Journal
SOFT COMPUTING
Volume 26, Issue 16, Pages 7449-7460Publisher
SPRINGER
DOI: 10.1007/s00500-021-06449-y
Keywords
Nucleus image; Image segmentation technology; GAN; FCN model; Fully connected layer convolution; Pixel loss
Ask authors/readers for more resources
The study proposes a method that combines FCN and GAN models for cell nucleus image segmentation, which achieved better results than other comparison methods.
The study aims at the problems of rough edges and low accuracy in processing cell nucleus image segmentation in existing image segmentation methods. The use of a generative adversarial network (GAN) and a fully convolutional network (FCN) model to segment cell nuclei is suggested. First, the FCN model is used to perform preliminary segmentation of the cell nucleus image, in which the fully connected layer convolution and skip connection are used to improve the accuracy of image segmentation, then improve the GAN, introduce splitting branches into the discriminator structure, and combine the GAN and the splitting network into one. At the same time, pixel loss is introduced in the generator to obtain a nucleus image that is visually more similar to the real image. Finally, the segmented image output by the FCN model is used as the input of the GAN to achieve high-precision segmentation of the nucleus image. The proposed method is experimentally demonstrated based on the 2018 data science bowl data set. The results show that it can achieve rapid convergence, and the mean intersection over union (MIoU) is 85.34%, which is better than other comparison methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available