Title :
A neural network to diagnose liver cancer
Author :
Maclin, Philip S. ; Dempsey, Jack
Author_Institution :
Tennessee Univ., Memphis, TN, USA
Abstract :
A backpropagation neural network is designed to diagnose five classifications of hepatic masses: metastatic carcinoma, hepatoma (HCC), cavernous hemangioma, abscess, and cirrhosis. BrainMaker Professional version 2.5 software is used in this research. The input submitted to the network consists of 35 numbers per patient case, which represents ultrasonographic data and laboratory tests. The network architecture has 35 elements in the input layer, two hidden layers of 35 elements each, and five elements in the output layer. After being trained to a learning tolerance of 1%, the network classifies hepatic masses correctly in 51 of 72 cases. Continued research should provide a computerized second opinion that will be especially helpful to clinicians
Keywords :
backpropagation; learning (artificial intelligence); medical diagnostic computing; neural nets; BrainMaker Professional version 2.5; abscess; backpropagation; cavernous hemangioma; cirrhosis; hepatic masses; hepatoma; learning; liver cancer diagnosis; medical diagnostic computing; metastatic carcinoma; neural network; Abdomen; Artificial neural networks; Biological neural networks; Cancer; Laboratories; Liver; Magnetic resonance imaging; Metastasis; Neural networks; Testing;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298777
