Localization of Craniomaxillofacial Landmarks on CBCT Images Using 3D Mask R-CNN and Local Dependency Learning

Abstract

Cephalometric analysis relies on accurate detection of craniomaxillofacial (CMF) landmarks from cone-beam computed tomography (CBCT) images. However, due to the complexity of CMF bony structures, it is difficult to localize landmarks efficiently and accurately. In this paper, we propose a deep learning framework to tackle this challenge by jointly digitalizing 105 CMF landmarks on CBCT images. By explicitly learning the local geometrical relationships between the landmarks, our approach extends Mask R-CNN for end-to-end prediction of landmark locations. Specifically, we first apply a detection network on a down-sampled 3D image to leverage global contextual information to predict the approximate locations of the landmarks. We subsequently leverage local information provided by higher-resolution image patches to refine the landmark locations. On patients with varying non-syndromic jaw deformities, our method achieves an average detection accuracy of 1.38± 0.95mm, outperforming a related state-of-the-art method.

Fig. 1:

Our coarse-to-fine framework for CMF landmark localization in CBCT images.

Fig. 2:

Our workflow for CMF landmark detection, illustrated for detecting four landmarks in two anatomical regions. The Multi-RPN generates several location proposals with anatomical region labels (illustrated by two different colors), which are processed by NMS. Then, a recognition network detects each landmark from the proposals in the form of a regressed bounding box and a corresponding landmark label (illustrated by four different colors). Finally, NMS post-processing is applied to further filter out redundant bounding boxes.

Fig. 3:

Architecture of the proposed Mask R-CNN for detecting landmarks.

Fig. 4:

Predefined anatomical landmark regions with landmarks in the same anatomical region marked with the same colors.

Fig. 5:

Example landmark localization results.

Fig. 6:

Landmark localization for four patients with slight deformity (left), severe deformity (middle), and defects (right).

Fig. 7:

Detection errors for bounding boxes of different sizes.