Automatic scoring of drug-induced sleep endoscopy for obstructive sleep apnea using deep learning

Hanif, Umaer; Kiær, Eva Kirkegaard; Capasso, Robson; Liu, Stanley Yung‐Chuan; Mignot, Emmanuel; Sørensen, Henrik Rokkjær; Jennum, Poul

doi:10.1016/j.sleep.2022.12.015

Cited by 5 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Snoring sounds were recorded during the DISE examination of OSA patients. Hanif et al used a deep learning approach for the automatic scoring of drug-induced sleep endoscopy in obstructive sleep apnea [ 29 ]. In their study, the research objective was to identify the degree of obstruction in the diseased sites (velum, oropharynx, tongue base, and epiglottis).…”

Section: Introductionmentioning

confidence: 99%

“…Evaluating the degree of obstruction in an affected area manually using DISE videos is not only inefficient but also lacks precision. Therefore, Hanif et al’s study [ 29 ] utilized deep learning to automatically score the degree of OSA obstruction. Their method was based on the grading criteria introduced by Kezirian in 2011 [ 12 ], using images of three degrees of OSA obstruction as the target for deep-learning image training.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of a Deep Learning-Based Epiglottis Obstruction Ratio Calculation System

Su,

2023

Sensors

View full text Add to dashboard Cite

Surgeons determine the treatment method for patients with epiglottis obstruction based on its severity, often by estimating the obstruction severity (using three obstruction degrees) from the examination of drug-induced sleep endoscopy images. However, the use of obstruction degrees is inadequate and fails to correspond to changes in respiratory airflow. Current artificial intelligence image technologies can effectively address this issue. To enhance the accuracy of epiglottis obstruction assessment and replace obstruction degrees with obstruction ratios, this study developed a computer vision system with a deep learning-based method for calculating epiglottis obstruction ratios. The system employs a convolutional neural network, the YOLOv4 model, for epiglottis cartilage localization, a color quantization method to transform pixels into regions, and a region puzzle algorithm to calculate the range of a patient’s epiglottis airway. This information is then utilized to compute the obstruction ratio of the patient’s epiglottis site. Additionally, this system integrates web-based and PC-based programming technologies to realize its functionalities. Through experimental validation, this system was found to autonomously calculate obstruction ratios with a precision of 0.1% (ranging from 0% to 100%). It presents epiglottis obstruction levels as continuous data, providing crucial diagnostic insight for surgeons to assess the severity of epiglottis obstruction in patients.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Development of a Deep Learning-Based Epiglottis Obstruction Ratio Calculation System

Su,

2023

Sensors

View full text Add to dashboard Cite

show abstract

Predicting Therapeutic Response to Hypoglossal Nerve Stimulation Using Deep Learning

Alapati,

Renslo,

Jackson

et al. 2024

The Laryngoscope

View full text Add to dashboard Cite

ObjectivesTo develop and validate machine learning (ML) and deep learning (DL) models using drug‐induced sleep endoscopy (DISE) images to predict the therapeutic efficacy of hypoglossal nerve stimulator (HGNS) implantation.MethodsPatients who underwent DISE and subsequent HGNS implantation at a tertiary care referral center were included. Six DL models and five ML algorithms were trained on images from the base of tongue (BOT) and velopharynx (VP) from patients classified as responders or non‐responders as defined by Sher's criteria (50% reduction in apnea‐hypopnea index (AHI) and AHI < 15 events/h). Precision, recall, F1 score, and overall accuracy were evaluated as measures of performance.ResultsIn total, 25,040 images from 127 patients were included, of which 16,515 (69.3%) were from responders and 8,262 (30.7%) from non‐responders. Models trained on the VP dataset had greater overall accuracy when compared to BOT alone and combined VP and BOT image sets, suggesting that VP images contain discriminative features for identifying therapeutic efficacy. The VCG‐16 DL model had the best overall performance on the VP image set with high training accuracy (0.833), F1 score (0.78), and recall (0.883). Among ML models, the logistic regression model had the greatest accuracy (0.685) and F1 score (0.813).ConclusionDeep neural networks have potential to predict HGNS therapeutic efficacy using images from DISE, facilitating better patient selection for implantation. Development of multi‐institutional data and image sets will allow for development of generalizable predictive models.Level of EvidenceN/A Laryngoscope, 2024

show abstract

Computer Vision and Videomics in Otolaryngology–Head and Neck Surgery

Paderno,

Bedi,

Rau

et al. 2024

Otolaryngologic Clinics of North America

View full text Add to dashboard Cite

Automatic scoring of drug-induced sleep endoscopy for obstructive sleep apnea using deep learning

Cited by 5 publications

References 47 publications

Development of a Deep Learning-Based Epiglottis Obstruction Ratio Calculation System

Development of a Deep Learning-Based Epiglottis Obstruction Ratio Calculation System

Predicting Therapeutic Response to Hypoglossal Nerve Stimulation Using Deep Learning

Computer Vision and Videomics in Otolaryngology–Head and Neck Surgery

Contact Info

Product

Resources

About