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

  1. Home
  3. Research Domains
  5. Biomedical And Clinical Sciences
  7. Oncology And Carcinogenesis
  9. Predictive And Prognostic Markers
  11. Prediction Of Mismatch Repair Status In Endometrial Cancer From Histological Slide Images Using Various Deep Learning-based Algorithms

Prediction of Mismatch Repair Status in Endometrial Cancer from Histological Slide Images Using Various Deep Learning-Based Algorithms

Mina Umemoto1, Tasuku Mariya1, Yuta Nambu2

  • 1Department of Obstetrics and Gynecology, Sapporo Medical University of Medicine, Sapporo 060-8556, Japan.

Cancers
|May 25, 2024

Related Experiment Videos

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells
07:46

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells

Published on: October 13, 2023

1.2K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Multiplexed Fluorescent Immunohistochemical Staining of Four Endometrial Immune Cell Types in Recurrent Miscarriage
05:16

Multiplexed Fluorescent Immunohistochemical Staining of Four Endometrial Immune Cell Types in Recurrent Miscarriage

Published on: August 4, 2021

3.3K

View abstract on PubMed

Summary
This summary is machine-generated.

Deep learning accurately predicts mismatch repair (MMR) deficiency in endometrial cancer using H&E slides. This AI approach offers a cost-effective pre-screening tool for molecular profiling.

Area of Science:

  • Computational pathology
  • Oncology
  • Digital pathology

Background:

  • Deep learning models predict molecular cancer profiles from H&E slides, primarily for gastric and colon cancers.
  • Mismatch repair (MMR) status is crucial for guiding endometrial cancer treatment.
  • Current methods for MMR status determination can be costly and time-consuming.

Purpose of the Study:

  • To investigate the efficacy of deep learning algorithms in predicting MMR status directly from H&E-stained endometrial cancer images.
  • To develop and validate a computational model for MMR status prediction in endometrial cancer.

Main Methods:

  • H&E-stained endometrial cancer slide images from 127 cases were digitized.
  • Images were segmented into tiles, and MMR protein (PMS2, MSH6) status was determined via immunohistochemistry and annotated.
Keywords:
artificial intelligencebiomarkerdeep learningdigital pathology

Related Experiment Videos

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells
07:46

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells

Published on: October 13, 2023

1.2K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Multiplexed Fluorescent Immunohistochemical Staining of Four Endometrial Immune Cell Types in Recurrent Miscarriage
05:16

Multiplexed Fluorescent Immunohistochemical Staining of Four Endometrial Immune Cell Types in Recurrent Miscarriage

Published on: August 4, 2021

3.3K
  • Various neural networks, including ResNet50, were trained using annotated image tiles to predict MMR status.

    • Main Results:

    • ResNet50 achieved the highest performance with an area under the receiver operating characteristic curve (AUROC) of 0.91 for predicting MMR status.
    • The model demonstrated significant accuracy in classifying endometrial cancer cases based on MMR proficiency/deficiency from digital slides.

    Conclusions:

    • Deep learning models can accurately predict MMR status in endometrial cancer from H&E images.
    • This AI-driven approach shows potential as a cost-effective pre-screening tool, potentially reducing the need for immediate genetic profiling.
    • The methodology may be adaptable for predicting other molecular profiles in various cancer types.
    endometrial cancer
    mismatch repair
    molecular classification
    whole-slide imaging