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: Jul 16, 2026

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material
11:12

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material

Published on: August 1, 2018

Breast Cancer Hormone Receptor Status Determination from H&E-Stained Biopsy Images Using Pixel-Level Classifiers.

Shuyang Wu1, Ines P Nearchou2, Sandrine Prost1

  • 1Centre for Inflammation Research, Institute of Regeneration and Repair, University of Edinburgh, Edinburgh EH16 4UU, UK.

Cancers
|July 15, 2026
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

Deciphering cytochrome P450 reductase role in MASLD: molecular mechanisms and pathophysiological implications.

Nature reviews. Gastroenterology & hepatology·2026
Same author

Multiplexed P21/MCM-2 Detection Predicts Relapse and May Identify Tyrosine Kinase Inhibitor-Resistant Patients in Clear Cell Renal Cell Carcinoma.

Cancer research communications·2026
Same author

Mutational scanning reveals oncogenic CTNNB1 mutations have diverse effects on signaling.

Nature genetics·2026
Same author

Long-Read Spatial Transcriptomics of Patient-Derived Clear Cell Renal Cell Carcinoma Organoids Identifies Heterogeneity and Transcriptional Remodelling Following NUC-7738 Treatment.

Cancers·2026
Same author

Cholangiocarcinoma 2026: status quo, unmet needs and priorities.

Nature reviews. Gastroenterology & hepatology·2025
Same author

Endometrial whole-slide images dataset for detection of malignancy in endometrial biopsies.

GigaScience·2025

This study developed a pixel-based classifier to predict hormone receptor status (oestrogen receptor, progesterone receptor, HER2) in breast cancer directly from H&E-stained biopsy images, showing promising results on internal and external datasets.

Area of Science:

  • Digital pathology and computational analysis
  • Breast cancer diagnostics
  • Biomarker quantification

Background:

  • Increasing adoption of digital pathology workflows and whole-slide imaging.
  • Current assessment of hormone receptor status (ER, PR, HER2) relies on manual pathologist scoring of immunohistochemically stained sections.
  • Need for efficient and accurate biomarker assessment in breast carcinoma.

Purpose of the Study:

  • To develop and evaluate a nested pixel classifier for predicting oestrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status.
  • To enable direct prediction from H&E-stained biopsy sections, bypassing the need for immunohistochemistry.
  • To assess the model's performance on both internal and external datasets using different scanner hardware.

Main Methods:

Keywords:
breast cancerdigital pathologyhormone receptor status predictionmachine learningslide-level prediction

More Related Videos

Mast Cells in the Microenvironment of Hepatocellular Carcinoma Confer Favorable Prognosis: A Retrospective Study using QuPath Image Analysis Software
07:32

Mast Cells in the Microenvironment of Hepatocellular Carcinoma Confer Favorable Prognosis: A Retrospective Study using QuPath Image Analysis Software

Published on: April 12, 2024

Related Experiment Videos

Last Updated: Jul 16, 2026

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material
11:12

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material

Published on: August 1, 2018

Mast Cells in the Microenvironment of Hepatocellular Carcinoma Confer Favorable Prognosis: A Retrospective Study using QuPath Image Analysis Software
07:32

Mast Cells in the Microenvironment of Hepatocellular Carcinoma Confer Favorable Prognosis: A Retrospective Study using QuPath Image Analysis Software

Published on: April 12, 2024

  • Utilized pathologist-verified pixel-level annotations to train nested pixel classifiers.
  • Employed biopsy cases stained with Hematoxylin and Eosin (H&E) for model training.
  • Evaluated model performance using Area Under the Curve (AUC) on internal and external test sets, including a diverse international cohort.

Main Results:

  • Achieved AUCs of 0.8030 for ER, 0.7956 for PR, and 0.7488 for HER2 on the internal test set.
  • Demonstrated predictive capabilities on an external cohort with AUCs of 0.7008 for ER and 0.7488 for PR, despite different scanner hardware and no training data from the external institution.
  • Highlighted the potential and challenges of using pixel-based classifiers for case-level predictions.

Conclusions:

  • A pixel-based classifier can be adapted for case/slide-level predictions of hormone receptor status in breast carcinoma.
  • The developed model shows potential for direct prediction from H&E-stained biopsy images, offering a complementary approach to traditional methods.
  • Challenges remain in generalizing pixel-based classifiers across different datasets and scanner hardware without image normalization.