@Article{JICS-14-156, author = {Yuhang Qin and Mao Cai}, title = {Residual and Dense Connection Combine Fully Convolutional Network for Infant Brain MRI Segmentation}, journal = {Journal of Information and Computing Science}, year = {2019}, volume = {14}, number = {2}, pages = {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. }, issn = {3080-180X}, doi = {https://doi.org/}, url = {http://global-sci.org/intro/article_detail/jics/22425.html} }