Year: 2019
Journal of Information and Computing Science, Vol. 14 (2019), Iss. 2 : pp. 156–160
Abstract
In the development of medical image segmentation, the application of convolutional neural networks has begun a profound revolution. The deep learning model is famous for excellent flexibility, efficiency and accuracy. The U-Net model is the beginning of task in the segmentation of medical images, which includes the basic operations of convolution, maxpooling, deconvolution, and concatenation. However, the U-Net model is disable to perform well on many types of data sets, because the model can’t solve the exact segmentation of the details. We proposed Residual and Dense Fully Convolutional Network (RDFCN) that consist of Residual Connection Block and Dense Connection Block, which makes up for the shortcomings of U-Net. The dataset we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu). This dataset is comprised of infant(between 6 and 9 months of age) brain MR images. After the testing, our model outperforms the U-Net and some of its improved models in evaluation of WM, GM and CSF.
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/2024-JICS-22425
Journal of Information and Computing Science, Vol. 14 (2019), Iss. 2 : pp. 156–160
Published online: 2019-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 5