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 Experiment Video

Updated: Sep 6, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.2K

Fast Noninvasive Morphometric Characterization of Free Human Sperms Using Deep Learning.

Guole Liu1,2, Hao Shi3, Huan Zhang4

  • 1School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China.

Microscopy and Microanalysis : the Official Journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada
|June 24, 2022
PubMed
Summary

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

ATACompass enables cross-species cell identity mapping for scATAC-seq without gene annotations.

Cell reports methods·2026
Same author

Diffusion prior-based zero-shot denoising for real-world fluorescence microscopy images via encoder-decoder guided sampling.

Biomedical optics express·2026
Same author

CellPolaris: Transfer Learning for Gene Regulatory Network Construction to Guide Cell State Transitions.

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

Artificial Intelligence-Enhanced Quantitative 3D Analysis of Distal Radioulnar Ligament Insertion Footprints of the Triangular Fibrocartilage Complex With Interactive Validation.

Orthopaedic surgery·2025
Same author

Cell-GraphCompass: modeling single cells with graph structure foundation model.

National science review·2025
Same author

Endoplasmic reticulum junctions serve as a platform for endosome-lysosome interactions through their stop-and-go motion switching.

Science advances·2025

This study introduces a deep learning method for automated sperm selection in in vitro fertilization (IVF). The AI tool enhances objectivity and efficiency in identifying high-quality sperm for improved treatment outcomes.

Area of Science:

  • Reproductive Medicine
  • Artificial Intelligence in Healthcare
  • Biomedical Imaging Analysis

Background:

  • Intracytoplasmic sperm injection (ICSI), a key component of in vitro fertilization (IVF), relies heavily on selecting high-quality sperm.
  • Manual sperm screening by clinicians lacks objectivity, consistency, and efficiency, hindering optimal IVF success rates.

Purpose of the Study:

  • To develop a fast, noninvasive deep learning method for automated characterization of human sperm morphology from bright-field microscopy images.
  • To overcome the limitations of manual sperm screening and provide an efficient tool for selecting viable sperm for ICSI.

Main Methods:

  • A three-stage deep learning approach was employed: object detection for sperm head identification, classification for in-focus image selection, and segmentation for extracting sperm head and vacuole geometry.
Keywords:
bright-field microscopydeep learninghuman spermintracytoplasmic sperm injectionsperm morphology

More Related Videos

Flow Cytometric Analysis of Biomarkers for Detecting Human Sperm Functional Defects
08:48

Flow Cytometric Analysis of Biomarkers for Detecting Human Sperm Functional Defects

Published on: April 21, 2022

2.7K
Techniques for Imaging Ca2+ Signaling in Human Sperm
07:38

Techniques for Imaging Ca2+ Signaling in Human Sperm

Published on: June 16, 2010

17.2K

Related Experiment Videos

Last Updated: Sep 6, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.2K
Flow Cytometric Analysis of Biomarkers for Detecting Human Sperm Functional Defects
08:48

Flow Cytometric Analysis of Biomarkers for Detecting Human Sperm Functional Defects

Published on: April 21, 2022

2.7K
Techniques for Imaging Ca2+ Signaling in Human Sperm
07:38

Techniques for Imaging Ca2+ Signaling in Human Sperm

Published on: June 16, 2010

17.2K
  • Customized lightweight neural network architectures were utilized to enable real-time analysis at 200 frames per second.

    • Main Results:

    • The models achieved high performance metrics: an F1-score of 0.951 for sperm head detection and a Dice score of 0.948 for sperm head segmentation.
    • Accurate in-focus image selection was demonstrated with a z-position estimation error within ±1.5 μm.
    • Comprehensive morphological parameters were derived from the segmented sperm head geometry.

    Conclusions:

    • The developed deep learning method offers a reliable and efficient solution for assisting clinicians in selecting high-quality sperm for successful IVF.
    • This study highlights the efficacy of deep learning in real-time analysis of live microscopy images for reproductive applications.