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

• Sponsor: Democritus University of Thrace (Other)
• Overall Status: Completed
• CT.gov ID: NCT04828187
• Collaborator: University of Thessaly (Other)
• Enrollment: 8
• Locations: 2
• Actual Duration (Months): 5.7
• Patients Per Site: 4
• Patients Per Site Per Month: 0.7

Study Details

Study Description

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.

Condition or Disease	Intervention/Treatment	Phase
Blinking; Deep Learning	Diagnostic Test: Comparison of the proposed artificial network with the ground truth

Detailed Description

This method is based on iris and sclera segmentation in both eyes from the acquired images, using state of the art deep learning encoder-decoder neural architectures (DLED). The sequence of the segmented frames is post-processed to calculate the distance between the eyelids of each eye (palpebral fissure) and the corresponding iris diameter. Theses quantities are temporally filtered and their fraction is subject to adaptive thresholding to identify blinks and determine their type, independently for each eye. The two DLEDs were trained with manually segmented images and the post-process was parameterized using a 4-minute video. After DLED training, the proposed system was tested on 8 different subjects, each one with a 4-10-minute video. 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 Design

• Study Type: Observational [Patient Registry]
• Actual Enrollment: 8 participants
• Observational Model: Cohort
• Time Perspective: Prospective
• Official Title: Development and Validation of Deep Neural Networks for Blinking Identification and Classification
• Actual Study Start Date: Oct 1, 2020
• Actual Primary Completion Date: Mar 10, 2021
• Actual Study Completion Date: Mar 25, 2021

Arms and Interventions

Arm

Intervention/Treatment

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; 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.

Outcome Measures

Primary Outcome Measures

1. Identification of complete and incomplete blinks [up to 1 week]

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

2. First frame of each blink [up to 1 week]

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

3. Last frame of each blink [up to 1 week]

   The frame in which eyelids open fully after a blink

Secondary Outcome Measures

1. Length of palpebral fissure of both eyes [up to 1 week]

   The distance between the upper eyelid margin and the lower eyelid margin (ie. the vertical dimension of the palpebral fissure),

2. Iris diameter of both eyes [up to 1 week]

   The horizontal diameter of the iris (ie. the horizontal white-to white distance)

Eligibility Criteria

Criteria

• Ages Eligible for Study: 18 Years to 75 Years
• Sexes Eligible for Study: All
• Accepts Healthy Volunteers: Yes

Inclusion Criteria

• Uncorrected Distance Visual Acuity above 6/12

Exclusion Criteria:

• corneal opacities

• age-related macular degeneration

• diagnosis of psychiatric diseases

• former eyelid surgery

Contacts and Locations

Locations

	Site	City	State	Country	Postal Code
1	Department of Ophthalmology, University Hospital of Alexandroupolis	Alexandroupolis	Evros	Greece	68100
2	Department of Computer Science and Biomedical Informatics, University of Thessaly	Lamia	Thessaly	Greece	35100

Sponsors and Collaborators

• Democritus University of Thrace
• University of Thessaly

Investigators

• Study Chair: Georgios Labiris, MD,PhD, Department of Ophthalmology, University Hospital of Alexandroupolis, Alexandroupolis, Greece

Study Documents (Full-Text)

None provided.

More Information

Publications

None provided.

• Responsible Party: Georgios Labiris, Associate Professor of Ophthalmology, Democritus University of Thrace
• ClinicalTrials.gov Identifier: NCT04828187
• Other Study ID Numbers: ES2/Th15/25-2-2021
• First Posted: Apr 1, 2021
• Last Update Posted: Apr 1, 2021
• Last Verified: Mar 1, 2021

• Individual Participant Data (IPD) Sharing Statement: Undecided
• Plan to Share IPD: Undecided
• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No
• Keywords provided by Georgios Labiris, Associate Professor of Ophthalmology, Democritus University of Thrace: deep learning; DeepLabv3+; iris and sclera segmentation; eye blink detection; complete and incomplete blink classification

Study Results

No Results Posted as of Apr 1, 2021