Cargando…

Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes

Imaging is a dominant strategy for data collection in neuroscience, yielding stacks of images that often scale to gigabytes of data for a single experiment. Machine learning algorithms from computer vision can serve as a pair of virtual eyes that tirelessly processes these images, automatically dete...

Descripción completa

Detalles Bibliográficos
Autores principales: Shahbazi, Ali, Kinnison, Jeffery, Vescovi, Rafael, Du, Ming, Hill, Robert, Joesch, Maximilian, Takeno, Marc, Zeng, Hongkui, da Costa, Nuno Maçarico, Grutzendler, Jaime, Kasthuri, Narayanan, Scheirer, Walter J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6155135/
https://www.ncbi.nlm.nih.gov/pubmed/30250218
http://dx.doi.org/10.1038/s41598-018-32628-3
_version_ 1783357832447393792
author Shahbazi, Ali
Kinnison, Jeffery
Vescovi, Rafael
Du, Ming
Hill, Robert
Joesch, Maximilian
Takeno, Marc
Zeng, Hongkui
da Costa, Nuno Maçarico
Grutzendler, Jaime
Kasthuri, Narayanan
Scheirer, Walter J.
author_facet Shahbazi, Ali
Kinnison, Jeffery
Vescovi, Rafael
Du, Ming
Hill, Robert
Joesch, Maximilian
Takeno, Marc
Zeng, Hongkui
da Costa, Nuno Maçarico
Grutzendler, Jaime
Kasthuri, Narayanan
Scheirer, Walter J.
author_sort Shahbazi, Ali
collection PubMed
description Imaging is a dominant strategy for data collection in neuroscience, yielding stacks of images that often scale to gigabytes of data for a single experiment. Machine learning algorithms from computer vision can serve as a pair of virtual eyes that tirelessly processes these images, automatically detecting and identifying microstructures. Unlike learning methods, our Flexible Learning-free Reconstruction of Imaged Neural volumes (FLoRIN) pipeline exploits structure-specific contextual clues and requires no training. This approach generalizes across different modalities, including serially-sectioned scanning electron microscopy (sSEM) of genetically labeled and contrast enhanced processes, spectral confocal reflectance (SCoRe) microscopy, and high-energy synchrotron X-ray microtomography (μCT) of large tissue volumes. We deploy the FLoRIN pipeline on newly published and novel mouse datasets, demonstrating the high biological fidelity of the pipeline’s reconstructions. FLoRIN reconstructions are of sufficient quality for preliminary biological study, for example examining the distribution and morphology of cells or extracting single axons from functional data. Compared to existing supervised learning methods, FLoRIN is one to two orders of magnitude faster and produces high-quality reconstructions that are tolerant to noise and artifacts, as is shown qualitatively and quantitatively.
format Online
Article
Text
id pubmed-6155135
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-61551352018-09-28 Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes Shahbazi, Ali Kinnison, Jeffery Vescovi, Rafael Du, Ming Hill, Robert Joesch, Maximilian Takeno, Marc Zeng, Hongkui da Costa, Nuno Maçarico Grutzendler, Jaime Kasthuri, Narayanan Scheirer, Walter J. Sci Rep Article Imaging is a dominant strategy for data collection in neuroscience, yielding stacks of images that often scale to gigabytes of data for a single experiment. Machine learning algorithms from computer vision can serve as a pair of virtual eyes that tirelessly processes these images, automatically detecting and identifying microstructures. Unlike learning methods, our Flexible Learning-free Reconstruction of Imaged Neural volumes (FLoRIN) pipeline exploits structure-specific contextual clues and requires no training. This approach generalizes across different modalities, including serially-sectioned scanning electron microscopy (sSEM) of genetically labeled and contrast enhanced processes, spectral confocal reflectance (SCoRe) microscopy, and high-energy synchrotron X-ray microtomography (μCT) of large tissue volumes. We deploy the FLoRIN pipeline on newly published and novel mouse datasets, demonstrating the high biological fidelity of the pipeline’s reconstructions. FLoRIN reconstructions are of sufficient quality for preliminary biological study, for example examining the distribution and morphology of cells or extracting single axons from functional data. Compared to existing supervised learning methods, FLoRIN is one to two orders of magnitude faster and produces high-quality reconstructions that are tolerant to noise and artifacts, as is shown qualitatively and quantitatively. Nature Publishing Group UK 2018-09-24 /pmc/articles/PMC6155135/ /pubmed/30250218 http://dx.doi.org/10.1038/s41598-018-32628-3 Text en © The Author(s) 2018 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
spellingShingle Article
Shahbazi, Ali
Kinnison, Jeffery
Vescovi, Rafael
Du, Ming
Hill, Robert
Joesch, Maximilian
Takeno, Marc
Zeng, Hongkui
da Costa, Nuno Maçarico
Grutzendler, Jaime
Kasthuri, Narayanan
Scheirer, Walter J.
Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes
title Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes
title_full Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes
title_fullStr Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes
title_full_unstemmed Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes
title_short Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes
title_sort flexible learning-free segmentation and reconstruction of neural volumes
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6155135/
https://www.ncbi.nlm.nih.gov/pubmed/30250218
http://dx.doi.org/10.1038/s41598-018-32628-3
work_keys_str_mv AT shahbaziali flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT kinnisonjeffery flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT vescovirafael flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT duming flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT hillrobert flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT joeschmaximilian flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT takenomarc flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT zenghongkui flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT dacostanunomacarico flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT grutzendlerjaime flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT kasthurinarayanan flexiblelearningfreesegmentationandreconstructionofneuralvolumes
AT scheirerwalterj flexiblelearningfreesegmentationandreconstructionofneuralvolumes