Dataset Information

Impact of Incomplete Blinking Analyzed Using a Deep Learning Model With the Keratograph 5M in Dry Eye Disease.

ABSTRACT:

Purpose

To establish a deep learning model (DLM) for blink analysis, and investigate whether blink video frame sampling rate influences the accuracy of analysis.

Methods

This case-controlled study recruited 50 dry eye disease (DED) participants and 50 normal subjects. Blink videos recorded by a Keratograph 5M, symptom questionnaires, and ocular surface assessments were collected. After processing the blink images as datasets, further training and evaluation of DLM was performed. Blink videos of 30 frames per second (FPS) under white light, eight FPS extracted from white light videos, and eight FPS under infrared light were processed by DLM to generate blink profiles, allowing comparison of blink parameters, and their association with DED symptoms and signs.

Results

The blink parameters based on 30 FPS video presented higher sensitivity and accuracy than those based on eight FPS. The average relative interpalpebral height (IPH), the frequency and proportion of incomplete blinking (IB) were much higher in DED participants than in normal controls (P < 0.001). The IB frequency was closely associated with DED symptoms and signs (|R| ≥ 0.195, P ≤ 0.048), as was IB proportion and the average IPH (R ≥ 0.202, P ≤ 0.042).

Conclusions

DLM is a powerful tool for analyzing blink videos with high accuracy and sensitivity, and a frame rate ≥ 30 FPS is recommended. The IB frequency is indicative of DED.

Translational relevance

The system of DLM-based blink analysis is of great potential for the assessment of IB and diagnosis of DED.

SUBMITTER: Zheng Q

PROVIDER: S-EPMC8976934 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Impact of Incomplete Blinking Analyzed Using a Deep Learning Model With the Keratograph 5M in Dry Eye Disease.

Zheng Qinxiang Q Wang Lei L Wen Han H Ren Yueping Y Huang Shenghai S Bai Furong F Li Na N Craig Jennifer P JP Tong Louis L Chen Wei W

Translational vision science & technology 20220301 3

<h4>Purpose</h4>To establish a deep learning model (DLM) for blink analysis, and investigate whether blink video frame sampling rate influences the accuracy of analysis.<h4>Methods</h4>This case-controlled study recruited 50 dry eye disease (DED) participants and 50 normal subjects. Blink videos recorded by a Keratograph 5M, symptom questionnaires, and ocular surface assessments were collected. After processing the blink images as datasets, further training and evaluation of DLM was performed. B ...[more]

PMID: 35357395

Similar Datasets

Project description:BackgroundAbnormal blinking pattern is associated with ocular surface diseases. However, blink is difficult to analyze due to the rapid movement of eyelids. Deep learning machine (DLM) has been proposed as an optional tool for blinking analysis, but its clinical practicability still needs to be proven. Therefore, the study aims to compare the DLM-assisted Keratograph 5M (K5M) as a novel method with the currently available Lipiview in the clinic and assess whether blinking parameters can be applied in the diagnosis of dry eye disease (DED).MethodsThirty-five DED participants and 35 normal subjects were recruited in this cross-sectional study. DED questionnaire and ocular surface signs were evaluated. Blinking parameters including number of blinks, number of incomplete blinking (IB), and IB rate were collected from the blinking videos recorded by the K5M and Lipiview. Blinking parameters were individually collected from the DLM analyzed K5M videos and Lipiview generated results. The agreement and consistency of blinking parameters were compared between the two devices. The association of blinking parameters to DED symptoms and signs were evaluated via heatmap.ResultsIn total, 140 eyes of 70 participants were included in this study. Lipiview presented a higher number of IB and IB rate than those from DLM-assisted K5M (P ≤ 0.006). DLM-assisted K5M captured significant differences in number of blinks, number of IB and IB rate between DED and normal subjects (P ≤ 0.035). In all three parameters, DLM-assisted K5M also showed a better consistency in repeated measurements than Lipiview with higher intraclass correlation coefficients (number of blinks: 0.841 versus 0.665; number of IB: 0.750 versus 0.564; IB rate: 0.633 versus 0.589). More correlations between blinking parameters and DED symptoms and signs were found by DLM-assisted K5M. Moreover, the receiver operating characteristic analysis showed the number of IB from K5M exhibiting the highest area under curve of 0.773.ConclusionsDLM-assisted K5M is a useful tool to analyze blinking videos and detect abnormal blinking patterns, especially in distinguishing DED patients from normal subjects. Large sample investigations are therefore warranted to assess its clinical utility before implementation.

Project description:ObjectiveTo investigate the clinical effects of IRT5 probiotics in the environmental dry eye model.MethodsEight week old male C57BL/6 mice were randomly divided into two groups; control group (n = 16) received oral gavage of 300 μL phosphate-buffered saline (PBS) alone once daily, IRT5 group (n = 9) received oral gavage of 1 x 109 CFU IRT5 probiotics powder in 300 μL PBS once daily, both groups for 11 to 12 days. Simultaneously, all mice underwent dry eye induction. Tear secretion, corneal staining and conjunctival goblet cell density were evaluated. Quantative real-time polymerase chain reaction (RT-PCR) for inflammation-related markers was performed. 16S ribosomal RNA of fecal microbiome was analyzed and compositional difference, alpha and beta diversities were assessed.ResultsThere was no difference in NEI score but significant increase in tear secretion was observed in IRT5 group (p < 0.001). There was no significant difference in goblet cell density between groups. Quantative RT-PCR of cornea and conjunctiva revealed increased TNF-α expression in IRT5 group (p < 0.001) whereas other markers did not significantly differ from control. IRT5 group had significantly increased species diversity by Shannon index (p = 0.041). Beta diversity of genus by UniFrac principle coordinates analysis showed significant distance between groups (p = 0.001). Compositional differences between groups were observed and some were significantly associated with tear secretion. Multivariate linear regression analysis revealed Christensenellaceae (p = 0.009), Lactobacillus Helveticus group (p = 0.002) and PAC001797_s (p = 0.011) to strongly influence tear secretion.ConclusionIn experimental dry eye model, IRT5 probiotics treatment partially improves experimental dry eye by increasing tear secretion which was associated with and influenced by the change in intestinal microbiome. Also, intestinal microbiome may affect the lacrimal gland through a different mechanism other than regulating inflammation.

Dataset Information

Impact of Incomplete Blinking Analyzed Using a Deep Learning Model With the Keratograph 5M in Dry Eye Disease.

Purpose

Methods

Results

Conclusions

Translational relevance

Publications

Impact of Incomplete Blinking Analyzed Using a Deep Learning Model With the Keratograph 5M in Dry Eye Disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets