Deep Feedback GMDH-Type Neural Network Using Principal Component-Regression Analysis and Its Application to Medical Image Recognition of Abdominal Multi-Organs

被引：4
|
作者：
Kondo, Tadashi [1 ]
Ueno, Junji [1 ]
Takao, Shoichiro [1 ]
机构：
[1] Univ Tokushima, Grad Sch Hlth Sci, 3-18-15 Kuramoto Cho, Tokushima 7708509, Japan
来源：
JOURNAL OF ROBOTICS NETWORKING AND ARTIFICIAL LIFE | 2015年 / 2卷 / 02期
关键词：
Deep neural networks; GMDH; Medical image recognition; Evolutionary computation;
D O I：
10.2991/jrnal.2015.2.2.6
中图分类号：
TP24 [机器人技术];
学科分类号：
080202 ; 1405 ;
摘要：
The deep feedback Group Method of Data Handling (GMDH)-type neural network is proposed and applied to the medical image recognition of abdominal organs such as the liver and spleen. In this algorithm, the principal component-regression analysis is used for the learning calculation of the neural network, and the accurate and stable predicted values are obtained. The neural network architecture is automatically organized so as to fit the complexity of the medical images using the prediction error criterion defined as Akaike's Information Criterion (AIC) or Prediction Sum of Squares (PSS). The recognition results show that the deep feedback GMDH-type neural network algorithm is useful for the medical image recognition of abdominal organs.
引用
收藏
页码：94 / 99
页数：6
相关论文
共 49 条
  • [21] 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
  • [22] 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
  • [23] 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
  • [24] 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
  • [25] Medical image analysis of abdominal X-ray CT images by deep multilayered GMDH-type neural network
    Takao, Shoichiro
    Kondo, Sayaka
    Ueno, Junji
    Kondo, Tadashi
    ARTIFICIAL LIFE AND ROBOTICS, 2018, 23 (02) : 271 - 278
  • [26] Medical image recognition of abdominal X-ray CT images by RBF GMDH-type neural network
    Kondo, Tadashi
    Ueno, Junji
    PROCEEDINGS OF SICE ANNUAL CONFERENCE, VOLS 1-8, 2007, : 1108 - 1112
  • [27] Medical image diagnosis of liver cancer by feedback GMDH-type neural network using knowledge base
    Kondo, Tadashi
    Ueno, Junji
    Takao, Shoichiro
    ARTIFICIAL LIFE AND ROBOTICS, 2013, 17 (3-4) : 488 - 494
  • [28] Medical image diagnosis of liver cancer by feedback GMDH-type neural network using knowledge base
    Kondo, Tadashi
    Ueno, Junji
    Takao, Shoichiro
    PROCEEDINGS OF THE SEVENTEENTH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL LIFE AND ROBOTICS (AROB 17TH '12), 2012, : 1021 - 1024
  • [29] 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
  • [30] The 3-dimensional medical image recognition of right and left kidneys by deep GMDH-type neural network
    20162002389167
    (1) Graduate School of Health Sciences, Tokushima University, 3-18-15 Kuramoto-cho, Tokushima; 770-8509, Japan, 1600, ASCS Publications; IEEE; IEEE Computer Society; IEEJ; Orion (Institute of Electrical and Electronics Engineers Inc., United States):
12345