis revealed specific bacterial taxa that were linked to certain conditions such as estrogen levels, contraceptive use, menopause, and breastfeeding. This study provides a detailed map of the vaginal microbiome associated with various health, lifestyle, and dietary factors, which will help with follow-up clinical and mechanistic research.
  • In the last years, full laboratory automation has transformed the field of clinical microbiology; today, deep learning architectures are fundamentally changing how computers can assist with challenging visual interpretation tasks in various domains. Here, the paper by Signoroni and colleagues introduces a system able to tackle a core task in clinical microbiology, the interpretation of diagnostic bacterial culture plates, including presumptive pathogen identification. The researchers achieved this by decomposing the problem into a hierarchy of complex subtasks and addressing them with a multi-network architecture called DeepColony. By working with a large stream of clinical data and a complete set of 32 pathogens, the suggested system effectively aided plate interpretation with a surprising level of accuracy in the extensive and rigorous framework of urinary tract infections. In conclusion, thanks to the rich species-related information generated, DeepColony can be used to develop trustworthy clinical decision support services in laboratory automation ecosystems. Surprise: Deepcolony is at the base of what PhenoMATRIX currently is!

Read the full studies:

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

Microbiology Time – October 2023

Microbiology Time

Here are the three papers we selected as the best ones in the last month:

  • Getting infected by Tuberculosis is a concrete risk for healthcare professionals working with TB patients, collecting and handling sputum samples for TB diagnosis. This study evaluates the risk perceptions of an alternative, less dangerous method to diagnose TB, tongue swabbing, implemented during the COVID-19 pandemic. Eighteen South African Healthcare professionals with experience using tongue swabbing at the South African Tuberculosis Vaccine Initiative were interviewed and assessed by their attitude toward provider-collected and supervised self-collected tongue swabbing. Facilitators and barriers to the use of tongue swabbing were also evaluated. Perception, barriers, and motivators of the use of tongue swabbing varied by use case, highlighting specific educational resources to enhance the safety of and adherence to the self-collection method.
  • HPV -DNA testing with self-collected samples showed extreme diagnostic accuracy and reliability. Nevertheless, to implement self-sampling in cervical screening programs, the standardization of the pre-analytical phase and the understanding of the acceptability of women are necessary in every country. In this second study, Illari Sechi and colleagues assessed the stability of self-collected vaginal samples, and the acceptability of self-collection in almost 200 women. Most of the women found it easy to use self-collection devices, and approximately half of the enrolled women declared preferring self-sampling to clinician-collected methods. This, paired with the high reliability and accuracy of HPV-DNA tests on self-collected samples, supports the adoption of self-collection in screening programs, even though HPV tests on self-samples must be standardized and optimized, and educational campaigns are needed to adequately inform and increase responsiveness in a target population.
  • Covid-19 is mainly a respiratory syndrome that can affect multiple organ systems with various symptoms. Deficits in smell and taste are some of the most common COVID-19 symptoms, which may last for months after the infection and which mechanisms are not fully elucidated. To identify the determinants of olfactory symptom persistence, the Italian research group obtained olfactory mucosa from 21 subjects and grouped them by the severity/persistence of olfactory symptoms. By analyzing cells with transcriptome analyses, Lupi and colleagues discovered that the overall gene expression and micro-RNA expression profile are altered for a long time after infection. Patients with persistent olfactory deficits displayed increased expression levels of genes related to inflammation and zinc homeostasis, suggesting an association of this metal with the olfactory deficit.

Read the full studies:

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.
Subscribe to our Newsletter!

I'm looking for...

Close Search

We love to talk
to people

Write us to satisfy your curiosity, get information or start a great collaboration!

Contact us for more info

Are you looking
for something?

Use our search tool and be surprised by how easy it is to get right to the point.

Search

Contact

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.

Newsletter

Thank you!Your submission
has been received!
Oops! Something went wrong while submitting the form.