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

Enhanced digital pathology image recognition via multi-attention mechanisms: the MACC-Net approach.

Scientific reports·2025
Same author

Enhanced boundary-directed lightweight approach for digital pathological image analysis in critical oncological diagnostics.

Journal of X-ray science and technology·2025
Same author

Bone tumor recognition strategy based on object region and context representation in medical decision-making system.

Scientific reports·2025
Same author

FASNet: Feature alignment-based method with digital pathology images in assisted diagnosis medical system.

Heliyon·2024
Same author

Intelligent cell images segmentation system: based on SDN and moving transformer.

Scientific reports·2024
Same author

Research on Artificial-Intelligence-Assisted Medicine: A Survey on Medical Artificial Intelligence.

Diagnostics (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jun 12, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.4K

Semi-supervised recognition for artificial intelligence assisted pathology image diagnosis.

Yao Pan1, Fangfang Gou2, Chunwen Xiao3

  • 1School of Computer Science, Jiangxi University of Traditional Chinese Medicine, Nanchang, 330004, China.

Scientific Reports
|September 20, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a new AI model for cytopathological image analysis, improving accuracy in cell segmentation. The Reliable-Unlabeled Semi-Supervised Segmentation (RU3S) model effectively uses unlabeled data, addressing diagnostic challenges in resource-limited settings.

More Related Videos

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

3.6K
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

2.7K

Related Experiment Videos

Last Updated: Jun 12, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.4K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

3.6K
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

2.7K

Area of Science:

  • Medical Diagnostics
  • Artificial Intelligence
  • Computer Vision

Background:

  • Cytopathological image analysis is vital for medical diagnostics but faces challenges with manual interpretation and data scarcity.
  • Limited medical expertise and the difficulty of acquiring high-quality labeled data hinder accurate cell identification.
  • Current semi-supervised learning models are inefficient in utilizing unlabeled data for improved segmentation.

Purpose of the Study:

  • To introduce an AI-assisted semi-supervised segmentation scheme to enhance cytopathological image analysis.
  • To address the challenge of limited labeled data by effectively leveraging unlabeled samples.
  • To improve the accuracy and efficiency of cell segmentation in medical diagnostics.

Main Methods:

  • Developed the Reliable-Unlabeled Semi-Supervised Segmentation (RU3S) model, integrating ResUNet-SE-ASPP-Attention (RSAA).
  • The RSAA model incorporates Squeeze-and-Excitation (SE), Atrous Spatial Pyramid Pooling (ASPP), and Attention modules within a ResUNet architecture.
  • Implemented a novel confidence filtering strategy to optimize the utilization of unlabeled data.

Main Results:

  • The RU3S model demonstrated significant improvements in accuracy by effectively leveraging unlabeled data.
  • Achieved a 2.0% increase in mean Intersection over Union (mIoU) accuracy compared to the state-of-the-art semi-supervised segmentation model (ST).
  • The confidence filtering strategy enhanced the exploitation of unlabeled samples, mitigating data scarcity issues.

Conclusions:

  • The proposed RU3S model offers an effective solution for cytopathological image segmentation, particularly in data-scarce environments.
  • The integration of advanced deep learning components and a novel filtering strategy significantly boosts segmentation performance.
  • This AI-driven approach holds promise for improving diagnostic accuracy and addressing healthcare disparities.