Skip to content
  • News
  • Blog
  • Contact Us
  • My Cart
  • Login
Official MSERM Website
  • Home
    • About Us
      • History
      • Quality Chart
      • Mission and Vision
      • What we do ?
      • Our Main Goals
      • Our Vision and Mission and Values
      • President Message
      • Leadership
      • Our Founders
      • Our Team Active members
      • Our Structure in Strategic Plan & Initiatives
      • Chairman’s Statement Executive Committee
      • Social media for the MSERM
    • Committees
      • Executive Committee
    • Statutes – MSERM
    • Partner Societies
  • Membership
    • Login
    • About MSERM Membership
    • FAQ
    • Terms & Conditions
    • Policy
  • Special Groups
    • Endometriosis and Endometrial Disorders
    • Endoscopic Surgery
    • ART
    • Implantation and Early Pregnany
    • Reproductive Endocrinology
    • Fertility Preservation
    • Embryology
    • Genetics and Reproductive Medicine
    • Andrology
  • MSERM Diplomas
    • Professional Diploma in Development of Obstetrics and Gynecology (PDDOG)
    • Diploma of Endometriosis, Clinical Aspects, Imaging Diagnostic and Surgery Management (DEITS)
    • Diploma of Clinical Embryology, Reproductive Genetics & Andrology (DERGA)
    • Diploma for Obstetric Anesthesia & Critical Care (DOACC)
    • Diploma of Reproductive Surgery (DRS)
  • Annual Meeting
    • MSERM 2022 Hybrid
    • MSERM 2023
    • MSERM 2024
    • MSERM 2025
  • MSERM Services
    • MSERM Scientific Books
    • Shop
    • MSERM Educations
      • Prof Eman Elgindy
      • Certification
      • MSERM TV
      • Workshops
        • 12th MSERM Workshop – Advanced course on “Severe Oligozoospermia & Reproductive Genetics”
        • 11th MSERM Workshop – Advanced course on “Revolution in Endometriosis and Infertility”
        • 9th MSERM Workshop – Endometriosis and Infertility
        • 8th MSERM Workshop – PRACTICE OF CYTOGENETICS
        • 7th MSERM Workshop & LABOMAC
        • 6th MSERM WORKSHOP – Clinical and Biological Aspects of Performing an Efficient Oocyte Pick Up -OPU
        • 5th Workshop – Clinical Embryology and Reproductive Genetics
        • 4th MSERM workshop – Virtual event – Ovarian Endometriosis
        • 3rd Workshop – Elective Oocyte Cryopreservation for Age-Related Fertility
      • FAQ
      • Presentations
    • Art Lab Posters
    • MSERM Webcast
    • Exam Preparation
    • Our Achievements
    • E-learning Platform
      • Certified Obstetrics and Gynecology Practitioners
      • Certified Obstetric Anesthesiologists Practitioners
      • Certified Clinical Embryologists Practitioners
      • Certified Reproductive Biology Practitioners
    • Research
  • MSERM Research Portal
    • Journals
    • Guidelines

Blog

  • Home
  • Art Lab Posters
  • MSERM – External Validation of an AI System for Blastocyst Implantation Prediction
Art Lab Posters

MSERM – External Validation of an AI System for Blastocyst Implantation Prediction

September 1, 2022admin

Track: ART – LAB, Assisted Reproductive Technology
Poster : ART Lab: Technology
Chloe Hardy
Clinical Embryologist
Cambridge IVF
Cambridge, United Kingdom

Objective: To assess the performance in a clinical setting of IVFvision.ai, an artificial intelligence (AI) system for blastocyst selection DESIGN: Retrospective analysis of single blastocyst transfer (SBT) images MATERIALS AND

Methods: Convolutional Neural Networks were used to develop IVFvision.ai, an algorithm that differentiates between Day-5 blastocysts with a positive or negative implantation outcome. Implantation was confirmed by the presence of an embryonic sac with heartbeat. External validation of IVFvision.ai was performed at a University IVF Clinic using 113 anonymised Embryoscope images of SBT. Assessed images were taken at 116±h hours post-insemination at the equatorial focal plane. The predictive ability and reliability of IVFvision.ai to correctly classify blastocysts according to implantation outcome were compared to the KIDScoreD5 v2 prediction algorithm, as well as three expert Clinical Embryologists. AUC for each predictor was estimated using ROC curve analysis. Sensitivity, specificity, PPV, NPV and accuracy were calculated using crosstabs. Reliability of IVFvision.ai and embryologist assessments was calculated by the Interclass correlation coefficient (ICC). Stepwise logistic regression was used to model predictors significantly associated with implantation controlling for maternal age and fertilisation method.

Results: IVFvision.ai had higher AUC and overall accuracy in predicting implantation compared to KIDScoreD5 and all embryologists (Table 1). The reliability of IVFvision.ai was perfect (ICC = 1.00, 95% CI 1.00 to 1.00), consistently returning the same classification after a triple reading process. The reliability between 3 embryologists was moderate (ICC = 0.744, 95% CI 0.606 to 0.838), significantly lower than that of IVFvision.ai. Stepwise logistic regression showed that only IVFvision.ai prediction (p=0.008) and fertilisation method (p=0.051) were significantly associated with implantation. The combined model IVFvision.ai+Fert had an AUC 0.740.
Table 1: Predictive characteristics

Track: ART – LAB, Assisted Reproductive Technology
Poster : ART Lab: Technology
Chloe Hardy
Clinical Embryologist
Cambridge IVF
Cambridge, United Kingdom

Objective: To assess the performance in a clinical setting of IVFvision.ai, an artificial intelligence (AI) system for blastocyst selection DESIGN: Retrospective analysis of single blastocyst transfer (SBT) images MATERIALS AND

Methods: Convolutional Neural Networks were used to develop IVFvision.ai, an algorithm that differentiates between Day-5 blastocysts with a positive or negative implantation outcome. Implantation was confirmed by the presence of an embryonic sac with heartbeat. External validation of IVFvision.ai was performed at a University IVF Clinic using 113 anonymised Embryoscope images of SBT. Assessed images were taken at 116±h hours post-insemination at the equatorial focal plane. The predictive ability and reliability of IVFvision.ai to correctly classify blastocysts according to implantation outcome were compared to the KIDScoreD5 v2 prediction algorithm, as well as three expert Clinical Embryologists. AUC for each predictor was estimated using ROC curve analysis. Sensitivity, specificity, PPV, NPV and accuracy were calculated using crosstabs. Reliability of IVFvision.ai and embryologist assessments was calculated by the Interclass correlation coefficient (ICC). Stepwise logistic regression was used to model predictors significantly associated with implantation controlling for maternal age and fertilisation method.

Results: IVFvision.ai had higher AUC and overall accuracy in predicting implantation compared to KIDScoreD5 and all embryologists (Table 1). The reliability of IVFvision.ai was perfect (ICC = 1.00, 95% CI 1.00 to 1.00), consistently returning the same classification after a triple reading process. The reliability between 3 embryologists was moderate (ICC = 0.744, 95% CI 0.606 to 0.838), significantly lower than that of IVFvision.ai. Stepwise logistic regression showed that only IVFvision.ai prediction (p=0.008) and fertilisation method (p=0.051) were significantly associated with implantation. The combined model IVFvision.ai+Fert had an AUC 0.740.
Table 1: Predictive characteristics

Post navigation

MSERM – A Promising Ligand and Microfluidics Sperm Sex Selection Method
MSERM – Laser Assisted Hatching of Human Embryos at Fertilization Check, on Day 1 of Culture, Allows For Continuous Uninterrupted Time-Lapse Incubation of 5+ Days, While Producing Hatching Blastocysts as Expected

The MSERM Secretariat

Moroccan Society for Endometriosis and Reproductive Medicine
1,Mansour Saadi Street, Racine, Casablanca, Morocco. CP 20100
Tel: +212 522 397 339
info@mserm.org

MSERM conferences:
Mob: +212 669 856 255
www.mserm-congress.org
mserm-congress@mserm.org

Recent Posts

  • MSERM- Professional Diploma in Imaging of Endometriosis – PDIE
  • MSERM Diploma for Obstetric Anesthesia & Critical Care – DOACC
  • MSERM Diploma in Senior Clinical Embryology – DSCE
  • MSERM Professional Diploma in Development of Obstetrics and Gynecology – PDDOG
  • le E-examen international organisé par la Société Marocaine pour l’Endometriose et la Médecine Reproduction MSERM 2023

MSERM

Welcome to the Moroccan Society for Endometriosis and Reproductive Medicine (MSERM) Initiated for conducting Hybrid events globally. Our attendees include academicians, professors, students, and Industrialists who come together to join and share their knowledge. Our organization believes in imparting holistic and sustainable development with the mission to ignite young Turks and prepare them for future challenges.

Quick Links

  • Certified Embryology Practitioners
  • Shop
  • Education
  • Webcast
  • MSERM – CGV
  • MSERM – PowerPoint Template
  • Request MSERM Membership Card

Photo Gallery

Check more photos here

Contact Info

1,Mansour Saadi Street, Racine, Casablanca, Morocco. CP 20100
Email: info@mserm.org
Tel: +212 6 69 85 62 55
Working Hours: Mon-Sat: 9.30 - 19.00

© All right reserved

 | MSERM

  • Refund Policy
  • Privacy Policy
  • Terms & Conditions

Event Booking

    Notifications