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 Videos

Automatic classification of human sperm head morphology.

Violeta Chang1, Laurent Heutte2, Caroline Petitjean2

  • 1Department of Computer Science, University of Chile, Beauchef 851, Santiago, Chile; Laboratory for Scientific Image Analysis, (SCIAN-Lab), Centro de Espermiograma Digital Asistido por Internet (CEDAI SpA), Biomedical Neuroscience Institute (BNI), Program of Anatomy and Developmental Biology, Biomedical Science Institute (ICBM), National Center for Health Information Systems (CENS), Faculty of Medicine, University of Chile, Independencia 1027, Santiago, Chile.

Computers in Biology and Medicine
|April 9, 2017
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

A CT Dataset with RECIST Measurements and Comprehensive Segmentation Masks for Tumors and Lymph Nodes.

Scientific data·2026
Same author

Referential Competencies in Digital Health: A Necessity for the Digital Transformation of Future Clinical Professionals.

Studies in health technology and informatics·2025
Same author

Super-resolution Imaging of Proteus mirabilis Biofilm by Expansion Microscopy.

Journal of visualized experiments : JoVE·2025
Same author

Digital Health Competencies: Core to Effective Health Sector Leadership.

Studies in health technology and informatics·2025
Same author

Delayed biofilm formation in non-motile uropathogenic Escherichia coli strain in static and dynamic growth conditions.

Microbial pathogenesis·2025
Same author

Human-in-the-Loop-A Deep Learning Strategy in Combination with a Patient-Specific Gaussian Mixture Model Leads to the Fast Characterization of Volumetric Ground-Glass Opacity and Consolidation in the Computed Tomography Scans of COVID-19 Patients.

Journal of clinical medicine·2024
This summary is machine-generated.

This study developed a novel method for classifying human sperm head morphology, aiding in infertility diagnosis. The system achieves expert-level accuracy, offering a valuable tool for assisted reproduction and research.

Area of Science:

  • Reproductive Biology
  • Medical Imaging
  • Computational Biology

Background:

  • Infertility affects 15% of couples globally, with semen analysis being a crucial first step.
  • Sperm morphology is a key clinical tool for fertility prognosis and guiding assisted reproduction decisions.
  • Accurate analysis of both normal and abnormal sperm morphology is critical for reproductive health assessments.

Purpose of the Study:

  • To develop and implement a novel methodology for characterizing and classifying human sperm heads.
  • To focus on in-depth analysis of abnormal sperm heads for improved fertility diagnosis and prognosis.
  • To create a system applicable to reproductive toxicology, basic research, and public health studies.

Main Methods:

  • A morphological characterization of human sperm heads based on shape measures was introduced.
Keywords:
InfertilitySperm head classificationSperm head morphological descriptorTwo-stage classification

Related Experiment Videos

  • A two-stage classification pipeline was developed, classifying sperm heads into five categories (1 normal, 4 abnormal) based on WHO guidelines.
  • An ensemble strategy for feature selection and a cascade of support vector machines were employed for classification.

    • Main Results:

    • The two-stage classification scheme achieved 58% average accuracy, outperforming some state-of-the-art monolithic classifiers.
    • On data with expert agreement, the system reached 73% average classification accuracy.
    • Fisher's exact test confirmed no statistically significant difference between the system's results and domain expert assessments.

    Conclusions:

    • The developed system demonstrates expert-like performance, serving as a supplementary tool for sperm head labeling.
    • Sperm head classification remains challenging due to expert variability, indicating potential for further system improvement.
    • Future work should explore alternative feature extraction and classification schemes to enhance accuracy.