Upper Airway Detection in Cone Beam Images

This paper describes a method developed to assist in the detection and reconstruction of the human upper airway using cone beam computed tomography (CBCT) image slices and a three dimensional (3D) Gaussian kernel blurring filter. The segmented airway is characterized by the corresponding three principal axes that are selected for viewing direction orientation via rotation and translation. The aforementioned axes are derived using the 3D Principal Component Analysis (PCA) result of the volume cross-sections. To finely adjust the view and airway, the major and minor axes of each slice are also computed using the two dimensional (2D) PCA in the respective planes. The extracted upper airway provides image bio-marking in the diagnostic assessment of patients with upper airway respiratory conditions such as obstructive sleep apnea, allergic rhinitis, and other related diseases as well as in planning of orthopedic/orthodontic therapies.