Title :
Hybrid GMDH-type neural network using artificial intelligence and its application to medical image diagnosis of liver cancer
Author :
Kondo, Tadashi ; Ueno, Junji ; Takao, Shoichiro
Author_Institution :
Grad. Sch. of Health Sci., Univ. of Tokushima, Tokushima, Japan
Abstract :
A hybrid Group Method of Data Handling (GMDH)-type neural network algorithm using artificial intelligence technology for medical image diagnosis is proposed and is applied to medical image diagnosis of the liver cancer. In this algorithm, the knowledge base for medical image diagnosis is used for organizing the neural network architecture for medical image diagnosis. Furthermore, the revised GMDH-type neural network algorithm has a feedback loop and can identify the characteristics of the medical images accurately using feedback loop calculations. The optimum neural network architecture fitting the complexity of the medical images is automatically organized so as to minimize the prediction error criterion defined as Akaike´s information criterion (AIC) or Prediction Sum of Squares (PSS). It is shown that the hybrid GMDH-type neural network is accurate and a useful method for the medical image diagnosis of the liver cancer.
Keywords :
artificial intelligence; cancer; data handling; liver; medical image processing; neural nets; Akaike information criterion; artificial intelligence technology; feedback loop; hybrid GMDH-type neural network algorithm; hybrid group method of data handling; liver cancer diagnosis; medical image diagnosis; neural network architecture; optimum neural network architecture; prediction error criterion; prediction sum of squares; Biological neural networks; Cancer; Input variables; Liver; Medical diagnostic imaging; Neurons; Artificial intelligence; CAD; GMDH; Medical image; Neural network;
Conference_Titel :
System Integration (SII), 2011 IEEE/SICE International Symposium on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4577-1523-5
DOI :
10.1109/SII.2011.6147603