What is it about?
Due to their regular geometric structure, the standard convolutions they use are inherently limited in dealing with geometric transformations while biomedical objects have huge variations in shape and size. In this paper , we present a novel U-net for biomedical image segmentation.
Featured Image
Photo by Tianshu Liu on Unsplash
Why is it important?
The proposed method has better generalization ability than the existing main methods and improves significantly the segmentation accuracy.
Perspectives
The proposed method will play an important role in clinical diagnosis, pathological analysis, and medical intervention.
Xuegang Hu
Chongqing University of Posts and Telecommunications
Read the Original
This page is a summary of: An improved U-net with deformable encoder - reshaping upsampling convolution decoder for biomedical image segmentation, IET Image Processing, October 2019, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-ipr.2019.0025.
You can read the full text:
Contributors
The following have contributed to this page
