Automatic Cephalometric landmark detection

Landmark identification is crucial in quantifying cephalometric analysis such as Steiner, Bjork, Ricketts, Kim, Nagasaki, etc. For applying these analysis to cephalometric image, dentist or orthodontist need to annotate some group of landmarks that corresponding to specified analysis. Manual annotation of landmarks is a tedious, laborious task and prone to human errors. Therefore, it’s necessary that they need an efficient automated application for landmark identification.
In this project, we developed an online efficient AI driven tools for automatically detecting landmark on Cephalometry image. The core part of these tools is our developed deep learning model with backbone DenseNet121. This model was trained on both public dataset of Cephalometric image ISBI 2015 and private dataset.
These tools currently has been integrated with other advanced technology tools in Viceph - an online AI driven application for orthodontist.