Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes

Journal Article · · Scientific Reports
 [1]; ORCiD logo [2];  [3];  [4]; ORCiD logo [5];  [6]; ORCiD logo [7]; ORCiD logo [7];  [7]; ORCiD logo [5];  [3];  [1]
  1. Univ. of Notre Dame, IN (United States)
  2. Univ. of Notre Dame, IN (United States); Argonne National Lab. (ANL), Argonne, IL (United States). Center for Nanoscale Materials
  3. Argonne National Lab. (ANL), Argonne, IL (United States). Center for Nanoscale Materials; Univ. of Chicago, IL (United States)
  4. Northwestern Univ., Evanston, IL (United States)
  5. Yale Univ., New Haven, CT (United States)
  6. Institute of Science and Technology Austria (IST) (Austria)
  7. Allen Inst. for Brain Science, Seattle, WA (United States)
+ Show Author Affiliations

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-specifc contextual clues and requires no training. This approach generalizes across diferent modalities, including serially-sectioned scanning electron microscopy (sSEM) of genetically labeled and contrast enhanced processes, spectral confocal refectance (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 fdelity of the pipeline’s reconstructions. FLoRIN reconstructions are of sufcient 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.

Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States). Argonne Leadership Computing Facility (ALCF)
Sponsoring Organization:
USDOE Office of Science (SC); Office of the Director of National Intelligence (ODNI); Intelligence Advanced Research Projects Activity (IARPA); NVIDIA Corporation; National Science Foundation (NSF)
Grant/Contract Number:
AC02-06CH11357; D16PC00002; D16PC00004; CNS-1629914
OSTI ID:
1624428
Journal Information:
Scientific Reports, Vol. 8, Issue 1; ISSN 2045-2322
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English

References (54)

The big data challenges of connectomics journal October 2014
DP2: Distributed 3D image segmentation using micro-labor workforce journal April 2013
CATMAID: collaborative annotation toolkit for massive amounts of image data journal April 2009
High-accuracy neurite reconstruction for high-throughput neuroanatomy journal July 2011
TrakEM2 Software for Neural Circuit Reconstruction journal June 2012
User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability journal July 2006
A visual motion detection circuit suggested by Drosophila connectomics journal August 2013
Synaptic Inputs Compete during Rapid Formation of the Calyx of Held: A New Model System for Neural Development journal August 2013
Learning to Segment Neurons with Non-local Quality Measures book January 2013
Automatic joint classification and segmentation of whole cell 3D images journal June 2009
Learning Structured Models for Segmentation of 2-D and 3-D Imagery journal May 2015
Automated tracing of myelinated axons and detection of the nodes of Ranvier in serial images of peripheral nerves: AUTOMATED TRACING OF MYELINATED AXONS AND DETECTION OF THE NODES OF RANVIER journal June 2015
Towards the automatic classification of neurons journal May 2015
A modular hierarchical approach to 3D electron microscopy image segmentation journal April 2014
Large-scale automatic reconstruction of neuronal processes from electron microscopy images journal May 2015
An efficient conditional random field approach for automatic and interactive neuron segmentation journal January 2016
Design and Evaluation of Interactive Proofreading Tools for Connectomics journal December 2014
Efficient semi-automatic 3D segmentation for neuron tracing in electron microscopy images journal May 2015
Detection of neuron membranes in electron microscopy images using a serial neural network architecture journal December 2010
VESICLE: Volumetric Evaluation of Synaptic Inferfaces using Computer Vision at Large Scale conference January 2015
Saturated Reconstruction of a Volume of Neocortex journal July 2015
Optimizing the 3D-reconstruction technique for serial block-face scanning electron microscopy journal May 2016
U-Net: Convolutional Networks for Biomedical Image Segmentation
  • Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas
  • Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28
book November 2015
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation conference January 2016
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation conference October 2016
Nuclei Segmentation of Fluorescence Microscopy Images Using Three Dimensional Convolutional Neural Networks conference July 2017
Adaptive Thresholding using the Integral Image journal January 2007
A note on the computation of high-dimensional integral images journal January 2011
Quantifying Mesoscale Neuroanatomy Using X-Ray Microtomography journal September 2017
Adaptive document image binarization journal February 2000
Automatic measurement of sister chromatid exchange frequency. journal July 1977
A Morphological Approach to Curvature-Based Evolution of Curves and Surfaces journal January 2014
A Threshold Selection Method from Gray-Level Histograms journal January 1979
Directed evolution of APEX2 for electron microscopy and proximity labeling journal November 2014
Picture Thresholding Using an Iterative Selection Method journal January 1978
An iterative algorithm for minimum cross entropy thresholding journal June 1998
Reconstruction of genetically identified neurons imaged by serial-section electron microscopy journal July 2016
Label-free in vivo imaging of myelinated axons in health and disease with spectral confocal reflectance microscopy journal March 2014
An Automated Pipeline for the Collection, Transfer, and Processing of Large-scale Tomography Data conference January 2018
TomoPy: a framework for the analysis of synchrotron tomographic data journal August 2014
Imaging ATUM ultrathin section libraries with WaferMapper: a multi-scale approach to EM reconstruction of neural circuits journal June 2014
Data from: Reconstruction of genetically identified neurons imaged by serial-section electron microscopy dataset January 2016
Proteomics of protein trafficking by in vivo tissue-specific labeling journal April 2021
High-precision automated reconstruction of neurons with flood-filling networks journal July 2018
Chunkflow: hybrid cloud processing of large 3D images by convolutional nets journal March 2021
TrakEM2 Software for Neural Circuit Reconstruction text January 2012
CATMAID: collaborative annotation toolkit for massive amounts of image data text January 2009
Machine Learning in Medical Imaging journal January 2012
TomoPy: A framework for the analysis of synchrotron tomographic data conference September 2014
CATMAID: Collaborative annotation toolkit for massive amounts of image data text January 2009
Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images preprint January 2013
Quantifying mesoscale neuroanatomy using X-ray microtomography preprint January 2016
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation preprint January 2016
Data from: Reconstruction of genetically identified neurons imaged by serial-section electron microscopy dataset January 2016

Figures / Tables (8)

Figure 1(p. 3)figure Figure 1
Figure 2(p. 4)figure Figure 2
Table 1(p. 5)table Table 1
Figure 3(p. 6)figure Figure 3
Figure 4(p. 7)figure Figure 4
Table 2(p. 8)table Table 2
Figure 5(p. 9)figure Figure 5
Figure 6(p. 11)figure Figure 6

Similar Records

Publisher Correction: Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes
Journal Article · 2018 · Scientific Reports · OSTI ID:1629360
+9 more
3D imaging techniques for characterising microcracks in cement-based materials
Journal Article · 2021 · Cement and Concrete Research · OSTI ID:23206394
+2 more
WE-H-206-00: Advances in Preclinical Imaging
Journal Article · 2016 · Medical Physics · OSTI ID:22679170

Related Subjects

47 OTHER INSTRUMENTATION
97 MATHEMATICS AND COMPUTING
59 BASIC BIOLOGICAL SCIENCES
science & technology - other topics
neural volume
standard thresholding methods
Joesch
grayscale properties
deep learning methods
image processing
neural circuits