International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 57 - Number 5 |
Year of Publication: 2012 |
Authors: Sonia Narang, Harsh K Verma, Uday Sachdev |
10.5120/9109-3261 |
Sonia Narang, Harsh K Verma, Uday Sachdev . Breast Cancer Detection using ART2 Model of Neural Networks. International Journal of Computer Applications. 57, 5 ( November 2012), 10-14. DOI=10.5120/9109-3261
Breast cancer has become a major cause of death among women . To reduce breast cancer deaths the most effective way is to detect it earlier. Early diagnosis requires correct and reliable diagnosis procedure that will allows physicians to distinguish benign breast tumors from malignant ones. So, to find an accurate and effective diagnosis method is very important. This paper presents a system which detects the cancer stage using Adaptive Resonance theory (ART2) Neural Network . A vigilance parameter (vp) in ARN2 defines the stopping criterion and hence helps in manipulating the accuracy of the trained network. We see that at vp=0. 2 the network has Recall (i. e. true negative rate) is 75% and average Accuracy=82. 64% and Precision is 79%.