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

•Proposed two ad-hoc deep learning networks to locate orofacial landmarks for anaesthesia from preoperative photos.•Trained by successive transfer learning stages, and with data augmentation techniques.•Compared to the consensus between manual annotations by two independent anaesthesiologists, as gr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computer methods and programs in biomedicine 2023-04, Vol.232, p.107428-107428, Article 107428
Hauptverfasser:	García-García, Fernando, Lee, Dae-Jin, Mendoza-Garcés, Francisco J., Irigoyen-Miró, Sofía, Legarreta-Olabarrieta, María J., García-Gutiérrez, Susana, Arostegui, Inmaculada
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Anaesthesia Anesthesia, General Deep learning Difficult airway Facial landmarks Female Humans Male Neural Networks, Computer Transfer learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!