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

Evaluating the quality and readability of AI-generated information on adenomyosis: a comparative analysis of ChatGPT and deepseek regarding query-model consistency.

Frontiers in public health·2026
Same author

Comparisons of CEAS, PC-CLD, and CRDS for NO<sub>2</sub> measurements under a complex atmosphere in Chengdu, China.

Journal of environmental sciences (China)·2026
Same author

Paternal intergenerational thyroid disruption in zebrafish induced by environmental prednisone exposure.

Aquatic toxicology (Amsterdam, Netherlands)·2026
Same author

Reproductive tract commensal bacterium Enterococcus faecium supernatant induces DNA damage associated stress responses and suppresses the growth of cervical cancer cells.

BMC microbiology·2026
Same author

A fusion model of deep learning and conventional features based on computed tomography angiography of carotid plaque for predicting the risk of acute ischemic stroke.

Quantitative imaging in medicine and surgery·2026
Same author

Delayed Surveillance for 4 Years Resulting in Synchronous Heterogeneous Gastric Epithelial Neoplasms in a Patient with Familial Adenomatous Polyposis.

Digestive diseases and sciences·2026
Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026
Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026
Same journal

Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

Medical image analysis·2026
Same journal

HyperCOCO: Multi-sensory HyperCOgnitive COmputing for learning population level brain connectivity.

Medical image analysis·2026
Same journal

PANTHER Challenge Report: Cross-Domain Pancreatic Tumor Segmentation in Magnetic Resonance Imaging.

Medical image analysis·2026
Same journal

DGCD-3D: Difference-guided conditional diffusion model for low-field 3D MRI enhancement to assist stroke assessment.

Medical image analysis·2026
See all related articles

Related Experiment Video

Updated: Apr 3, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

874

MOTDNet: Multi organ task decoupling network for cell segmentation.

Jinlin Yang1, Xintao Pang2, Chuan Lin1

  • 1School of Automation, Guangxi University of Science and Technology, Liuzhou, 545006, China.

Medical Image Analysis
|April 1, 2026
PubMed
Summary
This summary is machine-generated.

MOTDNet enhances histopathology image analysis by decoupling cell segmentation tasks. This novel network achieves state-of-the-art results in cell type identification and segmentation across diverse datasets.

Keywords:
Cell segmentationComputational pathologyMedical images,Multi-task learning

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Related Experiment Videos

Last Updated: Apr 3, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

874
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Area of Science:

  • Digital Pathology
  • Computer Vision
  • Medical Image Analysis

Background:

  • Accurate cell detection and segmentation in Hematoxylin and Eosin (H&E) stained histopathology images are crucial for clinical diagnosis.
  • Current methods often use a single decoder for nucleus shape capture, overlapping nucleus separation, and type identification, leading to gradient conflicts and reduced accuracy.
  • These limitations hinder the precise analysis of cellular structures in complex tissue samples.

Purpose of the Study:

  • To introduce MOTDNet, a novel heterogeneous task decoupling network for improved cell segmentation and classification in histopathology.
  • To address the limitations of existing methods by employing task-specific decoders and specialized convolutional techniques.
  • To enable accurate segmentation and identification of 5 cell types across 19 tissue types.

Main Methods:

  • Developed MOTDNet, a network incorporating directional pixel differential convolution (DPDC) and outer product convolution (OPC) with task-specific decoders.
  • Designed a CNN-SSM block for precise cell shape capture.
  • Utilized directional differential convolution for separating overlapping nuclei and outer product convolution for extracting contextual information.
  • Integrated the watershed algorithm for final prediction generation.

Main Results:

  • MOTDNet demonstrated strong performance on medical datasets (PanNuke, MoNuSeg, Kumar, CPM17) and competitive results on non-medical datasets (NYU-V2, Cityscape).
  • Achieved state-of-the-art (SOTA) performance on the PanNuke dataset, with an F-1 score of 0.83 and a mean panoptic quality of 0.4999.
  • The model is computationally efficient, requiring only 13 GFLOPs and 32M parameters.

Conclusions:

  • MOTDNet effectively decouples heterogeneous tasks in cell segmentation, overcoming gradient conflicts and improving accuracy.
  • The proposed network architecture and specialized convolutions offer a robust solution for cell segmentation and classification in histopathology.
  • This approach advances automated analysis of H&E stained images, supporting clinical pathology workflows.