Automated location of orofacial landmarks to characterize airway morphology in anaesthesia via deep convolutional neural networks

García-García, Fernando; Lee, Dae‐Jin; Mendoza-Garcés, Francisco J.; Irigoyen-Miró, Sofía; Legarreta, María José; García-Gutiérrez, Susana; Aróstegui, Inmaculada

doi:10.1016/j.cmpb.2023.107428

Cited by 3 publications

(15 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With this idea in mind, here we advocated for the three-staged approach outlined in Section 1.3. Whereas stage (A) was tackled in our previous work [32], (B) & (C) are novel contributions of the current article.…”

Section: Previous Work and Noveltymentioning

confidence: 96%

“…In a previous work [32], we proposed and validated DCNNs for the task of locating 2D orofacial landmarks in preoperative photographs: 27 frontal + 13 lateral. The system achieved satisfactory results in identifying the relative 2D coordinates of the landmarks within the image; with robust generalization and expert-like performance for the frontal view, and with a moderate degradation in the lateral view, consistent with comparable works like Cuendet et al [30].…”

Section: Previous Work and Noveltymentioning

confidence: 99%

“…• A first subgroup of 317 cases, also employed for the development of our landmarks DCNN [32]. However, one male patient had to be excluded due to missing information about his intubation manoeuvre(s).…”

Section: Cohortmentioning

confidence: 99%

“…In [32], we developed a DCNN to automatically locate orofacial landmarks in preoperative photographs. The 27 frontal and 13 lateral salient points were defined ad hoc by our anaesthesiologists to describe relevant anatomical items of the otolaryngeal structure: nose, lips, teeth, tongue, chin, mandible, neck, thyroid cartilage, sternal manubrium, nape, occiput (Figure 1a).…”

Section: Characterizing Airway Morphology 221 Previous Workmentioning

confidence: 99%

“…Thus, here we propose a method to obtain the corresponding 3D world coordinates. We tackle this 2D-to-3D coordinate transformation task as a camera pose estimation problem [37] (which is common in fields vi (a) Orofacial landmarks to characterize airway morphology in the context of anaesthesia -Diagram taken from our previous work [32].…”

Section: Novel Contributionmentioning

confidence: 99%

See 4 more Smart Citations

Reliable prediction of difficult airway for tracheal intubation from patient preoperative photographs by machine learning methods

García-García,

Lee,

Mendoza-Garcés

et al. 2024

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

Section: Previous Work and Noveltymentioning

confidence: 96%

Section: Previous Work and Noveltymentioning

confidence: 99%

Section: Cohortmentioning

confidence: 99%

Section: Characterizing Airway Morphology 221 Previous Workmentioning

confidence: 99%

Section: Novel Contributionmentioning

confidence: 99%

See 3 more Smart Citations

Reliable prediction of difficult airway for tracheal intubation from patient preoperative photographs by machine learning methods

García-García,

Lee,

Mendoza-Garcés

et al. 2024

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

Increasing Robustness of Intracortical Brain-Computer Interfaces for Recording Condition Changes via Data Augmentation

Yang,

Huang,

Huang

2024

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

A Survey Study of the 3D Facial Landmark Detection Techniques Used as a Screening Tool for Diagnosis of the Obstructive Sleep Apnea Syndrome

Hornák,

Duchoň

2024

ARM

View full text Add to dashboard Cite

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.

show abstract

Automated location of orofacial landmarks to characterize airway morphology in anaesthesia via deep convolutional neural networks

Cited by 3 publications

References 72 publications

Reliable prediction of difficult airway for tracheal intubation from patient preoperative photographs by machine learning methods

Reliable prediction of difficult airway for tracheal intubation from patient preoperative photographs by machine learning methods

Increasing Robustness of Intracortical Brain-Computer Interfaces for Recording Condition Changes via Data Augmentation

A Survey Study of the 3D Facial Landmark Detection Techniques Used as a Screening Tool for Diagnosis of the Obstructive Sleep Apnea Syndrome

Contact Info

Product

Resources

About