Microscope-Based AI Identifies Bacteria Accurately
By LabMedica International staff writers Posted on 26 Dec 2017 |
Image: The MetaFer Slide Scanning and Imaging platform with a Zeiss microscope (Photo courtesy of MetaSystems Group).
Microscopes enhanced with artificial intelligence (AI) could help clinical microbiologists diagnose potentially deadly blood infections and improve patients' odds of survival.
Scientists have demonstrated that an automated AI-enhanced microscope system is "highly adept" at identifying images of bacteria quickly and accurately. The automated system could help alleviate the current lack of highly trained microbiologists, expected to worsen as 20% of technologists reach retirement age in the next five years.
Scientists working with the Department of Pathology, Beth Israel Deaconess Medical Center, (Boston, MA, USA) used an automated microscope designed to collect high-resolution image data from microscopic slides. In this case, blood samples taken from patients with suspected bloodstream infections were incubated to increase bacterial numbers. Then, slides were prepared by placing a drop of blood on a glass slide and stained with dye to make the bacterial cell structures more visible.
The investigators then trained a convolutional neural network (CNN), a class of artificial intelligence modeled on the mammalian visual cortex and used to analyze visual data, to categorize bacteria based on their shape and distribution. These characteristics were selected to represent bacteria that most often cause bloodstream infections; the rod-shaped bacteria including Escherichia coli; the round clusters of Staphylococcus species; and the pairs or chains of Streptococcus species. All slides were imaged without coverslips using a MetaFer Slide Scanning and Imaging platform with a 140-slide capacity automated slide loader equipped with a 40× magnification Plan-Neofluar objective.
To train it, the scientists fed their unschooled neural network more than 25,000 images from blood samples prepared during routine clinical workups. By cropping these images, in which the bacteria had already been identified by human clinical microbiologists, the scientists generated more than 100,000 training images. The machine intelligence learned how to sort the images into the three categories of bacteria (rod-shaped, round clusters, and round chains or pairs), ultimately achieving nearly 95% accuracy.
The team challenged the algorithm to sort new images from 189 slides without human intervention. Overall, the algorithm achieved more than 93% accuracy in all three categories. Sensitivity/specificity was 98.4/75.0% for Gram-positive cocci in chains/pairs; 93.2/97.2% for Gram-positive cocci in clusters; and 96.3/98.1% for Gram-negative rods. The study was published on November 29, 2017, in the Journal of Clinical Microbiology.
Related Links:
Beth Israel Deaconess Medical Center
Scientists have demonstrated that an automated AI-enhanced microscope system is "highly adept" at identifying images of bacteria quickly and accurately. The automated system could help alleviate the current lack of highly trained microbiologists, expected to worsen as 20% of technologists reach retirement age in the next five years.
Scientists working with the Department of Pathology, Beth Israel Deaconess Medical Center, (Boston, MA, USA) used an automated microscope designed to collect high-resolution image data from microscopic slides. In this case, blood samples taken from patients with suspected bloodstream infections were incubated to increase bacterial numbers. Then, slides were prepared by placing a drop of blood on a glass slide and stained with dye to make the bacterial cell structures more visible.
The investigators then trained a convolutional neural network (CNN), a class of artificial intelligence modeled on the mammalian visual cortex and used to analyze visual data, to categorize bacteria based on their shape and distribution. These characteristics were selected to represent bacteria that most often cause bloodstream infections; the rod-shaped bacteria including Escherichia coli; the round clusters of Staphylococcus species; and the pairs or chains of Streptococcus species. All slides were imaged without coverslips using a MetaFer Slide Scanning and Imaging platform with a 140-slide capacity automated slide loader equipped with a 40× magnification Plan-Neofluar objective.
To train it, the scientists fed their unschooled neural network more than 25,000 images from blood samples prepared during routine clinical workups. By cropping these images, in which the bacteria had already been identified by human clinical microbiologists, the scientists generated more than 100,000 training images. The machine intelligence learned how to sort the images into the three categories of bacteria (rod-shaped, round clusters, and round chains or pairs), ultimately achieving nearly 95% accuracy.
The team challenged the algorithm to sort new images from 189 slides without human intervention. Overall, the algorithm achieved more than 93% accuracy in all three categories. Sensitivity/specificity was 98.4/75.0% for Gram-positive cocci in chains/pairs; 93.2/97.2% for Gram-positive cocci in clusters; and 96.3/98.1% for Gram-negative rods. The study was published on November 29, 2017, in the Journal of Clinical Microbiology.
Related Links:
Beth Israel Deaconess Medical Center
Latest Microbiology News
- Enhanced Rapid Syndromic Molecular Diagnostic Solution Detects Broad Range of Infectious Diseases
- Clinical Decision Support Software a Game-Changer in Antimicrobial Resistance Battle
- New CE-Marked Hepatitis Assays to Help Diagnose Infections Earlier
- 1 Hour, Direct-From-Blood Multiplex PCR Test Identifies 95% of Sepsis-Causing Pathogens
- Mouth Bacteria Test Could Predict Colon Cancer Progression
- Unique Metabolic Signature Could Enable Sepsis Diagnosis within One Hour of Blood Collection
- Groundbreaking Diagnostic Platform Provides AST Results With Unprecedented Speed
- Simple Blood Test Combined With Personalized Risk Model Improves Sepsis Diagnosis
- Blood Analysis Predicts Sepsis and Organ Failure in Children
- TB Blood Test Could Detect Millions of Silent Spreaders
- New Blood Test Cuts Diagnosis Time for Nontuberculous Mycobacteria Infections from Months to Hours
- New Tuberculosis Test to Expand Testing Access in Low- and Middle-Income Countries
- Rapid Test Diagnoses Tropical Disease within Hours for Faster Antibiotics Treatment
- Rapid Molecular Testing Enables Faster, More Targeted Antibiotic Treatment for Pneumonia
- Rapid AST Platform Provides Targeted Therapeutic Results Days Faster Than Current Standard of Care
- New Analysis Method Detects Pathogens in Blood Faster and More Accurately by Melting DNA