Points of interest linear attention network for real‐time non‐rigid liver volume to surface registration
Medical Physics · 2024
DOI: 10.1002/mp.17108 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2024. Verfasst von Zeming Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, Changsha, Hunan, China. Hauptthemen laut MEDLINE: Liver, Neural Networks, Computer. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, High Caliber Foreign Experts Introduction Plan of MOST, Hunan Province Natural Science Foundation of China.
Abstract (Originalsprache)
Background
In laparoscopic liver surgery, accurately predicting the displacement of key intrahepatic anatomical structures is crucial for informing the doctor's intraoperative decision‐making. However, due to the constrained surgical perspective, only a partial surface of the liver is typically visible. Consequently, the utilization of non‐rigid volume to surface registration methods becomes essential. But traditional registration methods lack the necessary accuracy and cannot meet real‐time requirements.
Purpose
To achieve high‐precision liver registration with only partial surface information and estimate the displacement of internal liver tissues in real‐time.
Methods
We propose a novel neural network architecture tailored for real‐time non‐rigid liver volume to surface registration. The network utilizes a voxel‐based method, integrating sparse convolution with the newly proposed points of interest (POI) linear attention module. POI linear attention module specifically calculates attention on the previously extracted POI. Additionally, we identified the most suitable normalization method RMSINorm.
Results
We evaluated our proposed network and other networks on a dataset generated from real liver models and two real datasets. Our method achieves an average error of 4.23 mm and a mean frame rate of 65.4 fps in the generation dataset. It also achieves an average error of 8.29 mm in the human breathing motion dataset.
Conclusions
Our network outperforms CNN‐based networks and other attention networks in terms of accuracy and inference speed.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China.
- Hunan Engineering Research Center of Machine Vision and Intelligent Medicine, Changsha, Hunan, China.
- Ecole Centrale de Lyon, University of Lyon, Lyon, France.
Förderung
- National Natural Science Foundation of China
- High Caliber Foreign Experts Introduction Plan of MOST
- Hunan Province Natural Science Foundation of China
- Central South University Research Programme of Advanced Interdisciplinary Studies
- Major Program from Xiangjiang Laboratory under Grant
Zitieren
APA
Chen, Z., Zou, B., Kui, X., Shi, Y., Lv, D., & Chen, L. (2024). Points of interest linear attention network for real‐time non‐rigid liver volume to surface registration. Medical Physics. https://doi.org/10.1002/mp.17108
Vancouver
Chen Z, Zou B, Kui X, Shi Y, Lv D, Chen L. Points of interest linear attention network for real‐time non‐rigid liver volume to surface registration. Medical Physics. 2024. doi:10.1002/mp.17108
BibTeX
@article{Chen2024,
author = {Chen, Zeming and Zou, Beiji and Kui, Xiaoyan and Shi, Yangyang and Lv, Ding and Chen, Liming},
title = {Points of interest linear attention network for real‐time non‐rigid liver volume to surface registration},
journal = {Medical Physics},
year = {2024},
doi = {10.1002/mp.17108}
}
EUVIMED