Medical image diagnosis of liver cancer by hybrid feedback GMDH-type neural network using principal component-regression analysis
| Autor: | Junji Ueno, Tadashi Kondo, Shoichiro Takao |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Quantitative Biology::Neurons and Cognition
Artificial neural network Time delay neural network business.industry Computer science Group method of data handling Physics::Medical Physics Computer Science::Neural and Evolutionary Computation Explained sum of squares Pattern recognition Feedback loop General Biochemistry Genetics and Molecular Biology Probabilistic neural network ComputingMethodologies_PATTERNRECOGNITION Artificial Intelligence Principal component regression Artificial intelligence Akaike information criterion business |
| Zdroj: | Artificial Life and Robotics. 20:145-151 |
| ISSN: | 1614-7456 1433-5298 |
| DOI: | 10.1007/s10015-015-0213-1 |
| Popis: | The hybrid feedback group method of data handling (GMDH)-type neural network is proposed and applied to the medical image diagnosis of liver cancer. 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. Furthermore, this neural network has the feedback loop and the complexity of neural network architecture is increased using the feedback loop calculations. The neural network architecture is automatically organized so as to fit the complexity of the nonlinear system using the prediction error criterion defined as Akaike's information criterion (AIC) or prediction sum of squares (PSS). The recognition results show that the hybrid feedback GMDH-type neural network algorithm is useful for the medical image diagnosis of liver cancer since the optimum neural network architecture is automatically organized. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink