Diagnosis of Hepatocellular Carcinoma Spectroscopy Based on the Feature Selection Approach of the Genetic Algorithm

Shao-qing Wang (Shandong Medical Imaging Research Institute, Shandong Jinan)
Qiang Liu (Shandong Medical Imaging Research Institute, Shandong Jinan)
Dong-yue Yu (Shandong Zibo Prison Hospital)
Guang-ju Liang (Shandong Province XinTai City People's Hospital)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 11, No 6: June 2013

This paper aims to study the application of medical imaging technology with artificial intelligence technology on how to improve the diagnostic accuracy rate for hepatocellular carcinoma. The   recognition method based on genetic algorithm (GA) and Neural Network are presented. GA was used to select 20 optimal features from the 401 initial features. BP (Back-propagation Neural Network, BP) and PNN (Probabilistic Neural Network, PNN) were used to classify tested samples based on these optimized features, and make comparison between results based on 20 optimal features and the all 401 features. The results of the experiment show that the method can improve the recognition rate. DOI: http://dx.doi.org/10.11591/telkomnika.v11i6.2663