EUVIMEDOpdag EUVIMED
Crossref

Points of interest linear attention network for real‐time non‐rigid liver volume to surface registration

Zeming Chen, Beiji Zou, Xiaoyan Kui, Yangyang Shi, Ding Lv, Liming Chen

Medical Physics · 2024

DOI: 10.1002/mp.17108 ↗

At a glance

Journal article in Medical Physics, 2024. Written by Zeming Chen and 5 co-authors. Institution: School of Computer Science and Engineering, Central South University, Changsha, Hunan, China. Major MEDLINE topics: Liver, Neural Networks, Computer. Cited 1 times so far (Crossref); 34 references. Funded by: National Natural Science Foundation of China, High Caliber Foreign Experts Introduction Plan of MOST, Hunan Province Natural Science Foundation of China.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

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.

Subjects

MeSH terms (MEDLINE)

LiverNeural Networks, ComputerHumansImage Processing, Computer-AssistedTime FactorsOrgan SizeTomography, X-Ray ComputedImaging, Three-Dimensional

Author keywords

attention networkdeep learningdeformation estimationnon‐rigid registration

Authors and institutions

  • 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.

Funding

  • 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

Cite

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}
}
Start for free →