PAT - Probabilistic Axon Tracking for Densely Labeled Neurons in Large 3D Micrographs

Henrik Skibbe, Marco Reisert, Ken Nakae, Akiya Watakabe, Junichi Hata, Hiroaki Mizukami, Hideyuki Okano, Tetsuo Yamamori, Shin Ishii

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

A major goal of contemporary neuroscience research is to map the structural connectivity of mammalian brain using microscopy imaging data. In this context, the reconstruction of densely labeled axons from two-photon microscopy images is a challenging and important task. The visually overlapping, crossing, and often strongly distorted images of the axons allow many ambiguous interpretations to be made. We address the problem of tracking axons in densely labeled samples of neurons in large image datasets acquired from marmoset brains. Our highresolution images were acquired using two-photon microscopy and they provided whole brain coverage, occupying terabytes of memory. Both the image distortions and the large dataset size frequently make it impractical to apply present-day neuron tracing algorithms to such data due to the optimization of such algorithms to the precise tracing of either single or sparse sets of neurons. Thus, new tracking techniques are needed. We propose a probabilistic axon tracking algorithm (PAT). PAT tackles the tracking of axons in two steps: locally (L-PAT) and globally (G-PAT). L-PAT is a probabilistic tracking algorithm that can tackle distorted, cluttered images of densely labeled axons. LPAT divides a large micrograph into smaller image stacks. It then processes each image stack independently before mapping the axons in each image to a sparse model of axon trajectories. GPAT merges the sparse L-PAT models into a single global model of axon trajectories by minimizing a global objective function using a probabilistic optimization method.We demonstrate the superior performance of PAT over standard approaches on synthetic data. Furthermore, we successfully apply PAT to densely labeled axons in large images acquired from marmoset brains.

Original languageEnglish
JournalIEEE Transactions on Medical Imaging
DOIs
Publication statusAccepted/In press - 2018 Jul 13

Fingerprint

Neurons
Axons
Brain
Microscopy
Callithrix
Microscopic examination
Photons
Trajectories
Neurosciences

Keywords

  • Axons
  • Image reconstruction
  • Microscopy
  • Spatial resolution
  • Three-dimensional displays

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Skibbe, H., Reisert, M., Nakae, K., Watakabe, A., Hata, J., Mizukami, H., ... Ishii, S. (Accepted/In press). PAT - Probabilistic Axon Tracking for Densely Labeled Neurons in Large 3D Micrographs. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/TMI.2018.2855736

PAT - Probabilistic Axon Tracking for Densely Labeled Neurons in Large 3D Micrographs. / Skibbe, Henrik; Reisert, Marco; Nakae, Ken; Watakabe, Akiya; Hata, Junichi; Mizukami, Hiroaki; Okano, Hideyuki; Yamamori, Tetsuo; Ishii, Shin.

In: IEEE Transactions on Medical Imaging, 13.07.2018.

Research output: Contribution to journalArticle

Skibbe, Henrik ; Reisert, Marco ; Nakae, Ken ; Watakabe, Akiya ; Hata, Junichi ; Mizukami, Hiroaki ; Okano, Hideyuki ; Yamamori, Tetsuo ; Ishii, Shin. / PAT - Probabilistic Axon Tracking for Densely Labeled Neurons in Large 3D Micrographs. In: IEEE Transactions on Medical Imaging. 2018.
@article{2e27b81895b24590ac27e0f9e34d827f,
title = "PAT - Probabilistic Axon Tracking for Densely Labeled Neurons in Large 3D Micrographs",
abstract = "A major goal of contemporary neuroscience research is to map the structural connectivity of mammalian brain using microscopy imaging data. In this context, the reconstruction of densely labeled axons from two-photon microscopy images is a challenging and important task. The visually overlapping, crossing, and often strongly distorted images of the axons allow many ambiguous interpretations to be made. We address the problem of tracking axons in densely labeled samples of neurons in large image datasets acquired from marmoset brains. Our highresolution images were acquired using two-photon microscopy and they provided whole brain coverage, occupying terabytes of memory. Both the image distortions and the large dataset size frequently make it impractical to apply present-day neuron tracing algorithms to such data due to the optimization of such algorithms to the precise tracing of either single or sparse sets of neurons. Thus, new tracking techniques are needed. We propose a probabilistic axon tracking algorithm (PAT). PAT tackles the tracking of axons in two steps: locally (L-PAT) and globally (G-PAT). L-PAT is a probabilistic tracking algorithm that can tackle distorted, cluttered images of densely labeled axons. LPAT divides a large micrograph into smaller image stacks. It then processes each image stack independently before mapping the axons in each image to a sparse model of axon trajectories. GPAT merges the sparse L-PAT models into a single global model of axon trajectories by minimizing a global objective function using a probabilistic optimization method.We demonstrate the superior performance of PAT over standard approaches on synthetic data. Furthermore, we successfully apply PAT to densely labeled axons in large images acquired from marmoset brains.",
keywords = "Axons, Image reconstruction, Microscopy, Spatial resolution, Three-dimensional displays",
author = "Henrik Skibbe and Marco Reisert and Ken Nakae and Akiya Watakabe and Junichi Hata and Hiroaki Mizukami and Hideyuki Okano and Tetsuo Yamamori and Shin Ishii",
year = "2018",
month = "7",
day = "13",
doi = "10.1109/TMI.2018.2855736",
language = "English",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - PAT - Probabilistic Axon Tracking for Densely Labeled Neurons in Large 3D Micrographs

AU - Skibbe, Henrik

AU - Reisert, Marco

AU - Nakae, Ken

AU - Watakabe, Akiya

AU - Hata, Junichi

AU - Mizukami, Hiroaki

AU - Okano, Hideyuki

AU - Yamamori, Tetsuo

AU - Ishii, Shin

PY - 2018/7/13

Y1 - 2018/7/13

N2 - A major goal of contemporary neuroscience research is to map the structural connectivity of mammalian brain using microscopy imaging data. In this context, the reconstruction of densely labeled axons from two-photon microscopy images is a challenging and important task. The visually overlapping, crossing, and often strongly distorted images of the axons allow many ambiguous interpretations to be made. We address the problem of tracking axons in densely labeled samples of neurons in large image datasets acquired from marmoset brains. Our highresolution images were acquired using two-photon microscopy and they provided whole brain coverage, occupying terabytes of memory. Both the image distortions and the large dataset size frequently make it impractical to apply present-day neuron tracing algorithms to such data due to the optimization of such algorithms to the precise tracing of either single or sparse sets of neurons. Thus, new tracking techniques are needed. We propose a probabilistic axon tracking algorithm (PAT). PAT tackles the tracking of axons in two steps: locally (L-PAT) and globally (G-PAT). L-PAT is a probabilistic tracking algorithm that can tackle distorted, cluttered images of densely labeled axons. LPAT divides a large micrograph into smaller image stacks. It then processes each image stack independently before mapping the axons in each image to a sparse model of axon trajectories. GPAT merges the sparse L-PAT models into a single global model of axon trajectories by minimizing a global objective function using a probabilistic optimization method.We demonstrate the superior performance of PAT over standard approaches on synthetic data. Furthermore, we successfully apply PAT to densely labeled axons in large images acquired from marmoset brains.

AB - A major goal of contemporary neuroscience research is to map the structural connectivity of mammalian brain using microscopy imaging data. In this context, the reconstruction of densely labeled axons from two-photon microscopy images is a challenging and important task. The visually overlapping, crossing, and often strongly distorted images of the axons allow many ambiguous interpretations to be made. We address the problem of tracking axons in densely labeled samples of neurons in large image datasets acquired from marmoset brains. Our highresolution images were acquired using two-photon microscopy and they provided whole brain coverage, occupying terabytes of memory. Both the image distortions and the large dataset size frequently make it impractical to apply present-day neuron tracing algorithms to such data due to the optimization of such algorithms to the precise tracing of either single or sparse sets of neurons. Thus, new tracking techniques are needed. We propose a probabilistic axon tracking algorithm (PAT). PAT tackles the tracking of axons in two steps: locally (L-PAT) and globally (G-PAT). L-PAT is a probabilistic tracking algorithm that can tackle distorted, cluttered images of densely labeled axons. LPAT divides a large micrograph into smaller image stacks. It then processes each image stack independently before mapping the axons in each image to a sparse model of axon trajectories. GPAT merges the sparse L-PAT models into a single global model of axon trajectories by minimizing a global objective function using a probabilistic optimization method.We demonstrate the superior performance of PAT over standard approaches on synthetic data. Furthermore, we successfully apply PAT to densely labeled axons in large images acquired from marmoset brains.

KW - Axons

KW - Image reconstruction

KW - Microscopy

KW - Spatial resolution

KW - Three-dimensional displays

UR - http://www.scopus.com/inward/record.url?scp=85049978834&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049978834&partnerID=8YFLogxK

U2 - 10.1109/TMI.2018.2855736

DO - 10.1109/TMI.2018.2855736

M3 - Article

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

ER -