Related Experiment Video
Updated: Jul 8, 2025
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
From the diagnosis of infectious keratitis to discriminating fungal subtypes; a deep learning-based study
Mohammad Soleimani1,2, Kosar Esmaili1, Amir Rahdar3
1Eye Research Center, Farabi Eye Hospital, Tehran University of Medical Sciences, Tehran, Iran.
Abstract:
Infectious keratitis (IK) is a major cause of corneal opacity. IK can be caused by a variety of microorganisms. Typically, fungal ulcers carry the worst prognosis. Fungal cases can be subdivided into filamentous and yeasts, which shows fundamental differences. Delays in diagnosis or initiation of treatment increase the risk of ocular complications. Currently, the diagnosis of IK is mainly based on slit-lamp examination and corneal scrapings. Notably, these diagnostic methods have their drawbacks, including experience-dependency, tissue damage, and time consumption. Artificial intelligence (AI) is designed to mimic and enhance human decision-making. An increasing number of studies have utilized AI in the diagnosis of IK. In this paper, we propose to use AI to diagnose IK (model 1), differentiate between bacterial keratitis and fungal keratitis (model 2), and discriminate the filamentous type from the yeast type of fungal cases (model 3). Overall, 9329 slit-lamp photographs gathered from 977 patients were enrolled in the study. The models exhibited remarkable accuracy, with model 1 achieving 99.3%, model 2 at 84%, and model 3 reaching 77.5%. In conclusion, our study offers valuable support in the early identification of potential fungal and bacterial keratitis cases and helps enable timely management.
Insights
Artificial intelligence (AI) aids in diagnosing infectious keratitis (IK), a leading cause of corneal opacity. AI models accurately identified IK, differentiated fungal from bacterial causes, and distinguished fungal types, improving early detection and management.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Infectious keratitis (IK) is a significant cause of corneal opacity, often leading to severe visual impairment.
- Fungal keratitis, particularly filamentous types, presents a worse prognosis compared to bacterial keratitis.
- Current diagnostic methods for IK, such as slit-lamp examination and corneal scrapings, are invasive, time-consuming, and experience-dependent.
Purpose of the Study:
- To develop and evaluate artificial intelligence (AI) models for the diagnosis of infectious keratitis (IK).
- To differentiate between bacterial and fungal keratitis using AI.
- To distinguish between filamentous and yeast types of fungal keratitis with AI.
Main Methods:
- A dataset of 9329 slit-lamp photographs from 977 patients with IK was utilized.
- Three AI models were developed: Model 1 for general IK diagnosis, Model 2 for bacterial vs. fungal differentiation, and Model 3 for fungal subtype classification.
- Model performance was evaluated based on accuracy metrics.
Main Results:
- Model 1 achieved a high accuracy of 99.3% in diagnosing infectious keratitis.
- Model 2 demonstrated 84% accuracy in differentiating between bacterial and fungal keratitis.
- Model 3 successfully discriminated between filamentous and yeast fungal keratitis with 77.5% accuracy.
Conclusions:
- AI models show significant potential for accurate and efficient diagnosis of infectious keratitis.
- AI can assist in distinguishing between bacterial and fungal etiologies, and further classify fungal subtypes.
- The proposed AI approach supports early identification and timely management of keratitis, potentially improving patient outcomes.
