TY - JOUR
T1 - A Multi-Scale Fully Convolutional Networks Model for Brain MRI Segmentation
AU - Zhihui Cao, Yuhang Qin and Yunjie Chen
JO - Journal of Information and Computing Science
VL - 2
SP - 083
EP - 088
PY - 2024
DA - 2024/01
SN - 13
DO - http://doi.org/
UR - https://global-sci.org/intro/article_detail/jics/22450.html
KW -   Convolutional  neural  networks
KW -   Fully  convolutional  networks
KW -   magnetic 
resonance image
KW -  multi-scale. 

AB - 1School of math and statistics, Nanjing University of Information Science & Technology, Nanjing 210044, China 
(Received October 01 2017, accepted January 15 2018) 
Abstract 。 Accurate  segmentation  for  brain  magnetic  resonance  (MR)  images  is  of  great  significance  to 
quantitative analysis of brain image. However, traditional segmentation methods suffer from the problems existing 
in brain images such as noise,  weak edges and intensity inhomogeneity (also named as  bias field). Convolutional 
neural networks based methods have been used to segment images; however, it is still hard to find accurate results 
for  brain  MR  images.  In  order  to  obtain  accurate  segmentation  results,  a  multi-scale  fully  convolution  networks 
model  (MSFCN)  is  proposed  in  this  paper.  First,  we  use  padding  convolutions  in  conv-layer  to  preserve  the 
resolution of feature maps. So we can obtain segmentation results with the same resolution as inputs. Then, different 
sized filters are utilized in the same conv-layer, after that, the outputs of these filters are concatenated together and 
fed  to  the  next  layer,  which  makes  the  model  learn  features  from  different  scales.  Both  experimental  results  and 
statistic results show that the proposed model can obtain more accurate results.