MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation

Run Su; Deyun Zhang; Jinhuai Liu; Chuandong Cheng

doi:10.3389/fgene.2021.639930

MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation

Front Genet. 2021 Feb 11:12:639930. doi: 10.3389/fgene.2021.639930. eCollection 2021.

Authors

Run Su^{1

2}, Deyun Zhang³, Jinhuai Liu^{1

2}, Chuandong Cheng^{4

5

6}

Affiliations

¹ Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China.
² Science Island Branch of Graduate School, University of Science and Technology of China, Hefei, China.
³ School of Engineering, Anhui Agricultural University, Hefei, China.
⁴ Department of Neurosurgery, The First Affiliated Hospital of University of Science and Technology of China (USTC), Hefei, China.
⁵ Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China.
⁶ Anhui Province Key Laboratory of Brain Function and Brain Disease, Hefei, China.

Abstract

Aiming at the limitation of the convolution kernel with a fixed receptive field and unknown prior to optimal network width in U-Net, multi-scale U-Net (MSU-Net) is proposed by us for medical image segmentation. First, multiple convolution sequence is used to extract more semantic features from the images. Second, the convolution kernel with different receptive fields is used to make features more diverse. The problem of unknown network width is alleviated by efficient integration of convolution kernel with different receptive fields. In addition, the multi-scale block is extended to other variants of the original U-Net to verify its universality. Five different medical image segmentation datasets are used to evaluate MSU-Net. A variety of imaging modalities are included in these datasets, such as electron microscopy, dermoscope, ultrasound, etc. Intersection over Union (IoU) of MSU-Net on each dataset are 0.771, 0.867, 0.708, 0.900, and 0.702, respectively. Experimental results show that MSU-Net achieves the best performance on different datasets. Our implementation is available at https://github.com/CN-zdy/MSU_Net.

Keywords: U-net; convolution kernel; medical image segmentation; multi-scale block; receptive field.