Classification of Keratitis from Eye Corneal Photographs using Deep Learning

TL;DR

This paper explores deep learning models to improve the diagnosis of keratitis infection types from eye corneal photographs, aiming to assist in low-resource settings where laboratory diagnostics are limited.

Contribution

It compares multiple deep learning approaches, introducing a novel multitask model with a multi-head classification layer that outperforms other models on a Brazilian dataset.

Findings

Multitask V2 achieved highest AUROC scores for infection prediction.

Sex significantly influences amoeba infection prediction.

Age impacts predictions for fungi and bacteria.

Abstract

Keratitis is an inflammatory corneal condition responsible for 10% of visual impairment in low- and middle-income countries (LMICs), with bacteria, fungi, or amoeba as the most common infection etiologies. While an accurate and timely diagnosis is crucial for the selected treatment and the patients' sight outcomes, due to the high cost and limited availability of laboratory diagnostics in LMICs, diagnosis is often made by clinical observation alone, despite its lower accuracy. In this study, we investigate and compare different deep learning approaches to diagnose the source of infection: 1) three separate binary models for infection type predictions; 2) a multitask model with a shared backbone and three parallel classification layers (Multitask V1); and, 3) a multitask model with a shared backbone and a multi-head classification layer (Multitask V2). We used a private Brazilian cornea dataset to conduct the empirical evaluation. We achieved the best results with Multitask V2, with an area under the receiver operating characteristic curve (AUROC) confidence intervals of 0.7413-0.7740 (bacteria), 0.8395-0.8725 (fungi), and 0.9448-0.9616 (amoeba). A statistical analysis of the impact of patient features on models' performance revealed that sex significantly affects amoeba infection prediction, and age seems to affect fungi and bacteria predictions.