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

ROS-Targeted Nanomotor Therapy in OA: Cartilage Protection and Pain Relief.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Inhibition of ferroptosis via SLC25A39-NRF2 axis drives Osimertinib resistance in lung adenocarcinoma.

Cellular and molecular life sciences : CMLS·2026
Same author

Dfpenicimeroterpenoid A, Meroterpenoids with 6/6/6/4/5 Polycyclic Skeletons from the Marine-Derived Fungus <i>Penicillium</i> sp. DF71.

Organic letters·2026
Same author

Promoting Consciousness Recovery in Patients with Acquired Brain Injury Through Multimodal Sensory Stimulation: A Randomized Controlled Trial of Median Nerve and Auricular Stimulation.

Neurocritical care·2026
Same author

Volume Deformation Control of Concrete for Hydraulic Structures Using Polyurethane-Modified Polycarboxylate Superplasticizer: A Review.

Materials (Basel, Switzerland)·2026
Same author

PPTase-Based Activation Unlocks New Anthraquinones from Marine-Derived <i>Micromonospora</i> sp. SCSIO 07396.

Journal of natural products·2026

Related Experiment Video

Updated: Mar 29, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

25.1K

MBMSA-UNet: A Multi-Scale Attention-Based Instance Segmentation Model for Moso Bamboo Cells.

Xue Zhou1, Ziwei Cheng1,2, Long Chen1

  • 1College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China.

Plants (Basel, Switzerland)
|March 28, 2026
PubMed
Summary

This study introduces MBMSA-UNet, an improved model for segmenting moso bamboo cells in microscopic images. It enhances accuracy and robustness for plant phenomics and materials analysis.

Keywords:
U-Netinstance segmentationmicroscopic image analysismoso bamboo cellsmulti-scale attentionparenchyma cellsvascular bundles

More Related Videos

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

1.2K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.2K

Related Experiment Videos

Last Updated: Mar 29, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

25.1K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

1.2K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.2K

Area of Science:

  • Plant biology
  • Materials science
  • Bioimage analysis

Background:

  • Accurate moso bamboo cell segmentation is crucial for plant phenomics and materials analysis.
  • Traditional algorithms struggle with complex bamboo structures like thick-walled fibers and large vessels, leading to segmentation inaccuracies.
  • Existing U-Net models lack sufficient feature extraction and boundary recognition for moso bamboo's composite tissues.

Purpose of the Study:

  • To develop an advanced deep learning model for precise instance segmentation of moso bamboo cells.
  • To address challenges posed by blurred boundaries, structural complexity, and overexposure in microscopic bamboo images.
  • To improve quantitative structural analysis of bamboo materials and advance plant phenomics research.

Main Methods:

  • Proposed MBMSA-UNet (Moso Bamboo Multi-Scale Attention U-Net), an enhanced U-Net architecture.
  • Incorporated a multi-scale channel-spatial attention block to manage diverse cell morphologies and scales.
  • Implemented adaptive feature reweighting for improved cross-layer fusion and boundary emphasis.

Main Results:

  • MBMSA-UNet demonstrated superior segmentation accuracy and robustness compared to standard U-Net and its variants.
  • The model effectively handled variations in cell size, shape, and wall thickness within moso bamboo tissues.
  • Suppressed interference from local overexposure and enhanced recognition of inter-cell boundaries.

Conclusions:

  • MBMSA-UNet provides a robust solution for segmenting complex moso bamboo cellular structures.
  • The model facilitates more accurate fine-grained quantitative analysis of bamboo tissues.
  • This advancement supports progress in both plant phenomics and bamboo material science.