The 3-dimensional medical image recognition of right and left kidneys by deep GMDH-type neural network

被引：0
|
作者：
20162002389167
机构：
来源：
(1) Graduate School of Health Sciences, Tokushima University, 3-18-15 Kuramoto-cho, Tokushima; 770-8509, Japan | 1600年 / ASCS Publications; IEEE; IEEE Computer Society; IEEJ; Orion卷 / Institute of Electrical and Electronics Engineers Inc., United States期
关键词：
In this study; the deep multi-layered Group Method of Data Handling (GMDH)-type neural network algorithm using principal component-regression analysis is applied to recognition problems of the right and left kidney regions. The deep multi-layered GMDH-type neural network algorithm can automatically organize the deep neural network architectures which have many hidden layers and these deep neural networks can identify the characteristics of very complex nonlinear systems. The architecture of the deep neural network with many hidden layers is automatically organized using the heuristic self-organization method; so as to minimize the prediction error criterion defined as Akaike's information criterion (AIC) or Prediction Sum of Squares (PSS). The heuristic self-organization method is a type of the evolutional computation. In this deep GMDH-type neural network; principal component-regression analysis is used as the learning algorithm of the weights in the deep GMDH-type neural network; and multi-colinearity does not occur and stable and accurate prediction values are obtained. This new algorithm is applied to the medical image recognitions of the right and left kidney regions. The optimum neural network architectures; which fit the complexity of the right and left kidney regions; are automatically organized and the right and left kidney regions are automatically recognized and extracted by the organized deep GMDH-type neural networks. The recognition results are compared with the conventional sigmoid function neural network trained using back propagation method and it is shown that this deep GMDH-type neural networks are useful for the medical image recognition problems of the right and left kidney regions. © 2015 IEEE;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
121117
引用
收藏
相关论文
共 50 条
  • [1] The 3-Dimensional Medical Image Recognition of Right and Left Kidneys by Deep GMDH-type Neural Network
    Kondo, Tadashi
    Ueno, Junji
    Takao, Shoichiro
    2015 INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATICS AND BIOMEDICAL SCIENCES (ICIIBMS), 2015, : 313 - 320
  • [2] Feedback GMDH-type neural network using prediction error criterion and its application to 3-dimensional medical image recognition
    Kondo, Tadashi
    2008 PROCEEDINGS OF SICE ANNUAL CONFERENCE, VOLS 1-7, 2008, : 1014 - 1019
  • [3] Multilayered GMDH-Type Neural Network with Radial Basis Functions and its Application to 3-Dimensional Medical Image Recognition of the Liver
    Kondo, Tadashi
    Ueno, Junji
    Pandya, Abhijit S.
    JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2007, 11 (01) : 96 - 104
  • [4] Three dimensional medical image recognition of lungs by revised GMDH-type neural network algorithm
    Kondo, Tadashi
    Ueno, Junji
    INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2006, 1 : 364 - 366
  • [5] Medical Image Diagnosis of Lung Cancer by Deep Feedback GMDH-Type Neural Network
    Kondo, Tadashi
    Ueno, Junji
    Takao, Shoichiro
    PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON ARTIFICIAL LIFE AND ROBOTICS (ICAROB 2016), 2016, : 125 - 129
  • [6] Medical Image Diagnosis of Lung Cancer by Deep Feedback GMDH-Type Neural Network
    Kondo, Tadashi
    Ueno, Junji
    Takao, Shoichiro
    JOURNAL OF ROBOTICS NETWORKING AND ARTIFICIAL LIFE, 2016, 2 (04): : 252 - 257
  • [7] Medical image recognition by using logistic GMDH-type neural networks
    Kondo, T
    Pandya, AS
    SICE 2001: PROCEEDINGS OF THE 40TH SICE ANNUAL CONFERENCE, INTERNATIONAL SESSION PAPERS, 2001, : 259 - 264
  • [8] MEDICAL IMAGE RECOGNITION OF ABDOMINAL MULTI-ORGANS BY RBF GMDH-TYPE NEURAL NETWORK
    Kondo, Tadashi
    Ueno, Junji
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2009, 5 (01): : 225 - 240
  • [9] Medical image recognition of the brain by revised GMDH-type neural network algorithm with a feedback loop
    Kondo, Tadashi
    Ueno, Junji
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2006, 2 (05): : 1039 - 1052
  • [10] Multi-layered GMDH-type neural network self-selecting optimum neural network architecture and its application to 3-dimensional medical image recognition of blood vessels
    Kondo, Tadashi
    Ueno, Junji
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2008, 4 (01): : 175 - 187
12345