@Article{cmes.2022.018565,
AUTHOR = {Jia Chen, Zhiqiang He, Dayong Zhu, Bei Hui, Rita Yi Man Li, Xiao-Guang Yue},
TITLE = {Mu-Net: Multi-Path Upsampling Convolution Network for Medical Image Segmentation},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {131},
YEAR = {2022},
NUMBER = {1},
PAGES = {73--95},
URL = {http://www.techscience.com/CMES/v131n1/46634},
ISSN = {1526-1506},
ABSTRACT = {Medical image segmentation plays an important role in clinical diagnosis, quantitative analysis, and treatment
process. Since 2015, U-Net-based approaches have been widely used for medical image segmentation. The purpose
of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.
However, the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of
some high-level information. More high-level information can make the segmentation more accurate. In this paper,
we propose MU-Net, a novel, multi-path upsampling convolution network to retain more high-level information.
The MU-Net mainly consists of three parts: contracting path, skip connection, and multi-expansive paths. The
proposed MU-Net architecture is evaluated based on three different medical imaging datasets. Our experiments
show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets. At the
same time, the computational efficiency is significantly improved by reducing the number of parameters by more
than half.},
DOI = {10.32604/cmes.2022.018565}
}