Condensed U-Net (CU-Net): An Improved U-Net Architecture for Cell Segmentation Powered by 4x4 Max-Pooling Layers

Investor logo
Investor logo

Warning

This publication doesn't include Faculty of Economics and Administration. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

AKBAS Cem Emre KOZUBEK Michal

Year of publication 2020
Type Article in Proceedings
Conference IEEE 17th International Symposium on Biomedical Imaging
MU Faculty or unit

Faculty of Informatics

Citation
Web https://ieeexplore.ieee.org/abstract/document/9098351
Doi http://dx.doi.org/10.1109/ISBI45749.2020.9098351
Keywords Biomedical Image Segmentation; Convolutional Neural Networks; Deep Learning; Feature Learning; Max Pooling
Description Recently, the U-Net has been the dominant approach in the cell segmentation task in biomedical images due to its success in a wide range of image recognition tasks. However, recent studies did not focus enough on updating the architecture of the U-Net and designing specialized loss functions for bioimage segmentation. We show that the U-Net architecture can achieve more successful results with efficient architectural improvements. We propose a condensed encoder-decoder scheme that employs the 4x4 max-pooling operation and triple convolutional layers. The proposed network architecture is trained using a novel combined loss function specifically designed for bioimage segmentation. On the benchmark datasets from the Cell Tracking Challenge, the experimental results show that the proposed cell segmentation system outperforms the U-Net.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.