SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection

Qin Liu; Han Deng; Chunfeng Lian; Xiaoyang Chen; Deqiang Xiao; Lei Ma; Xu Chen; Tianshu Kuang; Jaime Gateno; Pew-Thian Yap; James J. Xia

SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection

Image and Video Processing 2021-12-22 v2 Computer Vision and Pattern Recognition

Authors: Qin Liu , Han Deng , Chunfeng Lian , Xiaoyang Chen , Deqiang Xiao , Lei Ma , Xu Chen , Tianshu Kuang , Jaime Gateno , Pew-Thian Yap , James J. Xia

View on arXiv ↗ PDF ↗

Abstract

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.

Keywords

deep learning segmentation medical image segmentation cancer detection and segmentation

Cite

@article{arxiv.2110.03828,
  title  = {SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection},
  author = {Qin Liu and Han Deng and Chunfeng Lian and Xiaoyang Chen and Deqiang Xiao and Lei Ma and Xu Chen and Tianshu Kuang and Jaime Gateno and Pew-Thian Yap and James J. Xia},
  journal= {arXiv preprint arXiv:2110.03828},
  year   = {2021}
}

Comments

10 pages, 5 figures, accepted by MLMI 2021

SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection

Abstract

Keywords

Cite

Comments

Related papers