Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
AI-Assisted Diagnosis and Subtype Differentiation of Microbial Keratitis: One Step Forward to Mitigate Health Disparities
Author Affiliations & Notes
  • Mohammad Soleimani
    Ophthalmology, University of Illinois Chicago College of Medicine, Chicago, Illinois, United States
  • Amir Rahdar
    Ophthalmology, University of Illinois Chicago College of Medicine, Chicago, Illinois, United States
  • Kosar Esmaili
    Tehran University of Medical Sciences, Tehran, Tehran, Iran (the Islamic Republic of)
  • Kasra Cheraqpour
    Tehran University of Medical Sciences, Tehran, Tehran, Iran (the Islamic Republic of)
  • Mahbod Baharnoori
    Ophthalmology, University of Illinois Chicago College of Medicine, Chicago, Illinois, United States
  • Allison Kufta
    Ophthalmology, University of Illinois Chicago College of Medicine, Chicago, Illinois, United States
  • Seyed Farzad Mohammadi
    Ophthalmology, University of Illinois Chicago College of Medicine, Chicago, Illinois, United States
  • Albert Cheung
    Virginia Eye Consultants, Virginia, United States
  • Siamak Yousefi
    University of Tennessee Health Science Center, Tennessee, United States
  • Ali R Djalilian
    Ophthalmology, University of Illinois Chicago College of Medicine, Chicago, Illinois, United States
    University of Illinois Chicago, Richard and Loan Hill Department of Biomedical Engineering, Chicago, Illinois, United States, Illinois, United States
  • Footnotes
    Commercial Relationships   Mohammad Soleimani None; Amir Rahdar None; Kosar Esmaili None; Kasra Cheraqpour None; Mahbod Baharnoori None; Allison Kufta None; Seyed Farzad Mohammadi None; Albert Cheung None; Siamak Yousefi NIH, Code F (Financial Support); Ali Djalilian DOD, Code F (Financial Support), NIH, Code F (Financial Support), Core department grant, Code F (Financial Support), Eversight, Code F (Financial Support)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 1503. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Mohammad Soleimani, Amir Rahdar, Kosar Esmaili, Kasra Cheraqpour, Mahbod Baharnoori, Allison Kufta, Seyed Farzad Mohammadi, Albert Cheung, Siamak Yousefi, Ali R Djalilian; AI-Assisted Diagnosis and Subtype Differentiation of Microbial Keratitis: One Step Forward to Mitigate Health Disparities. Invest. Ophthalmol. Vis. Sci. 2024;65(7):1503.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Out of various causes of corneal opacity, microbial keratitis (MK) stands out as the foremost reason for corneal blindness. The current diagnostic methods have their drawbacks, including experience-dependency, tissue damage, and time consumption. We performed a retrospective artificial intelligence (AI)-based slit-lamp data analysis to detect MK, differentiate among bacterial, fungal, and Acanthamoeba keratitis (AK), and distinguish between subtypes of fungal keratitis (FK).

Methods : The dataset includes 10,739 slit-lamp images, categorized into four primary classes: 2,505 images of healthy corneas, 2,008 of FK, 4,816 of bacterial keratitis, and 1,410 of AK, sourced from 1,428 subjects. Three AI-based models employing Convolutional Neural Networks (CNN) were developed for the following purposes: first, to diagnose MK from healthy corneas; second, to differentiate among bacterial, fungal, and Acanthamoeba infections; and third, to distinguish between filamentous and yeast subtypes of FK cases (Figures 1,2). We calculated accuracy, sensitivity, specificity, precision, F1 score, R2 score, as well as area under the receiver operating characteristic curve (AUC-ROC).

Results : Model 1 for diagnosing healthy corneas and MK achieved 99.01% and 99.23% of accuracy rate, respectively with a 0.99 AUC-ROC. Model 2 for differentiating bacterial, fungal, and Acanthamoeba infections reached accuracies of 91.91%, 79.77%, and 81.27% with AUC-ROCs of 0.88, 0.87, and 0.90, respectively. Model 3 for discriminating fungal subtypes attained an accuracy of 76.19% and 77.84% for diagnosing filamentous and yeast subtypes, respectively with an AUC-ROC of 0.78. Findings were validated using 5-fold cross-validation.

Conclusions : The developed AI-based models are promising in early and precise diagnosis of MK, enhancing the differentiation of bacterial, fungal, and Acanthamoeba keratitis, and identifying fungal subtypes. These models may significantly aid timely and appropriate treatment interventions, especially in resource-privileged populations, thus mitigate health disparities. It will also reduce costs related to complications arising from late diagnosis.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Architecture of the CNN-based models. (a) The structure for models 1 and 3. (b) The structure for model 2.

Architecture of the CNN-based models. (a) The structure for models 1 and 3. (b) The structure for model 2.

 

Sample input images related to each type of keratitis, along with their squared heatmap versions, extracted from the first layer of model 2.

Sample input images related to each type of keratitis, along with their squared heatmap versions, extracted from the first layer of model 2.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×