Diagnosis of microbial keratitis using smartphone-captured images; a deep-learning model
Mohammad Soleimani, Albert Y. Cheung, Amir Rahdar, Artak Kirakosyan, Nicholas Tomaras, Isaiah Lee, Margarita De Alba, Mehdi Aminizade, Kosar Esmaili, Natalia Quiroz-Casian, Mohamad Javad Ahmadi, Siamak Yousefi, Kasra Cheraqpour
Abstract
BACKGROUND: Microbial keratitis (MK) poses a substantial threat to vision and is the leading cause of corneal blindness. The outcome of MK is heavily reliant on immediate treatment following an accurate diagnosis. The current diagnostics are often hindered by the difficulties faced in low and middle-income countries where there may be a lack of access to ophthalmic units with clinical experts and standardized investigating equipment. Hence, it is crucial to develop new and expeditious diagnostic approaches. This study explores the application of deep learning (DL) in diagnosing and differentiating subtypes of MK using smartphone-captured images. MATERIALS AND METHODS: The dataset comprised 889 cases of bacterial keratitis (BK), fungal keratitis (FK), and acanthamoeba keratitis (AK) collected from 2020 to 2023. A convolutional neural network-based model was developed and trained for classification. RESULTS: The study demonstrates the model's overall classification accuracy of 83.8%, with specific accuracies for AK, BK, and FK at 81.2%, 82.3%, and 86.6%, respectively, with an AUC of 0.92 for the ROC curves. CONCLUSION: The model exhibits practicality, especially with the ease of image acquisition using smartphones, making it applicable in diverse settings.