• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2017 Fiscal Year Final Research Report

Medical image analysis of abdominal X-ray CT images by hybrid deep neural network of deep logistic GMDH-type neural network and convolutional neural network

Research Project

  • PDF
Project/Area Number 15K06145
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Control engineering/System engineering
Research InstitutionThe University of Tokushima

Principal Investigator

UENO Junji  徳島大学, 大学院医歯薬学研究部(医学系), 教授 (60116788)

Co-Investigator(Kenkyū-buntansha) 近藤 正  徳島大学, 大学院医歯薬学研究部(医学系), 名誉教授 (80205559)
Project Period (FY) 2015-04-01 – 2018-03-31
Keywordsニューラルネットワーク / GMDH / MDCT / 医用画像診断 / CAD
Outline of Final Research Achievements

We proposed the hybrid artificial neural network algorisms of the convolutional neural network (CNN) and the deep GMDH-type neural networks. The deep GMDH-type neural networks can automatically organize the deep neural network architectures which have many hidden layers. These hybrid artificial neural network algorisms were applied to the medical image diagnosis of the liver cancer and the medical image recognitions of the abdominal organs such as spleen. The recognition results were compared with those of the conventional sigmoid function type neural network using the backpropagation algorithm as the learning calculations. It was shown that these proposed algorithms were useful for the medical image recognitions and the medical image diagnosis of the abdominal organs.

Free Research Field

放射線診断学

URL: 

Published: 2019-03-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi