Related Experiment Video
Updated: May 7, 2025
Drug-Induced Sleep Endoscopy DISE with Target Controlled Infusion TCI and Bispectral Analysis in Obstructive Sleep Apnea
Published on: December 6, 2016
Deep Learning-Based Quantification of Adenoid Hypertrophy and Its Correlation with Apnea-Hypopnea Index in Pediatric
Jie Cai1, Tianyu Xiu2, Yuliang Song1
1Department of Otorhinolaryngology, Head and Neck Surgery, Zhongnan Hospital of Wuhan University, Wuhan, 430000, People's Republic of China.
Insights
A new deep learning method accurately quantifies adenoid hypertrophy in children, showing a strong link to obstructive sleep apnea severity. This aids in diagnosing pediatric obstructive sleep apnea (OSA).
Area of Science:
- Otolaryngology
- Medical Imaging
- Artificial Intelligence
Background:
- Adenoid hypertrophy is a common cause of pediatric obstructive sleep apnea (OSA).
- Accurate assessment of adenoid hypertrophy is crucial for diagnosis and treatment planning.
- Current methods for quantifying adenoid hypertrophy can be subjective and time-consuming.
Purpose of the Study:
- To develop a deep learning (DL) methodology for quantitative assessment of adenoid hypertrophy from nasopharyngoscopy images.
- To investigate the correlation between DL-derived adenoid-to-nasopharyngeal (A/N) ratio and the apnea-hypopnea index (AHI) in pediatric OSA patients.
Main Methods:
- A dataset of 1500 nasopharyngoscopy images from pediatric patients (3-12 years) was used.
- Deep learning segmentation models were developed using the MMSegmentation framework with transfer and ensemble learning.
- Model performance was evaluated using precision, recall, MIoU, accuracy, Cohen's Kappa, and ROC curves. Correlation with AHI from polysomnography was analyzed.
Main Results:
- The ensemble learning-based SUMNet model achieved high performance: precision (0.9616), MIoU (0.8046), accuracy (0.9182), and Kappa (0.87).
- SUMNet demonstrated superior performance compared to expert evaluations in ROC analysis (AUC=0.85 vs. 0.74).
- A strong positive correlation was found between SUMNet-derived A/N ratios and AHI (r=0.4452 to 0.9052).
Conclusions:
- A precise and reliable deep learning method for quantifying adenoid hypertrophy was developed.
- The DL method effectively addresses challenges of limited sample sizes in deep learning.
- The significant correlation between adenoid hypertrophy and AHI highlights the clinical utility for pediatric OSA diagnosis.
Purpose:
This study aims to develop a deep learning methodology for quantitative assessing adenoid hypertrophy in nasopharyngoscopy images and to investigate its correlation with the apnea-hypopnea index (AHI) in pediatric patients with obstructive sleep apnea (OSA).
Patients And Methods:
A total of 1642 nasopharyngoscopy images were collected from pediatric patients aged 3 to 12 years. After excluding images with obscured secretions, incomplete adenoid exposure, 1500 images were retained for analysis. The adenoid-to-nasopharyngeal (A/N) ratio was manually annotated by two experienced otolaryngologists using MATLAB's imfreehand tool. Inter-annotator agreement was assessed using the Mann-Whitney U-test. Deep learning segmentation models were developed with the MMSegmentation framework, incorporating transfer learning and ensemble learning techniques. Model performance was evaluated using precision, recall, mean intersection over union (MIoU), overall accuracy, Cohen's Kappa, confusion matrices, and receiver operating characteristic (ROC) curves. The correlation between the A/N ratio and AHI, derived from polysomnography, was analyzed to evaluate clinical relevance.
Results:
Manual evaluation of adenoid hypertrophy by otolaryngologists (p=0.8507) and MATLAB calibration (p=0.679) demonstrated high consistency, with no significant differences. Among the deep learning models, the ensemble learning-based SUMNet outperformed others, achieving the highest precision (0.9616), MIoU (0.8046), overall accuracy (0.9182), and Kappa (0.87). SUMNet also exhibited superior consistency in classifying adenoid sizes. ROC analysis revealed that SUMNet (AUC=0.85) outperformed expert evaluations (AUC=0.74). A strong positive correlation was observed between the A/N ratio and AHI, with the correlation coefficients for SUMNet-derived ratios ranging from r=0.9052 (tonsils size+1) to r=0.4452 (tonsils size+3) and for expert-derived ratios ranging from r=0.4590 (tonsils size+1) to r=0.2681 (tonsils size+3).
Conclusion:
This study introduces a precise and reliable deep learning-based method for quantifying adenoid hypertrophy and addresses the challenge posed limited sample sizes in deep learning applications. The significant correlation between adenoid hypertrophy and AHI underscores the clinical utility of this method in pediatric OSA diagnosis.
Related Concept Videos
01:21Sleep Apnea
The condition is more prevalent among...
01:29Assessment of Ventilation II: Respiratory Depth and Rhythm
Respiratory depth measures the volume of air inhaled or exhaled during a breath. It can vary from shallow to deep and typically remains consistent when a person is at rest or asleep. Occasionally, individuals will automatically inhale deeply, known as sighing, which inflates the lungs with more air than normal breathing.
To assess respiratory depth, observe the degree of chest excursion or movement:
01:30Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
01:27Physical Assessment of the Respiratory Tract II: Inspection
Chest Configuration
The chest configuration...