Clinical Trials Logo

Clinical Trial 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.


Clinical Trial 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


Related Conditions & MeSH terms


NCT number NCT04828187
Study type Observational [Patient Registry]
Source Democritus University of Thrace
Contact
Status Completed
Phase
Start date October 1, 2020
Completion date March 25, 2021

See also
  Status Clinical Trial Phase
Not yet recruiting NCT05550012 - A New Deep-learning Based Artificial Intelligence Iterative Reconstruction (AIIR) Algorithm in Low-dose Liver CT N/A
Completed NCT04921488 - Interest of Artificial Intelligence in Cancer Screening Colonoscopy N/A
Completed NCT06274502 - Automated Detection and Diagnosis of Pathological DRGs in PHN Patients Using Deep Learning and Magnetic Resonance
Recruiting NCT05046366 - Development of an Artificial Intelligence System for Intelligent Pathological Diagnosis and Therapeutic Effect Prediction Based on Multimodal Data Fusion of Common Tumors and Major Infectious Diseases in the Respiratory System Using Deep Learning Technology.
Recruiting NCT04824378 - Study on Classification Method of Indocyanine Green Lymphography Based on Deep Learning
Recruiting NCT04592068 - AI Classifies Multi-Retinal Diseases
Recruiting NCT05058599 - Reconstruction Technology to Auxiliary Diagnosis and Guarantee Patient Privacy
Recruiting NCT05536024 - Combing a Deep Learning-Based Radiomics With Liquid Biopsy for Preoperative and Non-invasive Diagnosis of Glioma
Completed NCT05323279 - Evaluate the Effects of An AI System on Colonoscopy Quality of Novice Endoscopists N/A
Completed NCT06278272 - AI Evaluation of Pancreatic Exocrine Insufficiency in CP Patients
Recruiting NCT05426135 - Artificial Intelligence System for Assessment of Tumor Risk and Diagnosis and Treatment
Recruiting NCT05444166 - Explore the Relationship Between the Percentage of Colonoscopy Withdrawal Overspeed and the ADR
Recruiting NCT05617469 - DLCS for Predicting Neoadjuvant Chemotherapy Response
Active, not recruiting NCT05182099 - High Resolution HBA-MRI Using Deep Learning Reconstruction N/A
Recruiting NCT05204186 - Impact of COMORBIDities After Radical Cystectomy Using a Predictive Method With Artificial Intelligence
Active, not recruiting NCT05041777 - Optical-Coherence Tomography for the Non-invasive Diagnosis and Subtyping of Basal Cell Carcinoma
Not yet recruiting NCT06118840 - IDEAL Study: Blinded RCT for the Impact of AI Model for Cerebral Aneurysms Detection on Patients' Diagnosis and Outcomes N/A
Completed NCT06167863 - Retrospective Analysis of the Correlation Between Imaging Features and Pathology, Prognosis in Renal Tumors
Not yet recruiting NCT05336773 - Ulcerative Colitis Mayo Score With Artificial Intelligence