Open Access
ARTICLE
Mu-Net: Multi-Path Upsampling Convolution Network for Medical Image Segmentation
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
