Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

M-AMST: an automatic 3D neuron tracing method based on mean shift and adapted minimum spanning tree.

Zhijiang Wan1,2,3,4,5, Yishan He2,3,4,5, Ming Hao2,3,4,5

  • 1Beijing Advanced Innovation Center for Future Internet Technology, Beijing University of Technology, Beijing, China.

BMC Bioinformatics
|March 31, 2017
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Climatic reconstruction at the Miocene Shanwang basin, China, using leaf margin analysis, CLAMP, coexistence approach, and overlapping distribution analysis.

American journal of botany·2011
Same author

Novel candidate colorectal cancer biomarkers identified by methylation microarray-based scanning.

Endocrine-related cancer·2011
Same author

Stress and strain analysis of contractions during ramp distension in partially obstructed guinea pig jejunal segments.

Journal of biomechanics·2011
Same author

Role of Gα(12)- and Gα(13)-protein subunit linkage of D(3) dopamine receptors in the natriuretic effect of D(3) dopamine receptor in kidney.

Hypertension research : official journal of the Japanese Society of Hypertension·2011
Same author

Transarticular screw and C1 hook fixation for os odontoideum with atlantoaxial dislocation.

World neurosurgery·2011
Same author

Surgical treatments of myelopathy caused by cervical ligamentum flavum ossification.

World neurosurgery·2011
This summary is machine-generated.

The M-AMST algorithm improves neuron reconstruction by incorporating shape information, outperforming previous methods in accuracy and consistency across diverse datasets. This advancement aids in understanding brain mechanisms.

Area of Science:

  • Neuroscience
  • Computational Biology
  • Image Analysis

Background:

  • Understanding brain mechanisms is a grand challenge.
  • The BigNeuron project aims to create a big data resource for single neuron reconstruction.
  • Existing algorithms like mean shift and minimum spanning tree (M-MST) have limitations in capturing neuron shape information.

Purpose of the Study:

  • To propose an improved neuron reconstruction algorithm, M-AMST.
  • To enhance the weight calculation method in M-MST by incorporating neuron shape information.
  • To evaluate the performance of M-AMST on various neuron image datasets.

Main Methods:

  • Developed M-AMST, an algorithm using a rotating sphere model and coordinate transformation to improve MST weight calculation.
Keywords:
Coordinate transformationM-AMSTMean shiftNeuron reconstructionSphere model

Related Experiment Videos

  • Experiment 1: Compared M-AMST with M-MST and other algorithms using difference scores (ESA, DSA, PDS, MDNN) on APP2 dataset.
  • Experiment 2: Evaluated M-AMST on 7 diverse neuron image datasets, comparing its reconstruction accuracy against 6 other algorithms.

    • Main Results:

    • M-AMST achieved lower difference scores than M-MST in ESA, PDS, and MDNN.
    • M-AMST outperformed N-MST in ESA and MDNN.
    • M-AMST demonstrated superior performance on multiple datasets, achieving the best scores in 3 and second-best in 2 out of 7 tested datasets.

    Conclusions:

    • The M-AMST algorithm effectively improves neuron reconstruction by integrating shape information.
    • The rotating sphere model enhances weight calculation for more precise pathway extraction.
    • M-AMST shows broad applicability and robust performance across various neuron image datasets.