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

Association of Circular RNAs with Sperm Fertility Potential: Implications for Male Infertility Diagnosis.

Journal of reproduction & infertility·2026
Same author

A novel lightweight hybrid CNN-ViT for maize leaf disease classification.

Scientific reports·2026
Same author

Sphingolipids and Male Reproductive Health: A Narrative Review of Their Roles in Spermatogenesis, Fertility, and Dysfunction.

Reproductive sciences (Thousand Oaks, Calif.)·2025
Same author

Sphingolipids as key mediators in folliculogenesis and female fertility.

Life sciences·2025
Same author

Application of deep learning for detection of nasal bone fracture on X-ray nasal bone lateral view.

Dento maxillo facial radiology·2025
Same author

Enhancing spermatogonial stem cell differentiation: The role of alpha-ketoglutarate in in-Vitro cultures.

Theriogenology·2025

Related Experiment Video

Updated: Nov 19, 2025

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

6.9K

A robust deep learning-based multiclass segmentation method for analyzing human metaphase II oocyte images.

Sedighe Firuzinia1, Seyed Mahmoodreza Afzali1, Fatemeh Ghasemian2

  • 1Department of Computer Engineering, University of Guilan, Rasht, Iran.

Computer Methods and Programs in Biomedicine
|February 1, 2021
PubMed
Summary

This study introduces an automated deep learning framework for segmenting human metaphase II oocytes, improving accuracy in Intra-Cytoplasmic Sperm Injection (ICSI) assessments. The new method enhances embryo implantation potential analysis.

Keywords:
Convolutional neural networkDilated residual U-Net networkMII oocyte segmentationMulticlass segmentation

More Related Videos

Analysis of Chromosome Segregation, Histone Acetylation, and Spindle Morphology in Horse Oocytes
12:11

Analysis of Chromosome Segregation, Histone Acetylation, and Spindle Morphology in Horse Oocytes

Published on: May 11, 2017

11.2K
Techniques for Imaging Prometaphase and Metaphase of Meiosis I in Fixed Drosophila Oocytes
09:11

Techniques for Imaging Prometaphase and Metaphase of Meiosis I in Fixed Drosophila Oocytes

Published on: October 31, 2016

9.4K

Related Experiment Videos

Last Updated: Nov 19, 2025

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

6.9K
Analysis of Chromosome Segregation, Histone Acetylation, and Spindle Morphology in Horse Oocytes
12:11

Analysis of Chromosome Segregation, Histone Acetylation, and Spindle Morphology in Horse Oocytes

Published on: May 11, 2017

11.2K
Techniques for Imaging Prometaphase and Metaphase of Meiosis I in Fixed Drosophila Oocytes
09:11

Techniques for Imaging Prometaphase and Metaphase of Meiosis I in Fixed Drosophila Oocytes

Published on: October 31, 2016

9.4K

Area of Science:

  • Reproductive biology
  • Medical imaging
  • Artificial intelligence in healthcare

Background:

  • Human metaphase II (MII) oocyte morphology is crucial for predicting embryo development and implantation potential in Intra-Cytoplasmic Sperm Injection (ICSI).
  • Manual assessment of oocyte morphology is subjective and time-consuming.
  • Accurate segmentation of oocyte structures like ooplasm, zona pellucida (ZP), and perivitelline space (PVS) is vital for reliable analysis.

Purpose of the Study:

  • To develop an automated deep learning framework for segmenting human MII oocytes from low-resolution microscopic images.
  • To address the limitations of manual oocyte examination in ICSI procedures.
  • To evaluate the impact of different ground truth annotation types on segmentation performance.

Main Methods:

  • Development of a deep learning network based on an improved U-Net model.
  • Utilized a unique dataset of 1,009 human MII oocyte images with pixel-accurate ground truths.
  • Assessed the performance of binary and multiclass segmentation annotations.

Main Results:

  • The proposed multiclass segmentation algorithm achieved higher accuracy in segmenting complex oocyte structures compared to the two-class version.
  • Experimental results on 250 test images demonstrated superior performance of the developed architecture over U-Net and ENet models.
  • The framework accurately segments ooplasm, ZP, and PVS.

Conclusions:

  • The study presents an automated and accurate method for segmenting human MII oocytes.
  • This deep learning approach offers a significant advancement for ICSI and reproductive medicine research.
  • The findings provide valuable insights into improving objective oocyte assessment.