Corneal Edema Visualization With Optical Coherence Tomography Using Deep Learning: Proof of Concept.

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.

Determining Subclinical Edema in Fuchs Endothelial Corneal Dystrophy: Revised Classification using Scheimpflug Tomography for Preoperative Assessment.

PURPOSE: To determine if Scheimpflug tomography can identify subclinical corneal edema in Fuchs endothelial corneal dystrophy (FECD), and to recommend a new classification of FECD for clinical practice and research. DESIGN: Cross-sectional study with follow-up of outcomes. PARTICIPANTS: Ninety-three eyes from 57 subjects with a range of severity of FECD and 74 eyes from 40 subjects with normal corneas. METHODS: Corneas were clinically assessed for FECD and corneal edema by using slit-lamp biomicroscopy, and categorized as having clinically definite edema (obvious visible edema), being suspicious for subclinical edema (possible corneal thickening without obvious edema on slit-lamp examination), or not having edema (no clinical suspicion of edema). Tomographic pachymetry and elevation maps derived from Scheimpflug images were evaluated by 3 masked observers for specific features believed to be consistent with corneal edema. FECD clinical disease course and outcomes were reviewed from the time of Scheimpflug image acquisition to the last available follow-up. MAIN OUTCOME MEASURES: Presence of tomographic features: (1) loss of parallel isopachs, (2) displacement of the thinnest point of the cornea, and (3) focal posterior corneal surface depression. Clinical outcomes included the change in central corneal thickness (CCT) and vision after endothelial keratoplasty (EK). RESULTS: The 3 specific tomographic features were all present in all FECD corneas with clinically definite edema (n = 15), in ≥81% of FECD corneas suspicious for subclinical edema (n = 16), in ≤42% of FECD corneas deemed not to have edema (n = 62), and in ≤5% of normal corneas (n = 74). Corneas suspicious for subclinical edema that subsequently underwent EK (n = 9) all had at least 2 of the tomographic features present before EK, and improvement in vision, CCT, and tomographic features after EK confirmed the presence of subclinical edema preoperatively. CONCLUSIONS: Subclinical corneal edema in FECD can be detected by Scheimpflug tomography. We recommend classifying FECD corneas as having clinically definite edema (based on slit-lamp examination), subclinical edema (based on tomographic features without clinically definite edema), or no edema (no tomographic or slit-lamp features of edema). This classification is independent of CCT and should be considered when evaluating FECD eyes for cataract surgery or EK.

Edema de córnea e pós-operatório de catarata: proposta de uma nova classificaçäo / Corneal edema and cataract surgery

Pesquisou-se, através de estudo clínico em pacientes de ambulatório, o edema de córnea como complicaçäo pós-operatória na cirurgia de catarata. O estudo aborda os sinais de intensidade do edema corneano e propöe uma nova classificaçäo de forma a qualificar este mesmo edema. Esta classificaçäo é baseada em sinais biomicroscópicos e, principalmente, na paquimetria óptica da córnea. Através do acompanhamento de cada paciente em seu pós-operatório, traça-se um gráfico refletindo a evoluçäo do edema. Apresenta-se em conjunto, um estudo de 20 pacientes submetidos à facectomia e monitorados quanto ao edema pós-operatório por esta classificaçäo. O resultado é satisfatório, obtendo-se elemento de estatística da ordem de P<0,025 para validade dos fatos