Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei

The analysis of microscopic images from cell cultures plays an important role in the development of drugs. The segmentation of such images is a basic step to extract the viable information on which further evaluation steps are build. Classical image processing pipelines often fail under heterogeneou...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bruch Roman, Rudolf Rüdiger, Mikut Ralf, Reischl Markus
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2020
Materias:	sparse labeling deep learning iterative training semi-supervised learning semantic segmentation Medicine R
Acceso en línea:	https://doaj.org/article/e4a5b150923f44b58ccb623f327bec7c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e4a5b150923f44b58ccb623f327bec7c
record_format	dspace
spelling	oai:doaj.org-article:e4a5b150923f44b58ccb623f327bec7c2021-12-05T14:10:42ZEvaluation of semi-supervised learning using sparse labeling to segment cell nuclei2364-550410.1515/cdbme-2020-3103https://doaj.org/article/e4a5b150923f44b58ccb623f327bec7c2020-09-01T00:00:00Zhttps://doi.org/10.1515/cdbme-2020-3103https://doaj.org/toc/2364-5504The analysis of microscopic images from cell cultures plays an important role in the development of drugs. The segmentation of such images is a basic step to extract the viable information on which further evaluation steps are build. Classical image processing pipelines often fail under heterogeneous conditions. In the recent years deep neuronal networks gained attention due to their great potentials in image segmentation. One main pitfall of deep learning is often seen in the amount of labeled data required for training such models. Especially for 3D images the process to generate such data is tedious and time consuming and thus seen as a possible reason for the lack of establishment of deep learning models for 3D data. Efforts have been made to minimize the time needed to create labeled training data or to reduce the amount of labels needed for training. In this paper we present a new semisupervised training method for image segmentation of microscopic cell recordings based on an iterative approach utilizing unlabeled data during training. This method helps to further reduce the amount of labels required to effectively train deep learning models for image segmentation. By labeling less than one percent of the training data, a performance of 90% compared to a full annotation with 342 nuclei can be achieved.Bruch RomanRudolf RüdigerMikut RalfReischl MarkusDe Gruyterarticlesparse labelingdeep learningiterative trainingsemi-supervised learningsemantic segmentationMedicineRENCurrent Directions in Biomedical Engineering, Vol 6, Iss 3, Pp 398-401 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	sparse labeling deep learning iterative training semi-supervised learning semantic segmentation Medicine R
spellingShingle	sparse labeling deep learning iterative training semi-supervised learning semantic segmentation Medicine R Bruch Roman Rudolf Rüdiger Mikut Ralf Reischl Markus Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei
description	The analysis of microscopic images from cell cultures plays an important role in the development of drugs. The segmentation of such images is a basic step to extract the viable information on which further evaluation steps are build. Classical image processing pipelines often fail under heterogeneous conditions. In the recent years deep neuronal networks gained attention due to their great potentials in image segmentation. One main pitfall of deep learning is often seen in the amount of labeled data required for training such models. Especially for 3D images the process to generate such data is tedious and time consuming and thus seen as a possible reason for the lack of establishment of deep learning models for 3D data. Efforts have been made to minimize the time needed to create labeled training data or to reduce the amount of labels needed for training. In this paper we present a new semisupervised training method for image segmentation of microscopic cell recordings based on an iterative approach utilizing unlabeled data during training. This method helps to further reduce the amount of labels required to effectively train deep learning models for image segmentation. By labeling less than one percent of the training data, a performance of 90% compared to a full annotation with 342 nuclei can be achieved.
format	article
author	Bruch Roman Rudolf Rüdiger Mikut Ralf Reischl Markus
author_facet	Bruch Roman Rudolf Rüdiger Mikut Ralf Reischl Markus
author_sort	Bruch Roman
title	Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei
title_short	Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei
title_full	Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei
title_fullStr	Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei
title_full_unstemmed	Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei
title_sort	evaluation of semi-supervised learning using sparse labeling to segment cell nuclei
publisher	De Gruyter
publishDate	2020
url	https://doaj.org/article/e4a5b150923f44b58ccb623f327bec7c
work_keys_str_mv	AT bruchroman evaluationofsemisupervisedlearningusingsparselabelingtosegmentcellnuclei AT rudolfrudiger evaluationofsemisupervisedlearningusingsparselabelingtosegmentcellnuclei AT mikutralf evaluationofsemisupervisedlearningusingsparselabelingtosegmentcellnuclei AT reischlmarkus evaluationofsemisupervisedlearningusingsparselabelingtosegmentcellnuclei
_version_	1718371814045908992

Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei

Ejemplares similares