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

Toward Accurate Deep Learning-Based Prediction of Ki67, ER, PR, and HER2 Status From H&E-Stained Breast Cancer Images.

Applied immunohistochemistry & molecular morphology : AIMM·2025
Same author

Molecular dissection of cobra venom highlights heparinoids as an antidote for spitting cobra envenoming.

Science translational medicine·2024
Same author

Fit-for-Purpose Ki-67 Immunohistochemistry Assays for Breast Cancer.

Laboratory investigation; a journal of technical methods and pathology·2024
Same author

Dermonecrosis caused by a spitting cobra snakebite results from toxin potentiation and is prevented by the repurposed drug varespladib.

Proceedings of the National Academy of Sciences of the United States of America·2024
Same author

Is Oncotype DX testing informative for breast cancers with low ER expression? A retrospective review from a biomarker testing referral center.

Breast (Edinburgh, Scotland)·2024
Same author

Repurposed drugs and their combinations prevent morbidity-inducing dermonecrosis caused by diverse cytotoxic snake venoms.

Nature communications·2023

Related Experiment Video

Updated: Aug 25, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Using Deep Learning to Predict Final HER2 Status in Invasive Breast Cancers That are Equivocal (2+) by

Sean A Rasmussen1, Valerie J Taylor1, Alexi P Surette2

  • 1Queen Elizabeth II Health Sciences Centre and Dalhousie University, Halifax, Nova Scotia, Canada.

Applied Immunohistochemistry & Molecular Morphology : AIMM
|October 17, 2022
PubMed
Summary

A deep learning model predicts HER2 gene amplification directly from IHC slides, showing promise for triaging breast cancer cases. This AI approach could aid treatment planning where in situ hybridization testing is limited.

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

180
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

6.9K

Related Experiment Videos

Last Updated: Aug 25, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

180
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

6.9K

Area of Science:

  • Computational pathology
  • Oncology
  • Biomarker analysis

Background:

  • Human Epidermal growth factor Receptor 2 (HER2) testing is crucial for invasive breast carcinoma treatment decisions.
  • Immunohistochemistry (IHC) and in situ hybridization (ISH) are standard HER2 tests, but ISH is costly and time-consuming.
  • Equivocal (2+) IHC results necessitate ISH, creating a bottleneck in diagnostic workflows.

Purpose of the Study:

  • To develop and validate a deep learning algorithm for direct prediction of HER2 gene amplification status from HER2 2+ IHC slides.
  • To assess the feasibility of using artificial intelligence to streamline HER2 testing in breast cancer diagnostics.
  • To potentially reduce reliance on expensive and time-consuming ISH procedures.

Main Methods:

  • A convolutional neural network (CNN) using EfficientNet B0 architecture was trained on digitized HER2 2+ IHC slides.
  • Transfer learning was employed, with patches extracted for training and 5-fold cross-validation.
  • An internal dataset of 115 cases and an external validation set of 36 cases were utilized.

Main Results:

  • The model achieved an Area Under the Curve (AUC) of 0.83 with 79% accuracy on the internal test set.
  • External validation yielded an AUC of 0.79 with 81% accuracy.
  • Sensitivity and specificity, while promising, were not sufficient to replace ISH entirely.

Conclusions:

  • Direct prediction of HER2 gene amplification from IHC using deep learning is a viable approach.
  • This AI method shows potential for triaging cases and guiding early treatment planning, especially in resource-limited settings.
  • Further refinement is needed to enhance sensitivity and specificity for potential replacement of reflexive ISH testing.