The Clinical Value of Explainable Deep Learning for Diagnosing Fungal Keratitis Using in vivo Confocal Microscopy Images.

Fan Xu,Ningning Tang,Yunru Lin,Min Li,Xipeng Pan,Rushi Lan,Qi Chen,Siming Zeng,Jian Lv,Yikun Qin,Fen Tang,Li Jiang,Wenjing He,Yiyi Hong,Guangyi Huang

doi:10.3389/fmed.2021.797616

Abstract

Background: Artificial intelligence (AI) has great potential to detect fungal keratitis using in vivo confocal microscopy images, but its clinical value remains unclarified. A major limitation of its clinical utility is the lack of explainability and interpretability.Methods: An explainable AI (XAI) system based on Gradient-weighted Class Activation Mapping (Grad-CAM) and Guided Grad-CAM was established. In this randomized controlled trial, nine ophthalmologists (three expert ophthalmologists, three competent ophthalmologists, and three novice ophthalmologists) read images in each of the conditions: unassisted, AI-assisted, or XAI-assisted. In unassisted condition, only the original IVCM images were shown to the readers. AI assistance comprised a histogram of model prediction probability. For XAI assistance, explanatory maps were additionally shown. The accuracy, sensitivity, and specificity were calculated against an adjudicated reference standard. Moreover, the time spent was measured.Results: Both forms of algorithmic assistance increased the accuracy and sensitivity of competent and novice ophthalmologists significantly without reducing specificity. The improvement was more pronounced in XAI-assisted condition than that in AI-assisted condition. Time spent with XAI assistance was not significantly different from that without assistance.Conclusion: AI has shown great promise in improving the accuracy of ophthalmologists. The inexperienced readers are more likely to benefit from the XAI system. With better interpretability and explainability, XAI-assistance can boost ophthalmologist performance beyond what is achievable by the reader alone or with black-box AI assistance.

Highlights

Fungal keratitis (FK) is one of the most common causes of cornea-derived blindness [1] but the diagnosis and treatment of this disease remain difficult [2, 3]
We developed an XAI-based system to diagnose FK using In vivo confocal microscopy (IVCM) images and provided visual explanations based on Grad-Class Activation Mapping (CAM) and Guided Grad-CAM methods to highlight the relevance for the decision of individual pixel regions in the input image
The model achieved an area under the receiver-operating characteristic (ROC) curve (AUC) of 0.983 (P < 0.001) and accuracy, sensitivity, and specificity of 0.965, 0.936, and 0.982, respectively

Summary

Introduction

Fungal keratitis (FK) is one of the most common causes of cornea-derived blindness [1] but the diagnosis and treatment of this disease remain difficult [2, 3]. Culture routinely takes several days before the results are available. In vivo confocal microscopy (IVCM) is a useful method for the diagnosis of FK, which allows non-invasive and in vivo detection of even subtle changes in the living cornea [5, 6]. Correct and prompt monitoring of the fungal hyphae in IVCM images contributes to make a diagnosis of FK as early as possible and optimize the appropriate management of patients [10]. Artificial intelligence (AI) has great potential to detect fungal keratitis using in vivo confocal microscopy images, but its clinical value remains unclarified. A major limitation of its clinical utility is the lack of explainability and interpretability

Methods

Results

Discussion

Conclusion