Chem. J. Chinese Universities ›› 1994, Vol. 15 ›› Issue (7): 982.

• Articles • Previous Articles     Next Articles

Classification of Human Senile Cataract Lenses Based on Metal Contents Using Neural Networks

CAI Shu-An1, XU Lu2, YANG Yi-Qiu2, HU Chang-Yu2, P. C. Jors3, J. W. Ball3, S. L. Dixon3   

  1. 1. The First Clinical College, Norman Bethune University of Medical Sciences;
    2. Changchun Institute of Applied Chemistry, Academia Sinica, Changchun, 130022;
    3. Department of Chemistry, The Pennsylvania State University, USA
  • Received:1993-08-21 Revised:1994-04-22 Online:1994-07-24 Published:1994-07-24

Abstract: Senile cataract lenses.nuclei from cataract lenses, and normal lenses were successfully separated into three classes using quasi-Newton neural networks. Tlie lenses were classified based on the concentrations of K, Na, Ca, Mg, Cu, Fe, Zn and Mn measured by atomic absorption spectroscopy.The 30 cataract lenses used in this study were randomly divided into a 23 member training set and 7 member test set.The architecture including the number of layers, the number of neurons in each layer, and the initial weights were varied in order to study their effects on the performance of the neural network.Once trained, the neural network correctly classified all 30 cataract lenses.

Key words: Neural network, Human senile cataract, Trace metal elements

TrendMD: