Highlights As was shown in this paper, OSA screening can be based on facial anatomical landmarks identified in 3D scans. The authors of this paper believe that the amount of quality data necessary for the learning-based methods is too large and therefore see potential in the hybrid template and knowledge-based methods. We plan to use the MeshMonk toolbox in combination with a low-cost Kinect like 3D camera to scan pediatric patients. Automatically identified facial landmarks can not only automate an existing OSA screening protocol but can also help to find new facial features related to the OSA. The ultimate goal is to develop a relatively cheap device, possibly even mobile phone-based, to automatically screen pediatric patients for OSA. What are the main findings? OSA screening can be based on facial anatomical landmarks identified in 3D scans. Landmark detection based on hybrid templates and knowledge-based methods has significant potential. What is the implication of the main finding? Pediatric patients can be screened faster with higher precision. New facial features related to the OSA may be discovered. Abstract Obstructive Sleep Apnea (OSA) is a common disorder affecting both adults and children. It is characterized by repeated episodes of apnea (stopped breathing) and hypopnea (reduced breathing), which result in intermittent hypoxia. We recognize pediatric and adult OSA, and this paper focuses on pediatric OSA. While adults often suffer from daytime sleepiness, children are more likely to develop behavioral abnormalities. Early diagnosis and treatment are important to prevent negative effects on children’s development. Without the treatment, children may be at increased risk of developing high blood pressure or other heart problems. The gold standard for OSA diagnosis is the polysomnography (sleep study) PSG performed at a sleep center. Not only is it an expensive procedure, but it can also be very stressful, especially for children. Patients have to stay at the sleep center during the night. Therefore, screening tools are very important. Multiple studies have shown that OSA screening tools can be based on facial anatomical landmarks. Anatomical landmarks are landmarks located at specific anatomical locations. For the purpose of the screening tool, a specific list of anatomical locations needs to be identified. We are presenting a survey study of the automatic identification of these landmarks on 3D scans of the patient’s head. We are considering and comparing both knowledge-based and AI-based identification techniques, with a focus on the development of the automatic OSA screening tool.
【저자키워드】 deep learning, transfer learning, data augmentation, obstructive sleep apnea, 3D anatomical landmark detection, hybrid template and knowledge-based landmark detection,