SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection
This work addresses medical image analysis for clinical applications, but appears incremental as it builds on existing CNN-based methods.
The authors tackled the problem of segmenting bones and detecting landmarks in CBCT/CT images, achieving results such as segmenting 2 bones and detecting 175 landmarks on a dataset of 170 images.
We propose a multi-stage coarse-to-fine CNN-based framework, called SkullEngine, for high-resolution segmentation and large-scale landmark detection through a collaborative, integrated, and scalable JSD model and three segmentation and landmark detection refinement models. We evaluated our framework on a clinical dataset consisting of 170 CBCT/CT images for the task of segmenting 2 bones (midface and mandible) and detecting 175 clinically common landmarks on bones, teeth, and soft tissues.