AUTHOR=Cai Sijing , Wu Yi , Chen Guannan 

TITLE=A Novel Elastomeric UNet for Medical Image Segmentation

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 14 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2022.841297

DOI=10.3389/fnagi.2022.841297

ISSN=1663-4365

ABSTRACT=The medical image segmentation is of important support for clinical medical application. As most of the current medical image segmentation models are limited in the U-shaped structure, to some extent the deep Convolutional Neural Network(CNN) structure design is hard to be accomplished. The design in this article mimic the way the wave is elastomeric propagating, extending the structure from both the horizontal and spatial dimensions for realizing the Elastomeric Network (ENet) structure. The ENet can be divided into two types: Horizontal ENet and Spatial ENet, based on the propagation direction. The advantages of this design are threefold. First, the training structure can be deepened effectively. Secondly, the independence brought by each branch (a U-shape design) makes the flexible design redundancy available. Finally, a horizontal and vertical series-parallel structure helps on feature accumulation and recursion. Researchers can adjust the design according to the requirements to achieve better segmentation performance for the independent structural design. The proposed networks were evaluated on 2 datasets: a self-built dataset (Multi-Photon Microscopy, MPM) and benchmark retinal datasets (DRIVE). The results of experiments demonstrated that the performance of ENet outperformed the UNet and its variants.