Topology Preserving Segmentation Fusion for Cells with Complex Shapes

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F21%3A00118940" target="_blank" >RIV/00216224:14330/21:00118940 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ISBI48211.2021.9433867" target="_blank" >http://dx.doi.org/10.1109/ISBI48211.2021.9433867</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ISBI48211.2021.9433867" target="_blank" >10.1109/ISBI48211.2021.9433867</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Topology Preserving Segmentation Fusion for Cells with Complex Shapes

Popis výsledku v původním jazyce

We present an algorithm to fuse simply connected segmentation masks of complex and variable shapes that often appear in cell imaging. The algorithm is designed to preserve topology of the input masks and to faithfully represent their protrusions. It works in three main phases: (1) the detection of geodesic ends that correspond to the protrusions, (2) optimal matching of the geodesic ends, and (3) contour averaging of corresponding boundary segments. We show that our algorithm overcomes commonly used pixel-wise fusion algorithms (namely majority voting, SIMPLE, STAPLE, and topology-preserving STAPLE), as well as recently published geometric median shapes in terms of the visual quality of results as well as better representation of protrusions. We demonstrate the performance of our method based on synthetic images as well as real images from the cell segmentation benchmark datasets.

Název v anglickém jazyce

Topology Preserving Segmentation Fusion for Cells with Complex Shapes

Popis výsledku anglicky

We present an algorithm to fuse simply connected segmentation masks of complex and variable shapes that often appear in cell imaging. The algorithm is designed to preserve topology of the input masks and to faithfully represent their protrusions. It works in three main phases: (1) the detection of geodesic ends that correspond to the protrusions, (2) optimal matching of the geodesic ends, and (3) contour averaging of corresponding boundary segments. We show that our algorithm overcomes commonly used pixel-wise fusion algorithms (namely majority voting, SIMPLE, STAPLE, and topology-preserving STAPLE), as well as recently published geometric median shapes in terms of the visual quality of results as well as better representation of protrusions. We demonstrate the performance of our method based on synthetic images as well as real images from the cell segmentation benchmark datasets.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

<a href="/cs/project/GA21-20374S" target="_blank" >GA21-20374S: Segmentace a sledování buněk se složitým tvarem</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

The IEEE International Symposium on Biomedical Imaging

ISBN

9781665412469

ISSN

1945-7928

e-ISSN

1945-8452

Počet stran výsledku

4

Strana od-do

204-207

Název nakladatele

IEEE

Místo vydání

Nice

Místo konání akce

Nice, France

Datum konání akce

13. 4. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000786144100046