Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network
We propose a novel shape-aware relation network for accurate and real-time landmark detection in endoscopic submucosal dissection (ESD) surgery. This task is of great clinical significance but extremely challenging due to bleeding, lighting reflection, and motion blur in the complicated surgical environment.
This paper has been accepted by MEDIMA 2021. Get the full paper on Arxiv.
Fig. 1. Overview of our proposed shape-aware relation network for real-time landmark detection in ESD surgery.
- Network
- Pre-processing
- Training Codes
- Pretrained Weights
For more details or any questions, please feel easy to contact us by email ^_^
- Install the library of COCO and DCNv2.
Detailed parameters of our trained network will be uploaded soon !!!
- Pretrained Weights
- Inference Tools
- Data
If you find this work interesting or useful, please consider citing:
@article{WANG2021102291,
title = {Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network},
journal = {Medical Image Analysis},
pages = {102291},
year = {2021},
issn = {1361-8415},
doi = {https://doi.org/10.1016/j.media.2021.102291},
url = {https://www.sciencedirect.com/science/article/pii/S1361841521003364},
author = {Jiacheng Wang and Yueming Jin and Shuntian Cai and Hongzhi Xu and Pheng-Ann Heng and Jing Qin and Liansheng Wang}
}