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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Entorhinal Cortex Hyperexcitability Drives Selective Hippocampal Injury and Cognitive Impairment After Global Cerebral Ischemia.

Journal of the American Heart Association·2026
Same author

Detection of M-protein by iMS-IP and iMS-FLC assays redefines previously non-secretory POEMS syndrome.

Clinical chemistry and laboratory medicine·2026
Same author

Connecting single-cell transcriptomes to projectomes in the mouse visual cortex.

Nature·2026
Same author

An Archaeal Cyclodextrin Glycosyltransferase from <i>Haloferax</i> sp.: Characterization and Application in Starch Degradation.

International journal of molecular sciences·2026
Same author

Localized amyloid-β oligomers in the lateral entorhinal cortex drives olfactory dysfunction through aberrant neuronal and network activity.

Acta neuropathologica communications·2026
Same authorSame journal

A quantitative and precision‑oriented neuronal reconstruction approach based on data grading.

Brain informatics·2026

Related Experiment Video

Updated: Jun 4, 2025

High-Throughput Analysis of Optical Mapping Data Using ElectroMap
07:36

High-Throughput Analysis of Optical Mapping Data Using ElectroMap

Published on: June 4, 2019

9.2K

High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural

Hong Zhang1, Zhikang Lu1, Peicong Gong1

  • 1Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University, Sanya, 572025, China.

Brain Informatics
|December 18, 2024
PubMed
Summary
This summary is machine-generated.

We developed an automated pipeline for processing large mouse brain imaging datasets. This system significantly reduces processing time and manual labor, improving efficiency for high-throughput mesoscopic optical imaging.

Keywords:
Differential guided filteringHigh-throughput mesoscopic optical imagingMachine learning and deep learningMouse brain data parsing

More Related Videos

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates
10:18

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

Published on: July 9, 2020

2.9K
Simultaneous Imaging of Microglial Dynamics and Neuronal Activity in Awake Mice
08:26

Simultaneous Imaging of Microglial Dynamics and Neuronal Activity in Awake Mice

Published on: August 23, 2022

2.2K

Related Experiment Videos

Last Updated: Jun 4, 2025

High-Throughput Analysis of Optical Mapping Data Using ElectroMap
07:36

High-Throughput Analysis of Optical Mapping Data Using ElectroMap

Published on: June 4, 2019

9.2K
Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates
10:18

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

Published on: July 9, 2020

2.9K
Simultaneous Imaging of Microglial Dynamics and Neuronal Activity in Awake Mice
08:26

Simultaneous Imaging of Microglial Dynamics and Neuronal Activity in Awake Mice

Published on: August 23, 2022

2.2K

Area of Science:

  • Neuroscience
  • Biomedical Imaging
  • Computational Biology

Background:

  • High-throughput mesoscopic optical imaging generates massive mouse brain datasets.
  • Current processing methods for these datasets are labor-intensive and computationally expensive, involving manual cropping and artifact removal.
  • Large datasets (up to 220TB) require efficient processing for subsequent analyses.

Purpose of the Study:

  • To design an efficient deep differential guided filtering module (DDGF) for refining image details and reducing noise in mesoscopic mouse brain data.
  • To develop a lightweight deep differential guided filtering segmentation network (DDGF-SegNet) for robust image segmentation.
  • To create an automated, parallelized processing pipeline to streamline the entire workflow for large-scale mouse brain datasets.

Main Methods:

  • Fusion of multi-scale iterative differential guided filtering with deep learning to create the DDGF module.
  • Development of the DDGF-SegNet for image segmentation, achieving high performance metrics (Dice: 0.92, Precision: 0.98, Recall: 0.91, Jaccard: 0.86).
  • Implementation of connectivity analysis for 3D spatial orientation and an automated pipeline optimized for Message Passing Interface (MPI) parallel computation.

Main Results:

  • The DDGF module effectively refines image details and mitigates background noise.
  • The DDGF-SegNet demonstrated robust segmentation performance on the mouse brain dataset.
  • The automated pipeline reduced processing time for a mouse brain dataset to 1.1 hours.

Conclusions:

  • The developed automated pipeline significantly enhances manual efficiency (25x) and overall data processing efficiency (2.4x).
  • This approach paves the way for more efficient big data processing and analysis in high-throughput mesoscopic optical imaging.
  • The DDGF-SegNet and automated pipeline offer a scalable solution for handling large-scale neuroimaging data.