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

Milk mid-chain fatty acids and vitamin D supplementation are associated with prevalence of exclusive breastfeeding in Bangladeshi mothers.

The British journal of nutrition·2026
Same author

The role of micronutrient deficiencies in nutritional anemia beyond iron: An expert perspective on the scope and strength of the current evidence.

Advances in nutrition (Bethesda, Md.)·2026
Same author

Dual Adjacent Capture Probe-Induced Hybridization Chain Reaction in a Cyclic Array Reactor for Rapid and Sensitive Fluorescence Detection of Norovirus in Aquatic Food.

Analytical chemistry·2026
Same author

Machine learning identification of maternal inflammatory response and systemic inflammatory response from placental membrane whole slide images.

Placenta·2026
Same author

Engineering the human placenta: Advances in modeling placental function.

Placenta·2026
Same author

Mapping the flow of painterly gesture.

Patterns (New York, N.Y.)·2026

Related Experiment Video

Updated: Nov 25, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

817

Multi-region saliency-aware learning for cross-domain placenta image segmentation.

Zhuomin Zhang1, Dolzodmaa Davaasuren1, Chenyan Wu1

  • 1The Pennsylvania State University, University Park, PA, USA.

Pattern Recognition Letters
|December 16, 2020
PubMed
Summary
This summary is machine-generated.

We developed a new method for placenta image segmentation that improves accuracy by focusing on key regions. This approach enhances segmentation and prediction of fetal and maternal inflammatory response.

Keywords:
PathologyPhoto image analysisPlacentaTransfer learning

More Related Videos

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

3.2K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.4K

Related Experiment Videos

Last Updated: Nov 25, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

817
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

3.2K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.4K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Accurate segmentation of placenta images is crucial for diagnosing fetal and maternal inflammatory response (FIR, MIR).
  • Existing cross-domain transfer learning methods often fail to preserve semantic details of paired regions during image translation.
  • There is a need for advanced methods to improve multi-region semantic mapping in medical image analysis.

Purpose of the Study:

  • To introduce a novel multi-region saliency-aware learning (MSL) method for cross-domain placenta image segmentation.
  • To enhance the preservation of semantic information across different domains in medical image translation.
  • To improve the accuracy of segmentation and prediction of placental diagnoses like FIR and MIR.

Main Methods:

  • The MSL method incorporates an attention mechanism to identify discriminative semantic regions.
  • Attention consistency is used as a guidance for retaining semantics post-translation.
  • A saliency-consistent constraint is employed to maintain the integrity of salient regions during adversarial translation.

Main Results:

  • The proposed MSL method demonstrated superior performance in placenta image segmentation compared to state-of-the-art approaches.
  • Experiments on real-world placenta datasets confirmed the efficacy of MSL in improving segmentation accuracy.
  • The method showed significant improvements in predicting placental diagnoses, specifically FIR and MIR.

Conclusions:

  • The MSL method effectively addresses the limitations of existing transfer learning techniques in medical image segmentation.
  • The integration of attention and saliency constraints enables robust multi-region semantic mapping.
  • MSL offers a promising advancement for automated analysis and diagnosis in placental imaging.