Dataset Information

Effects of fluorescein staining on laser in vivo confocal microscopy images of the cornea.

ABSTRACT: This study was designed to identify whether topical fluorescein, a common ophthalmic tool, affects laser in vivo confocal microscopy of the cornea, a tool with growing applications. Twenty-five eye care specialists were asked to identify presence or absence of fluorescein in 99 confocal micrographs of healthy corneas. Responses were statistically similar to guessing for the epithelium (48%?±?14% of respondents correct per image) and the subbasal nerve plexus (49%?±?11% correct), but results were less clear for the stroma. Dendritic immune cells were quantified in bilateral images from subjects who had been unilaterally stained with fluorescein. Density of dendritic immune cells was statistically similar between the unstained and contralateral stained eyes of 24 contact lens wearers (P = .72) and of 10 nonwearers (P = .53). Overall, the results indicated that fluorescein staining did not interfere with laser confocal microscopy of corneal epithelium, subbasal nerves, or dendritic immune cells.

SUBMITTER: Sindt CW

PROVIDER: S-EPMC3272843 | biostudies-literature | 2012

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Effects of fluorescein staining on laser in vivo confocal microscopy images of the cornea.

Sindt Christine W CW Critser D Brice DB Grout Trudy K TK Kern Jami R JR

Journal of ophthalmology 20120126

This study was designed to identify whether topical fluorescein, a common ophthalmic tool, affects laser in vivo confocal microscopy of the cornea, a tool with growing applications. Twenty-five eye care specialists were asked to identify presence or absence of fluorescein in 99 confocal micrographs of healthy corneas. Responses were statistically similar to guessing for the epithelium (48% ± 14% of respondents correct per image) and the subbasal nerve plexus (49% ± 11% correct), but results were ...[more]

PMID: 22363837

Similar Datasets

Project description:To report the in vivo laser confocal microscopy findings of corneas with keratoconus, with special attention to abnormality of Bowman's layer and sub-Bowman's fibrous structures (Kobayashi-structures [K-structures]).Sixteen keratoconic eyes in 8 consecutive patients with keratoconus (4 males, 4 females, mean age, 41.1 years) were included in this study. Slit-lamp biomicroscopic photos were taken with or without fluorescein staining. The existence of anterior corneal mosaic (ACM) after eyelid rubbing under fluorescein staining was documented. In vivo laser confocal microscopic examinations were performed for all patients in both the central cone and the peripheral cornea to examine the existence of K-structures.According to the Amsler-Krumeich scale, the eyes were graded as follows: stage 1 (n=3), stage 2 (n=1), stage 3 (n=1), and stage 4 (n=11). ACM was observed in 7 eyes (61.1%) in the cone area and 16 eyes (100%) in the peripheral cornea among all keratoconic eyes enrolled in this study. In addition, K-structures were observed in the 7 eyes (61.1%) and 16 eyes (100%) in the peripheral cornea among all keratoconic eyes. The presence of the K-structures was completely matched (100%) with the presence of ACM in both the central cone and the peripheral cornea. In 11 eyes with stage 4 keratoconus, ACM and K-structure was absent in 9 eyes (81.8%) in the cone area. On the contrary, in 5 eyes with mild-to-moderate keratoconus (grade 1 to 3), ACM and K-structure was present in all eyes (100%) in the cone area. The absent ratio of ACM and K-structures in the cone area was significantly higher in stage 4 severe keratoconus compared to mild-to-moderate keratoconus (grade 1 to 3) (Fisher, P=0.005).The existence of ACM and K-structures in both the central cone and the peripheral cornea showed perfect accord in patients with keratoconus, indicating a strong association of ACM and K-structures in patients with keratoconus. With the progress of the keratoconus, it seemed that ACM and K-structure progressively disappeared, suggesting Bowman's layer abnormalities due to keratoconus. Further study in larger groups of patients with keratoconus is required to fully understand the significance of ACM/K-structures in keratoconic eyes and their association with Bowman's layer.

Project description:PurposeIn vivo confocal microscopy (IVCM) is a noninvasive, reproducible, and inexpensive diagnostic tool for corneal diseases. However, widespread and effortless image acquisition in IVCM creates serious image analysis workloads on ophthalmologists, and neural networks could solve this problem quickly. We have produced a novel deep learning algorithm based on generative adversarial networks (GANs), and we compare its accuracy for automatic segmentation of subbasal nerves in IVCM images with a fully convolutional neural network (U-Net) based method.MethodsWe have collected IVCM images from 85 subjects. U-Net and GAN-based image segmentation methods were trained and tested under the supervision of three clinicians for the segmentation of corneal subbasal nerves. Nerve segmentation results for GAN and U-Net-based methods were compared with the clinicians by using Pearson's R correlation, Bland-Altman analysis, and receiver operating characteristics (ROC) statistics. Additionally, different noises were applied on IVCM images to evaluate the performances of the algorithms with noises of biomedical imaging.ResultsThe GAN-based algorithm demonstrated similar correlation and Bland-Altman analysis results with U-Net. The GAN-based method showed significantly higher accuracy compared to U-Net in ROC curves. Additionally, the performance of the U-Net deteriorated significantly with different noises, especially in speckle noise, compared to GAN.ConclusionsThis study is the first application of GAN-based algorithms on IVCM images. The GAN-based algorithms demonstrated higher accuracy than U-Net for automatic corneal nerve segmentation in IVCM images, in patient-acquired images and noise applied images. This GAN-based segmentation method can be used as a facilitating diagnostic tool in ophthalmology clinics.Translational relevanceGenerative adversarial networks are emerging deep learning models for medical image processing, which could be important clinical tools for rapid segmentation and analysis of corneal subbasal nerves in IVCM images.

Dataset Information

Effects of fluorescein staining on laser in vivo confocal microscopy images of the cornea.

Publications

Effects of fluorescein staining on laser in vivo confocal microscopy images of the cornea.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets