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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F20%3A00115503" target="_blank" >RIV/00216224:14330/20:00115503 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/abstract/document/9098351" target="_blank" >https://ieeexplore.ieee.org/abstract/document/9098351</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ISBI45749.2020.9098351" target="_blank" >10.1109/ISBI45749.2020.9098351</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IEEE 17th International Symposium on Biomedical Imaging

ISBN

9781538693308

ISSN

1945-7928

e-ISSN

1945-8452

Počet stran výsledku

5

Strana od-do

446-450

Název nakladatele

IEEE

Místo vydání

Iowa

Místo konání akce

Iowa, USA

Datum konání akce

1. 1. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000578080300083