Open Access
ARTICLE
Mu-Net: Multi-Path Upsampling Convolution Network for Medical Image Segmentation
Jia Chen1, Zhiqiang He1, Dayong Zhu1, Bei Hui1,*, Rita Yi Man Li2, Xiao-Guang Yue3,4,5
1 School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu,
610054, China
2 Department of Economics and Finance/Sustainable Real Estate Research Center, Hong Kong Shue Yan University, Hong Kong, China
3 Rattanakosin International College of Creative Entrepreneurship, Rajamangala University of Technology Rattanakosin, Nakhon
Pathom, 73170, Thailand
4 Department of Computer Science and Engineering, School of Sciences, European University Cyprus, Nicosia, 1516, Cyprus
5 CIICESI, ESTG, Polit´ecnico do Porto, 4610-156, Felgueiras, Portugal
* Corresponding Author: Bei Hui. Email:
Computer Modeling in Engineering & Sciences 2022, 131(1), 73-95. https://doi.org/10.32604/cmes.2022.018565
Received 02 August 2021; Accepted 21 October 2021; Issue published 24 January 2022
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.
Keywords
Cite This Article
Chen, J., He, Z., Zhu, D., Hui, B., Yi, R. et al. (2022). Mu-Net: Multi-Path Upsampling Convolution Network for Medical Image Segmentation.
CMES-Computer Modeling in Engineering & Sciences, 131(1), 73–95. https://doi.org/10.32604/cmes.2022.018565