Generate Navigations to Guide and Automate Nasotracheal Intubation Process

Nasotracheal Intubation is a complex medical procedure in which a ventilating tube is inserted into the human trachea (windpipe) through the nose. Improper positioning carries potentially fatal consequences and therefore confirmation of correct positioning is mandatory. To overcome the consequences1, this research propose a system to guide and automate Nasotracheal Intubation by providing the physician with necessary directions to move the intubation tube. This study is a proof of concept to prove that generating directions using a trained model has practical potential. In the proposed system, different anatomical landmarks along the path from nose to carina are identified, captured images are preprocessed and use a Convolutional Neural Network based on image classification to predict the class of each anatomical landmark. The proposed system has been trained using the training dataset of 9753 images and the performance of the system evaluated using the testing dataset of 2438 images. The results, obtained using the pre-trained model, show that the system correctly classified 2385 out of 2438 (97.8%). The outcome of this research has been a successful enhancement in correct positioning of the intubation tube with the generation of navigation details of Nasotracheal Intubation process and has established for further improvements.