$Deep learning-based optical field screening for robust optical diffraction tomography$
Código QR

Deep learning-based optical field screening for robust optical diffraction tomography

Abstract In tomographic reconstruction, the image quality of the reconstructed images can be significantly degraded by defects in the measured two-dimensional (2D) raw image data. Despite the importance of screening defective 2D images for robust tomographic reconstruction, manual inspection and rul...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	DongHun Ryu, YoungJu Jo, Jihyeong Yoo, Taean Chang, Daewoong Ahn, Young Seo Kim, Geon Kim, Hyun-Seok Min, YongKeun Park
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2019
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/9eecb8381ec241acaec2addcce5caa2a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9eecb8381ec241acaec2addcce5caa2a
record_format	dspace
spelling	oai:doaj.org-article:9eecb8381ec241acaec2addcce5caa2a2021-12-02T15:09:14ZDeep learning-based optical field screening for robust optical diffraction tomography10.1038/s41598-019-51363-x2045-2322https://doaj.org/article/9eecb8381ec241acaec2addcce5caa2a2019-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-019-51363-xhttps://doaj.org/toc/2045-2322Abstract In tomographic reconstruction, the image quality of the reconstructed images can be significantly degraded by defects in the measured two-dimensional (2D) raw image data. Despite the importance of screening defective 2D images for robust tomographic reconstruction, manual inspection and rule-based automation suffer from low-throughput and insufficient accuracy, respectively. Here, we present deep learning-enabled quality control for holographic data to produce robust and high-throughput optical diffraction tomography (ODT). The key idea is to distil the knowledge of an expert into a deep convolutional neural network. We built an extensive database of optical field images with clean/noisy annotations, and then trained a binary-classification network based upon the data. The trained network outperformed visual inspection by non-expert users and a widely used rule-based algorithm, with >90% test accuracy. Subsequently, we confirmed that the superior screening performance significantly improved the tomogram quality. To further confirm the trained model’s performance and generalisability, we evaluated it on unseen biological cell data obtained with a setup that was not used to generate the training dataset. Lastly, we interpreted the trained model using various visualisation techniques that provided the saliency map underlying each model inference. We envision the proposed network would a powerful lightweight module in the tomographic reconstruction pipeline.DongHun RyuYoungJu JoJihyeong YooTaean ChangDaewoong AhnYoung Seo KimGeon KimHyun-Seok MinYongKeun ParkNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 9, Iss 1, Pp 1-9 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q DongHun Ryu YoungJu Jo Jihyeong Yoo Taean Chang Daewoong Ahn Young Seo Kim Geon Kim Hyun-Seok Min YongKeun Park Deep learning-based optical field screening for robust optical diffraction tomography
description	Abstract In tomographic reconstruction, the image quality of the reconstructed images can be significantly degraded by defects in the measured two-dimensional (2D) raw image data. Despite the importance of screening defective 2D images for robust tomographic reconstruction, manual inspection and rule-based automation suffer from low-throughput and insufficient accuracy, respectively. Here, we present deep learning-enabled quality control for holographic data to produce robust and high-throughput optical diffraction tomography (ODT). The key idea is to distil the knowledge of an expert into a deep convolutional neural network. We built an extensive database of optical field images with clean/noisy annotations, and then trained a binary-classification network based upon the data. The trained network outperformed visual inspection by non-expert users and a widely used rule-based algorithm, with >90% test accuracy. Subsequently, we confirmed that the superior screening performance significantly improved the tomogram quality. To further confirm the trained model’s performance and generalisability, we evaluated it on unseen biological cell data obtained with a setup that was not used to generate the training dataset. Lastly, we interpreted the trained model using various visualisation techniques that provided the saliency map underlying each model inference. We envision the proposed network would a powerful lightweight module in the tomographic reconstruction pipeline.
format	article
author	DongHun Ryu YoungJu Jo Jihyeong Yoo Taean Chang Daewoong Ahn Young Seo Kim Geon Kim Hyun-Seok Min YongKeun Park
author_facet	DongHun Ryu YoungJu Jo Jihyeong Yoo Taean Chang Daewoong Ahn Young Seo Kim Geon Kim Hyun-Seok Min YongKeun Park
author_sort	DongHun Ryu
title	Deep learning-based optical field screening for robust optical diffraction tomography
title_short	Deep learning-based optical field screening for robust optical diffraction tomography
title_full	Deep learning-based optical field screening for robust optical diffraction tomography
title_fullStr	Deep learning-based optical field screening for robust optical diffraction tomography
title_full_unstemmed	Deep learning-based optical field screening for robust optical diffraction tomography
title_sort	deep learning-based optical field screening for robust optical diffraction tomography
publisher	Nature Portfolio
publishDate	2019
url	https://doaj.org/article/9eecb8381ec241acaec2addcce5caa2a
work_keys_str_mv	AT donghunryu deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography AT youngjujo deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography AT jihyeongyoo deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography AT taeanchang deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography AT daewoongahn deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography AT youngseokim deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography AT geonkim deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography AT hyunseokmin deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography AT yongkeunpark deeplearningbasedopticalfieldscreeningforrobustopticaldiffractiontomography
_version_	1718387892032634880

Deep learning-based optical field screening for robust optical diffraction tomography

Ejemplares similares