Three dimensional medical image diagnosis of lung, liver and brain using new artificial neural network

2016 Fiscal Year Final Research Report

• Project/Area Number: 26420421
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Control engineering/System engineering
• Research Institution: The University of Tokushima
• Principal Investigator: KONDO Tadashi 徳島大学, 大学院医歯薬学研究部(医学系), 教授 (80205559)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: ニューラルネットワーク / 医用画像診断

Outline of Final Research Achievements

In this study, the revised GMDH(Group Method of Data Handling)-type neural network algorithms using revised heuristic self-organization method and principal component-regression analysis, was developed and these algorithms were applied to the medical image recognitions of brain, lungs and heart and the medical image diagnosis of lung cancer. The revised GMDH-type neural network algorithms can automatically organize the artificial neural network architectures using the revised heuristic self-organization method, and these algorithms can automatically organize the optimum artificial neural network architectures fitting the complexity of many types of medical images such as X-ray CT image, MRI image and so on.

Free Research Field

工学