A method for constructing real-time FEM-based simulator of stomach behavior with large-scale deformation by neural networks

Kenichi Morooka, Tomoyuki Taguchi, Xian Chen, Ryo Kurazume, Makoto Hashizume, Tsutomu Hasegawa

研究成果: 著書/レポートタイプへの貢献会議での発言

3 引用 (Scopus)

抄録

This paper presents a method for simulating the behavior of stomach with large-scale deformation. This simulator is generated by the real-time FEM-based analysis by using a neural network. There are various deformation patterns of hollow organs by changing both its shape and volume. In this case, one network can not learn the stomach deformation with a huge number of its deformation pattern. To overcome the problem, we propose a method of constructing the simulator composed of multiple neural networks by 1)partitioning a training dataset into several subsets, and 2)selecting the data included in each subset. From our experimental results, we can conclude that our method can speed up the training process of a neural network while keeping acceptable accuracy.

元の言語英語
ホスト出版物のタイトルMedical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling
8316
DOI
出版物ステータス出版済み - 2012
イベントMedical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling - San Diego, CA, 米国
継続期間: 2 5 20122 7 2012

その他

その他Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling
米国
San Diego, CA
期間2/5/122/7/12

Fingerprint

stomach
simulators
Stomach
Simulators
Neural networks
Finite element method
set theory
education
organs
hollow

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

これを引用

Morooka, K., Taguchi, T., Chen, X., Kurazume, R., Hashizume, M., & Hasegawa, T. (2012). A method for constructing real-time FEM-based simulator of stomach behavior with large-scale deformation by neural networks. : Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling (巻 8316). [83160J] https://doi.org/10.1117/12.911171

A method for constructing real-time FEM-based simulator of stomach behavior with large-scale deformation by neural networks. / Morooka, Kenichi; Taguchi, Tomoyuki; Chen, Xian; Kurazume, Ryo; Hashizume, Makoto; Hasegawa, Tsutomu.

Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling. 巻 8316 2012. 83160J.

研究成果: 著書/レポートタイプへの貢献会議での発言

Morooka, K, Taguchi, T, Chen, X, Kurazume, R, Hashizume, M & Hasegawa, T 2012, A method for constructing real-time FEM-based simulator of stomach behavior with large-scale deformation by neural networks. : Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling. 巻. 8316, 83160J, Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling, San Diego, CA, 米国, 2/5/12. https://doi.org/10.1117/12.911171
Morooka K, Taguchi T, Chen X, Kurazume R, Hashizume M, Hasegawa T. A method for constructing real-time FEM-based simulator of stomach behavior with large-scale deformation by neural networks. : Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling. 巻 8316. 2012. 83160J https://doi.org/10.1117/12.911171
Morooka, Kenichi ; Taguchi, Tomoyuki ; Chen, Xian ; Kurazume, Ryo ; Hashizume, Makoto ; Hasegawa, Tsutomu. / A method for constructing real-time FEM-based simulator of stomach behavior with large-scale deformation by neural networks. Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling. 巻 8316 2012.
@inproceedings{4449f8b1b3cc40eaac4ccaa8d9a2ecae,
title = "A method for constructing real-time FEM-based simulator of stomach behavior with large-scale deformation by neural networks",
abstract = "This paper presents a method for simulating the behavior of stomach with large-scale deformation. This simulator is generated by the real-time FEM-based analysis by using a neural network. There are various deformation patterns of hollow organs by changing both its shape and volume. In this case, one network can not learn the stomach deformation with a huge number of its deformation pattern. To overcome the problem, we propose a method of constructing the simulator composed of multiple neural networks by 1)partitioning a training dataset into several subsets, and 2)selecting the data included in each subset. From our experimental results, we can conclude that our method can speed up the training process of a neural network while keeping acceptable accuracy.",
author = "Kenichi Morooka and Tomoyuki Taguchi and Xian Chen and Ryo Kurazume and Makoto Hashizume and Tsutomu Hasegawa",
year = "2012",
doi = "10.1117/12.911171",
language = "English",
isbn = "9780819489654",
volume = "8316",
booktitle = "Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling",

}

TY - GEN

T1 - A method for constructing real-time FEM-based simulator of stomach behavior with large-scale deformation by neural networks

AU - Morooka, Kenichi

AU - Taguchi, Tomoyuki

AU - Chen, Xian

AU - Kurazume, Ryo

AU - Hashizume, Makoto

AU - Hasegawa, Tsutomu

PY - 2012

Y1 - 2012

N2 - This paper presents a method for simulating the behavior of stomach with large-scale deformation. This simulator is generated by the real-time FEM-based analysis by using a neural network. There are various deformation patterns of hollow organs by changing both its shape and volume. In this case, one network can not learn the stomach deformation with a huge number of its deformation pattern. To overcome the problem, we propose a method of constructing the simulator composed of multiple neural networks by 1)partitioning a training dataset into several subsets, and 2)selecting the data included in each subset. From our experimental results, we can conclude that our method can speed up the training process of a neural network while keeping acceptable accuracy.

AB - This paper presents a method for simulating the behavior of stomach with large-scale deformation. This simulator is generated by the real-time FEM-based analysis by using a neural network. There are various deformation patterns of hollow organs by changing both its shape and volume. In this case, one network can not learn the stomach deformation with a huge number of its deformation pattern. To overcome the problem, we propose a method of constructing the simulator composed of multiple neural networks by 1)partitioning a training dataset into several subsets, and 2)selecting the data included in each subset. From our experimental results, we can conclude that our method can speed up the training process of a neural network while keeping acceptable accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84860257874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860257874&partnerID=8YFLogxK

U2 - 10.1117/12.911171

DO - 10.1117/12.911171

M3 - Conference contribution

AN - SCOPUS:84860257874

SN - 9780819489654

VL - 8316

BT - Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling

ER -