Highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistance
Current state-of-the-art infection and antimicrobial resistance (AMR) diagnostics are based on culture-based methods with a detection time of 48–96 h. Therefore, it is essential to develop novel methods that can do real-time diagnoses. Here, we demonstrate that the complimentary use of label-free op...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1154620/full |
| _version_ | 1797848203756830720 |
|---|---|
| author | Azeem Ahmad Ramith Hettiarachchi Ramith Hettiarachchi Abdolrahman Khezri Balpreet Singh Ahluwalia Balpreet Singh Ahluwalia Dushan N. Wadduwage Rafi Ahmad Rafi Ahmad |
| author_facet | Azeem Ahmad Ramith Hettiarachchi Ramith Hettiarachchi Abdolrahman Khezri Balpreet Singh Ahluwalia Balpreet Singh Ahluwalia Dushan N. Wadduwage Rafi Ahmad Rafi Ahmad |
| author_sort | Azeem Ahmad |
| collection | DOAJ |
| description | Current state-of-the-art infection and antimicrobial resistance (AMR) diagnostics are based on culture-based methods with a detection time of 48–96 h. Therefore, it is essential to develop novel methods that can do real-time diagnoses. Here, we demonstrate that the complimentary use of label-free optical assay with whole-genome sequencing (WGS) can enable rapid diagnosis of infection and AMR. Our assay is based on microscopy methods exploiting label-free, highly sensitive quantitative phase microscopy (QPM) followed by deep convolutional neural networks-based classification. The workflow was benchmarked on 21 clinical isolates from four WHO priority pathogens that were antibiotic susceptibility tested, and their AMR profile was determined by WGS. The proposed optical assay was in good agreement with the WGS characterization. Accurate classification based on the gram staining (100% recall for gram-negative and 83.4% for gram-positive), species (98.6%), and resistant/susceptible type (96.4%), as well as at the individual strain level (100% sensitivity in predicting 19 out of the 21 strains, with an overall accuracy of 95.45%). The results from this initial proof-of-concept study demonstrate the potential of the QPM assay as a rapid and first-stage tool for species, strain-level classification, and the presence or absence of AMR, which WGS can follow up for confirmation. Overall, a combined workflow with QPM and WGS complemented with deep learning data analyses could, in the future, be transformative for detecting and identifying pathogens and characterization of the AMR profile and antibiotic susceptibility. |
| first_indexed | 2024-04-09T18:23:39Z |
| format | Article |
| id | doaj.art-ce5d7172f1a94e5b8a5dfb1680f006b2 |
| institution | Directory Open Access Journal |
| issn | 1664-302X |
| language | English |
| last_indexed | 2024-04-09T18:23:39Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj.art-ce5d7172f1a94e5b8a5dfb1680f006b22023-04-12T05:31:05ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2023-04-011410.3389/fmicb.2023.11546201154620Highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistanceAzeem Ahmad0Ramith Hettiarachchi1Ramith Hettiarachchi2Abdolrahman Khezri3Balpreet Singh Ahluwalia4Balpreet Singh Ahluwalia5Dushan N. Wadduwage6Rafi Ahmad7Rafi Ahmad8Department of Physics and Technology, UiT The Arctic University of Norway, Tromsø, NorwayDepartment of Electronic and Telecommunication Engineering, University of Moratuwa, Moratuwa, Sri LankaCenter for Advanced Imaging, Faculty of Arts and Sciences, Harvard University, Cambridge, MA, United StatesDepartment of Biotechnology, Inland Norway University of Applied Sciences, Hamar, NorwayDepartment of Physics and Technology, UiT The Arctic University of Norway, Tromsø, NorwayDepartment of Clinical Science, Intervention and Technology, Karolinska Insitute, Stockholm, SwedenCenter for Advanced Imaging, Faculty of Arts and Sciences, Harvard University, Cambridge, MA, United StatesDepartment of Biotechnology, Inland Norway University of Applied Sciences, Hamar, NorwayInstitute of Clinical Medicine, Faculty of Health Sciences, UiT—The Arctic University of Norway, Tromsø, NorwayCurrent state-of-the-art infection and antimicrobial resistance (AMR) diagnostics are based on culture-based methods with a detection time of 48–96 h. Therefore, it is essential to develop novel methods that can do real-time diagnoses. Here, we demonstrate that the complimentary use of label-free optical assay with whole-genome sequencing (WGS) can enable rapid diagnosis of infection and AMR. Our assay is based on microscopy methods exploiting label-free, highly sensitive quantitative phase microscopy (QPM) followed by deep convolutional neural networks-based classification. The workflow was benchmarked on 21 clinical isolates from four WHO priority pathogens that were antibiotic susceptibility tested, and their AMR profile was determined by WGS. The proposed optical assay was in good agreement with the WGS characterization. Accurate classification based on the gram staining (100% recall for gram-negative and 83.4% for gram-positive), species (98.6%), and resistant/susceptible type (96.4%), as well as at the individual strain level (100% sensitivity in predicting 19 out of the 21 strains, with an overall accuracy of 95.45%). The results from this initial proof-of-concept study demonstrate the potential of the QPM assay as a rapid and first-stage tool for species, strain-level classification, and the presence or absence of AMR, which WGS can follow up for confirmation. Overall, a combined workflow with QPM and WGS complemented with deep learning data analyses could, in the future, be transformative for detecting and identifying pathogens and characterization of the AMR profile and antibiotic susceptibility.https://www.frontiersin.org/articles/10.3389/fmicb.2023.1154620/fullquantitative phase microscopywhole genome sequencingmachine learningantibiotic resistancedeep learningrapid diagnosis |
| spellingShingle | Azeem Ahmad Ramith Hettiarachchi Ramith Hettiarachchi Abdolrahman Khezri Balpreet Singh Ahluwalia Balpreet Singh Ahluwalia Dushan N. Wadduwage Rafi Ahmad Rafi Ahmad Highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistance Frontiers in Microbiology quantitative phase microscopy whole genome sequencing machine learning antibiotic resistance deep learning rapid diagnosis |
| title | Highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistance |
| title_full | Highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistance |
| title_fullStr | Highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistance |
| title_full_unstemmed | Highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistance |
| title_short | Highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistance |
| title_sort | highly sensitive quantitative phase microscopy and deep learning aided with whole genome sequencing for rapid detection of infection and antimicrobial resistance |
| topic | quantitative phase microscopy whole genome sequencing machine learning antibiotic resistance deep learning rapid diagnosis |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1154620/full |
| work_keys_str_mv | AT azeemahmad highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance AT ramithhettiarachchi highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance AT ramithhettiarachchi highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance AT abdolrahmankhezri highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance AT balpreetsinghahluwalia highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance AT balpreetsinghahluwalia highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance AT dushannwadduwage highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance AT rafiahmad highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance AT rafiahmad highlysensitivequantitativephasemicroscopyanddeeplearningaidedwithwholegenomesequencingforrapiddetectionofinfectionandantimicrobialresistance |