Pierre Zéboulon1, Wassim Ghazal1, Damien Gatinel1,2. 1. Department of Ophthalmology, Rothschild Foundation, Paris, France; and. 2. CEROC (Center of Expertise and Research in Optics for Clinicians).
Abstract
PURPOSE: Optical coherence tomography (OCT) is essential for the diagnosis and follow-up of corneal edema, but assessment can be challenging in minimal or localized edema. The objective was to develop and validate a novel automated tool to detect and visualize corneal edema with OCT. METHODS: We trained a convolutional neural network to classify each pixel in the corneal OCT images as "normal" or "edema" and to generate colored heat maps of the result. The development set included 199 OCT images of normal and edematous corneas. We validated the model's performance on 607 images of normal and edematous corneas of various conditions. The main outcome measure was the edema fraction (EF), defined as the ratio between the number of pixels labeled as edema and those representing the cornea for each scan. Overall accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve were determined to evaluate the model's performance. RESULTS: Mean EF was 0.0087 ± 0.01 in the normal scans and 0.805 ± 0.26 in the edema scans (P < 0.0001). Area under the receiver operating characteristic curve for EF in the diagnosis of corneal edema in individual scans was 0.994. The optimal threshold for distinguishing normal from edematous corneas was 6.8%, with an accuracy of 98.7%, sensitivity of 96.4%, and specificity of 100%. CONCLUSIONS: The model accurately detected corneal edema and distinguished between normal and edematous cornea OCT scans while providing colored heat maps of edema presence.
PURPOSE: Optical coherence tomography (OCT) is essential for the diagnosis and follow-up of corneal edema, but assessment can be challenging in minimal or localized edema. The objective was to develop and validate a novel automated tool to detect and visualize corneal edema with OCT. METHODS: We trained a convolutional neural network to classify each pixel in the corneal OCT images as "normal" or "edema" and to generate colored heat maps of the result. The development set included 199 OCT images of normal and edematous corneas. We validated the model's performance on 607 images of normal and edematous corneas of various conditions. The main outcome measure was the edema fraction (EF), defined as the ratio between the number of pixels labeled as edema and those representing the cornea for each scan. Overall accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve were determined to evaluate the model's performance. RESULTS: Mean EF was 0.0087 ± 0.01 in the normal scans and 0.805 ± 0.26 in the edema scans (P < 0.0001). Area under the receiver operating characteristic curve for EF in the diagnosis of corneal edema in individual scans was 0.994. The optimal threshold for distinguishing normal from edematous corneas was 6.8%, with an accuracy of 98.7%, sensitivity of 96.4%, and specificity of 100%. CONCLUSIONS: The model accurately detected corneal edema and distinguished between normal and edematous cornea OCT scans while providing colored heat maps of edema presence.