A Fully Automated System for Sizing Nasal PAP Masks Using Facial Photographs
This addresses a practical issue for PAP mask users by automating mask sizing, though it appears incremental as it builds on existing facial detection methods.
The researchers tackled the problem of sizing nasal Positive Airway Pressure (PAP) masks by developing a fully automated system using facial photographs, achieving 64.71% accuracy in correct mask size selection and 86.1% accuracy within one size.
We present a fully automated system for sizing nasal Positive Airway Pressure (PAP) masks. The system is comprised of a mix of HOG object detectors as well as multiple convolutional neural network stages for facial landmark detection. The models were trained using samples from the publicly available PUT and MUCT datasets while transfer learning was also employed to improve the performance of the models on facial photographs of actual PAP mask users. The fully automated system demonstrated an overall accuracy of 64.71% in correctly selecting the appropriate mask size and 86.1% accuracy sizing within 1 mask size.