Sensitivity and Specificity of Laser-Scanning In Vivo Confocal Microscopy for Filamentous Fungal Keratitis: Role of Observer Experience

Purpose To determine sensitivity and specificity of laser-scanning in vivo confocal microscopy (LS-IVCM) for detection of filamentous fungi in patients with microbial keratitis and to evaluate the effect of observer's imaging experience on these parameters. Design Retrospective reliability study. Methods This study included 21 patients with filamentous fungal keratitis and 24 patients with bacterial keratitis (as controls). The etiology of infection was confirmed based on the response to specific therapy regardless of culture results. All patients had undergone full-thickness corneal imaging by a LS-IVCM (Heidelberg Retina Tomograph 3 with Rostock Cornea Module; Heidelberg Engineering, Heidelberg, Germany). The images were evaluated for the presence of fungal filaments by 2 experienced observers and 2 inexperienced observers. All observers were masked to the clinical and microbiologic data. Results The mean number of images obtained per eye was 917 ± 353. The average sensitivity of LS-IVCM for detecting fungal filaments was 71.4% ± 0% for the experienced observers and 42.9% ± 6.7% for the inexperienced observers. The average specificity was 89.6% ± 3.0% and 87.5% ± 17.7% for these 2 groups of observers, respectively. Although there was a good agreement between the 2 experienced observers (κ = 0.77), the inexperienced observers showed only a moderate interobserver agreement (κ = 0.51). The LS-IVCM sensitivity was higher in patients with fungal infections who had positive culture or longer duration of the disease. Conclusions Although LS-IVCM has a high specificity for diagnosing filamentous fungal keratitis, its sensitivity is moderate and highly dependent on the level of the observer's experience and training with this imaging modality.