Augmentation Technique for Artificial Phase-Contrast Microscopy Image Synthesis for the Training of Deep Learning Algorithms

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F19%3APU137321" target="_blank" >RIV/00216305:26220/19:PU137321 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.researchgate.net/publication/335365184_Augmentation_Technique_for_Artificial_Phase-Contrast_Microscopy_Image_Synthesis_for_the_Training_of_Deep_Learning_Algorithms" target="_blank" >https://www.researchgate.net/publication/335365184_Augmentation_Technique_for_Artificial_Phase-Contrast_Microscopy_Image_Synthesis_for_the_Training_of_Deep_Learning_Algorithms</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Augmentation Technique for Artificial Phase-Contrast Microscopy Image Synthesis for the Training of Deep Learning Algorithms

Popis výsledku v původním jazyce

Phase contrast image segmentation is crucial for various biological tasks such as quantitative or comparative analysis at single cell level. Deep learning-based image segmentation has been transferred into the field of microscopy imaging. A large amount of precisely annotated cells is required. Thus, the annotation process is for the experts lengthy and time-consuming. This paper introduces a strategy and augmentation technique for artificial phase-contrast images synthesis aiming to train and support the generalisation ability of deep learning algorithms.

Název v anglickém jazyce

Augmentation Technique for Artificial Phase-Contrast Microscopy Image Synthesis for the Training of Deep Learning Algorithms

Popis výsledku anglicky

Phase contrast image segmentation is crucial for various biological tasks such as quantitative or comparative analysis at single cell level. Deep learning-based image segmentation has been transferred into the field of microscopy imaging. A large amount of precisely annotated cells is required. Thus, the annotation process is for the experts lengthy and time-consuming. This paper introduces a strategy and augmentation technique for artificial phase-contrast images synthesis aiming to train and support the generalisation ability of deep learning algorithms.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

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