Machine learning for image-based detection of patients with obstructive sleep apnea: an exploratory study

Lakner

et al. 2022

Life

This study aimed to analyse the thickness of the adipose tissue (AT) around the upper airways with anthropometric parameters in the prediction and pathogenesis of OSA and obstruction of the upper airways using artificial intelligence. One hundred patients were enrolled in this prospective investigation, who were divided into control (non-OSA) and mild, moderately severe, and severe OSA according to polysomnography. All participants underwent drug-induced sleep endoscopy, anthropometric measurements, and neck MRI. The statistical analyses were based on artificial intelligence. The midsagittal SAT, the parapharyngeal fat, and the midsagittal tongue fat were significantly correlated with BMI; however, no correlation with AHI was observed. Upper-airway obstruction was correctly categorised in 80% in the case of the soft palate, including parapharyngeal AT, sex, and neck circumference parameters. Oropharyngeal obstruction was correctly predicted in 77% using BMI, parapharyngeal AT, and abdominal circumferences, while tongue-based obstruction was correctly predicted in 79% using BMI. OSA could be predicted with 99% precision using anthropometric parameters and AT values from the MRI. Age, neck circumference, midsagittal and parapharyngeal tongue fat values, and BMI were the most vital parameters in the prediction. Basic anthropometric parameters and AT values based on MRI are helpful in predicting OSA and obstruction location using artificial intelligence.

Section: Introductionmentioning

confidence: 99%

The Predictive Role of the Upper-Airway Adipose Tissue in the Pathogenesis of Obstructive Sleep Apnoea

Lakner

et al. 2022

Life

“…It minimizes the delay in diagnosis and referral of patients to secondary or tertiary care without the need to consider patient privacy breaches. Only Tsuiki et al ( 20 ) reported a similar study in which they developed a deep convolutional neural network using lateral cephalometric radiographs to diagnose severe OSA, with sensitivity reaching 92%.…”

Section: Discussionmentioning

confidence: 99%

“…Facial photography can provide a composite measure of both skeletal and soft tissues and has been shown to capture phenotypic information regarding upper airway structures ( 18 , 19 ). Hence, the presence of OSA or even the magnitude of the AHI can be predicted using facial imaging with an accuracy that can reach 87–91% ( 20 , 21 ). However, for this technique, the faces of patients often need to be individually outlined, photographed, and measured.…”

Section: Introductionmentioning

confidence: 99%

Prediction of obstructive sleep apnea using deep learning in 3D craniofacial reconstruction

Zhang¹,

Feng²,

Li³

et al. 2023

J Thorac Dis

Background: Obstructive sleep apnea (OSA) is a common sleep disorder. However, current diagnostic methods are labor-intensive and require professionally trained personnel. We aimed to develop a deep learning model using upper airway computed tomography (CT) to predict OSA and to warn the medical technician if a patient has OSA while the patient is undergoing any head and neck CT scan, even for other diseases.Methods: A total of 219 patients with OSA [apnea-hypopnea index (AHI) ≥10/h] and 81 controls (AHI <10/h) were enrolled. We reconstructed each patient's CT into 3 types (skeletal structures, external skin structures, and airway structures) and captured reconstructed models in 6 directions (front, back, top, bottom, left profile, and right profile). The 6 images from each patient were imported into the ResNet-18 network to extract features and output the probability of OSA using two fusion methods: Add and Concat.Five-fold cross-validation was used to reduce bias. Finally, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated.Results: All 18 views with Add as the feature fusion performed better than did the other reconstruction and fusion methods. This gave the best performance for this prediction method with an AUC of 0.882. Conclusions:We present a model for predicting OSA using upper airway CT and deep learning. The model has satisfactory performance and enables CT to accurately identify patients with moderate to severe OSA.

“…They reported a limited reliability in the assessment of the tongue and soft palate area using lateral cephalograms. Tsuiki et al 14 included groups of patients with severe OSA and non-OSA according to the craniofacial morphology. They employed the deep learning approach to perform lateral cephalogram-based image classi cation, with successful identi cation of individuals with severe OSA by deep CNNs using lateral cephalogram.…”

Section: Introductionmentioning

confidence: 99%

“…The lateral cephalogram has been acknowledged as the tool con rming the potential relevance of OSA in patients with suspected symptoms. [13][14][15] Deep learning is a subset of arti cial intelligence (AI) technique that can learn from special features and make predictions about image data with or without supervision. 11 Amongst the various deep learning approaches, convolutional neural networks (CNNs) have been highlighted in image recognition to recognize anatomical structures in medical images automatically.…”

Section: Introductionmentioning

confidence: 99%

Development of screening patients with obstructive sleep apnea with deep learning in the lateral cephalogram: Overcoming modality differences with knowledge distillation

Kim

Jeong

Lee

et al. 2022

Preprint

Undetected obstructive sleep apnea (OSA) can lead to consequences of severe systematic disease. The lateral cephalogram in orthodontics is a valuable screening tool. We hypothesized that a deep learning-based classifier might be able to differentiate sleep apnea as anatomical features that humans do not recognize in lateral cephalogram. Moreover, since the imaging devices used by each hospital could be different, various modalities in radiography need to be overcome in real clinical practice. Therefore, we proposed a knowledge distillation deep learning model to classify patients into OSA and non-OSA groups using the lateral cephalogram and to overcome modality differences simultaneously. Lateral cephalograms of 500 OSA patients and 500 non-OSA patients from two different devices were included. ResNet-50 and ResNet-50 with a feature-based knowledge distillation model were trained and their suitability for classification and modality normalization were compared. Through knowledge distillation, it was confirmed through ROC analysis and Grad-CAM that our model exhibits high performance without being deceived by features caused by modality differences. By checking the probability values predicting OSA, an improvement in overcoming the modality differences in lateral cephalogram was observed, which could be applied in the actual clinical situation.