The application of convolution neural network for the detection of Micro Nucleuses (MNs) in human lymphocyte images acquired by an image flow cytometer is considered in this paper. The existing method of detection, IMAQ Match Pattern, is described. The training algorithm of the convolution neural network (CNN) and the detection procedure are presented. The performance of both detection methods are explored on the set of human lymphocyte images at the different intensities of Gaussian noise alteration. Our results show that the IMAQ Match Pattern method provides low detection rates of the MNs at the presence even of the small intensity of Gaussian noise alteration. Instead the CNN provides much higher detection rates at the different intensities of Gaussian noise alteration.
Detection of Micro Nucleus in Human Lymphocytes Altered by Gaussian Noise Using Convolution Neural Network
Lamonaca F;
2011-01-01
Abstract
The application of convolution neural network for the detection of Micro Nucleuses (MNs) in human lymphocyte images acquired by an image flow cytometer is considered in this paper. The existing method of detection, IMAQ Match Pattern, is described. The training algorithm of the convolution neural network (CNN) and the detection procedure are presented. The performance of both detection methods are explored on the set of human lymphocyte images at the different intensities of Gaussian noise alteration. Our results show that the IMAQ Match Pattern method provides low detection rates of the MNs at the presence even of the small intensity of Gaussian noise alteration. Instead the CNN provides much higher detection rates at the different intensities of Gaussian noise alteration.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.