Development and Validation of Deep Neural Networks for Blinking Identification and Classification

NCT04828187 | Completed DMC

• 1 other identifier: ES2/Th15/25-2-2021
• Study Type: observational
• Target: 8
• Locations: 1 country
• Sites: 2

Brief Summary

Primary objective of this study is the development and validation of a system of deep neural networks which automatically detects and classifies blinks as "complete" or "incomplete" in image sequences.

Conditions

Blinking; Deep Learning

Keywords

deep learning; DeepLabv3+; iris and sclera segmentation; eye blink detection; complete and incomplete blink classification

Outcome Measures

Primary Outcomes (3)

• Identification of complete and incomplete blinks

  Complete and incomplete blinks are defined by the "length of palpebral fissure-to-iris diameter" ratio

  up to 1 week

• First frame of each blink

  The frame in which the upper eyelid starts to move down and cover the cornea

  up to 1 week

• Last frame of each blink

  The frame in which eyelids open fully after a blink

  up to 1 week

Secondary Outcomes (2)

• Length of palpebral fissure of both eyes

  up to 1 week

• Iris diameter of both eyes

  up to 1 week

Study Arms (1)

Study group

8 patients aged between 18 to 75 years with Uncorrected Distance Visual Acuity ≥ 5/10

Diagnostic Test: Comparison of the proposed artificial network with the ground truth

Interventions

Comparison of the proposed artificial network with the ground truth DIAGNOSTIC_TEST

Both eyes will be included for each study participant. Participants watched a 4-10-minute video in standard mesopic environmental lighting conditions at 3.5m viewing distance. Simultaneously, all blinking moves will be recorded through a web infrared camera. The proposed system was tested on the 8 different subjects. Several metrics of blink detection and classification accuracy were calculated against the ground truth, which was generated by 3 independent experts, whose conflicts were resolved by a senior expert. Two independent blink identifications are assumed to be in agreement, if and only if there is sufficient temporal overlapping and the type of blink is the same between the DLED system and the ground truth.

Study group

Eligibility Criteria

• Age: 18 Years - 75 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients aged from 18 to 75 years with Uncorrected Distance Visual Acuity ≥ 5/10

You may qualify if:

• Uncorrected Distance Visual Acuity above 6/12

You may not qualify if:

• corneal opacities
• age-related macular degeneration
• diagnosis of psychiatric diseases
• former eyelid surgery

Sponsors & Collaborators

• Democritus University of Thrace: lead
• University of Thessaly: collaborator

Study Sites (2)

Department of Ophthalmology, University Hospital of Alexandroupolis

Alexandroupoli, Evros, 68100, Greece

Location

Department of Computer Science and Biomedical Informatics, University of Thessaly

Lamia, Thessaly, 35100, Greece

Location

Related Publications (1)

• Nousias G, Panagiotopoulou EK, Delibasis K, Chaliasou AM, Tzounakou AM, Labiris G. Video-Based Eye Blink Identification and Classification. IEEE J Biomed Health Inform. 2022 Jul;26(7):3284-3293. doi: 10.1109/JBHI.2022.3153407. Epub 2022 Jul 1.

  PMID: 35213320 BACKGROUND

Study Officials

• Georgios Labiris, MD,PhD

  Department of Ophthalmology, University Hospital of Alexandroupolis, Alexandroupolis, Greece

  STUDY CHAIR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor of Ophthalmology

Study Record Dates

• First Submitted: March 29, 2021
• First Posted: April 1, 2021
• Study Start: October 1, 2020
• Primary Completion: March 10, 2021
• Study Completion: March 25, 2021
• Last Updated: January 4, 2023

Record last verified: 2023-01

Locations

GR (2)