基于深度学习的髋关节应力分布算法研究

刘远平; 宋昱锴; 张小燕; 刘贤强

doi:10.11959/j.issn.2096-6652.201934

您当前的位置：

首页 >

文章列表页 >

基于深度学习的髋关节应力分布算法研究

学术论文 | 更新时间：2024-06-05

- 基于深度学习的髋关节应力分布算法研究
- Research on hip joint stress distribution algorithms based on deep learning
- 智能科学与技术学报 2019年1卷第3期页码：260-268
- 作者机构：
- 作者简介：
  
  [ "刘远平（1996- ），男，广东韶关人，深圳大学计算机与软件学院本科生，主要研究方向为图像处理、数据挖掘等。" ]
  [ "宋昱锴（1996- ），男，四川自贡人，深圳大学计算机与软件学院硕士生，主要研究方向为图像处理。" ]
  [ "张小燕（1984- ），女，山东济宁人，博士，深圳大学计算机与软件学院讲师，主要研究方向为图像处理、多媒体内容分析等。" ]
  [ "刘贤强（1991- ），男，四川内江人，深圳大学计算机与软件学院硕士生，就职于奥瑞科技有限公司，主要研究方向为髋关节的生物力学。" ]
- 基金信息：
- DOI：10.11959/j.issn.2096-6652.201934
  中图分类号： TP301
- 网络出版日期：2019-09，
  
  纸质出版日期：2019-09-20
- 稿件说明：
移动端阅览
刘远平, 宋昱锴, 张小燕, 等. 基于深度学习的髋关节应力分布算法研究[J]. 智能科学与技术学报, 2019,1(3):260-268.

Yuanping LIU, Yukai SONG, Xiaoyan ZHANG, et al. Research on hip joint stress distribution algorithms based on deep learning[J]. Chinese journal of intelligent science and technology, 2019, 1(3): 260-268.
刘远平, 宋昱锴, 张小燕, 等. 基于深度学习的髋关节应力分布算法研究[J]. 智能科学与技术学报, 2019,1(3):260-268. DOI： 10.11959/j.issn.2096-6652.201934.

Yuanping LIU, Yukai SONG, Xiaoyan ZHANG, et al. Research on hip joint stress distribution algorithms based on deep learning[J]. Chinese journal of intelligent science and technology, 2019, 1(3): 260-268. DOI： 10.11959/j.issn.2096-6652.201934.

摘要

针对髋关节软骨的应力分布算法研究问题，设计了一个基于深度学习模型来代替有限元分析。该深度学习模型分为无监督学习模块和有监督学习模块，首先使用无监督学习模块对髋关节的软骨和股骨进行形状编码；之后实现对应力分布数据的编码与解码，使得应力数据能够与神经网络相结合；然后通过监督学习，利用编码好的应力数据进行监督，使神经网络学习得到一个从髋关节软骨和股骨的形状码到应力分布的应力码的映射关系；最终得到一个拟合的深度学习模型。此模型能够在一定程度上模拟有限元分析方法，但是由于其平均绝对误差和归一化平均绝对误差比较大，所以还不能完全替代有限元分析方法。在此基础上，进一步探索了新模型在特征利用上的局限，并提出了改进的方向。

Abstract

Aiming at the problem of the stress distribution algorithm of hip cartilage

a deep learning model to replace the finite element analysis (FEA) was proposed.This deep learning model was divided into unsupervised learning module and supervised learning module.Firstly

an unsupervised learning module was adopted to encode the shape of hip cartilage and femur.Then the coding and decoding of stress distribution implement was implemented so that stress data can be combined with the neural network.Next a supervised learning module supervised by the stress data was used

and the model uses neural networks to learn a mapping relationship from the shape code of the hip cartilage and femur to the stress code of the stress distribution.Finally

a fitted deep learning model was obtained.This deep learning model can simulate the FEA method to a certain extent.But the mean absolute error and the normalized mean absolute error are still larger than that of the FEA method

so the FEA method cannot be completely replaced by our deep learning model.Meanwhile

the limitations of the deep learning model in the use of input features were studied

and a direction to improve the performance of the model was proposed.

关键词

Keywords

references

AURICCHIO F , CONTI M , MORGANTI S , et al . Simulation of transcatheter aortic valve implantation:a patient-specific finite element approach [J ] . Computer Methods in Biomechanics and Biomedical Engineering , 2014 , 17 ( 12 ): 1347 - 1357 .

CAPELLI C , BOSI G M , CERRI E , et al . Patient-specific simulations of transcatheter aortic valve stent implantation [J ] . Medical ＆ Biological Engineering ＆ Computing , 2012 , 50 ( 2 ): 183 - 192 .

DWYER H A , MATTHEWS P B , AZADANI A N , et al . Migration forces of transcatheter aortic valves in patients with noncalcific aortic insufficiency [J ] . The Journal of Thoracic and Cardiovascular Surgery , 2009 , 138 ( 5 ): 1227 - 1233 .

MORGANTI S , CONTI M , AIELLO M , et al . Simulation of transcatheter aortic valve implantation through patient-specific finite element analysis:two clinical cases [J ] . Journal of Biomechanics , 2014 , 47 ( 11 ): 2547 - 2555 .

WANG Q , KODALI S , PRIMIANO C , et al . Simulations of transcatheter aortic valve implantation:implications for aortic root rupture [J ] . Biomechanics and Modeling in Mechanobiology , 2015 , 14 ( 1 ): 29 - 38 .

WANG Q , SIROIS E , SUN W , et al . Patient-specific modeling of biomechanical interaction in transcatheter aortic valve deployment [J ] . Journal of Biomechanics , 2012 , 45 ( 11 ): 1965 - 1971 .

MORGANTI S , BRAMBILLA N , PETRONIO A S , et al . Prediction of patient-specific post-operative outcomes of TAVI procedure:the impact of the positioning strategy on valve performance [J ] . Journal of Biomechanics , 2015 , 49 ( 12 ): 2513 - 2519 .

DE JAEGERE P , DE SANTIS G , RODRIGUEZOLIVARES R , et al . Patient-specific computer modeling to predict aortic regurgitation after transcatheter aortic valve replacement [J ] . Jacc-cardiovascular Interventions , 2016 , 9 ( 5 ): 508 - 512 .

SUN W , MARTIN C , PHAM T , et al . Computational modeling of cardiac valve function and intervention [J ] . Annual Review of Biomedical Engineering , 2014 , 16 ( 1 ): 53 - 76 .

LIANG L , LIU M , MARTIN C , et al . A machine learning approach to investigate the relationship between shape features and numerically predicted risk of ascending aortic aneurysm [J ] . Biomechanics ＆ Modeling in Mechanobiology , 2017 , 16 ( 5 ): 1 - 15 .

WANG Q , PRIMIANO C , MCKAY R G , et al . CT image-based engineering analysis of transcatheter aortic valve replacement [J ] . Jacc-cardiovascular Imaging , 2014 , 7 ( 5 ): 526 - 528 .

BUENO-PALOMEQUE F L , CORTÉS-RODRÍGUEZ C J , GARCÍASARMIENTO C D , et al . A comparative case study of the pre and post operative stress distribution in a dysplastic hip joint [C ] // Proceedings of the 11th International Symposium,Computer Methods in Biomechanics and Biomedical Engineering,April 3 - 7,2013,Salt Lake City,Utah,USA.[S.l.:s.n] . 2013

HELLWIG F L , TONG J , HUSSELL J G . Hip joint degeneration due to cam impingement:a finite element analysis [J ] . Computer Methods in Biomechanics ＆ Biomedical Engineering , 2016 , 19 ( 1 ): 41 - 48 .

王正军 , 孙立明 . ANSYS 18.0有限元分析基础与实例教程 [M ] . 北京 : 机械工业出版社 , 2018 .

WANG Z J , SUN L M.ANSYS 18 . 0 finite element analysis basics and examples tutorial [M ] . Beijing : China Machine PressPress , 2018 .

ZAMEER S , MOHAMMED M A H . Evaluation of contact stress distribution of hip joint model using finite element method [J ] . Esrsa Publications , 2014 , 3 ( 6 ): 1603 - 1610 .

LIANG L , LIU M , MARTIN C , et al . A deep learning approach to estimate stress distribution:a fast and accurate surrogate of finite-element analysis [J ] . Journal of the Royal Society Interface , 2018 , 15 ( 138 ).

HEIMANN T , MEINZER H . Statistical shape models for 3D medical image segmentation:a review [J ] . Medical Image Analysis , 2009 , 13 ( 4 ): 543 - 563 .

DUGAS C , BENGIO Y , BELISLE F , et al . Incorporating second-order functional knowledge for better option pricing [C ] // Neural Information Processing Systems,November 27-December 2,2000,Denver,USA . Boston:MIT Press , 2000 : 472 - 478 .

张钹 . 人工智能进入后深度学习时代 [J ] . 智能科学与技术学报 , 2019 , 1 ( 1 ): 4 - 6 .

ZHANG B . Artificial intelligence is entering the post deep-learning era [J ] . Chinese Journal of Intelligent Science and Technology , 2019 , 1 ( 1 ): 4 - 6 .

郑南宁 . 人工智能新时代 [J ] . 智能科学与技术学报 , 2019 , 1 ( 1 ): 1 - 3 .

ZHENG N N . The new era of artificial intelligence [J ] . Chinese Journal of Intelligent Science and Technology , 2019 , 1 ( 1 ): 1 - 3 .

浏览量

754

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Cerberus：基于深度学习的跨网站社交机器人检测系统

基于视觉的列车轨道缺陷检测综述

动态环境下基于语义信息与几何约束的视觉SLAM系统

融合音画同步的唇形合成研究

基于深度学习的MRI脑卒中病灶分割方法综述