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

Including tumor-infiltrating lymphocytes into the PREDICT prognostic model for triple-negative breast cancer survival.

Annals of oncology : official journal of the European Society for Medical Oncology·2026
Same author

Prognostic role of serum thymidine kinase 1 kinetics during neoadjuvant chemotherapy for early breast cancer.

ESMO open·2021
Same author

Artificial intelligence as the next step towards precision pathology.

Journal of internal medicine·2020
Same author

Anodic cyclization reactions: reversing the polarity of ketene dithioacetal groups.

Organic letters·2001
Same author

Assessment of total energy expenditure in a Chinese population by a physical activity questionnaire: examination of validity.

International journal of food sciences and nutrition·2001
Same author

Downregulation of the ERK 1 and 2 mitogen activated protein kinases using antisense oligonucleotides inhibits proliferation of porcine vascular smooth muscle cells.

Atherosclerosis·2001
Same journal

The ethical obligation to use positive trial results.

Annals of oncology : official journal of the European Society for Medical Oncology·2026
Same journal

Lorlatinib: The Crown Jewel of ALK Inhibitors.

Annals of oncology : official journal of the European Society for Medical Oncology·2026
Same journal

TROP2-Directed Antibody Drug Conjugates: New First-Line Treatment for All Patients with Advanced Triple-Negative Breast Cancer?

Annals of oncology : official journal of the European Society for Medical Oncology·2026
Same journal

When artificial intelligence learns to abstain: towards clinically responsible diagnostic support in liver pathology.

Annals of oncology : official journal of the European Society for Medical Oncology·2026
Same journal

PRMT5 inhibitors in MTAP loss NSCLC with actionable genomic alterations: a new kid on the block?

Annals of oncology : official journal of the European Society for Medical Oncology·2026
Same journal

Refining decision making in hormone receptor-positive early-stage breast cancer: moving from static to dynamic.

Annals of oncology : official journal of the European Society for Medical Oncology·2026
See all related articles

Related Experiment Video

Updated: Oct 13, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

382

Improved breast cancer histological grading using deep learning.

Y Wang1, B Acs2, S Robertson2

  • 1Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.

Annals of Oncology : Official Journal of the European Society for Medical Oncology
|November 10, 2021
PubMed
Summary
This summary is machine-generated.

A new deep learning model, DeepGrade, improves breast cancer risk stratification for intermediate-grade (NHG 2) tumors. DeepGrade identifies patients with higher recurrence risk, offering a cost-effective alternative to molecular profiling for clinical decisions.

Keywords:
artificial intelligencebreast cancerdeep learningdigital pathologyhistological grade

More Related Videos

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

760
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

6.5K

Related Experiment Videos

Last Updated: Oct 13, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

382
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

760
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

6.5K

Area of Science:

  • Digital pathology
  • Artificial intelligence in oncology
  • Breast cancer prognostics

Background:

  • The Nottingham histological grade (NHG) is a standard prognostic tool for breast cancer.
  • Approximately 50% of breast cancer patients fall into the intermediate-risk NHG 2 category, limiting clinical decision-making.
  • There is a need for improved risk stratification within the NHG 2 group.

Purpose of the Study:

  • To develop and validate a novel deep learning model, DeepGrade, for improved risk stratification of NHG 2 breast cancer patients.
  • To assess the prognostic value of DeepGrade by stratifying NHG 2 cases into high and low recurrence risk groups.

Main Methods:

  • Utilized digital whole-slide histopathology images (WSIs) from 1567 patients for model development and internal validation.
  • Externally validated the model's generalizability using WSIs from an additional 1262 patients.
  • Stratified NHG 2 cases into DG2-high and DG2-low groups and analyzed recurrence-free survival.

Main Results:

  • DeepGrade provided independent prognostic information, stratifying NHG 2 cases into DG2-high and DG2-low groups.
  • DG2-high patients demonstrated a significantly increased risk of recurrence compared to DG2-low patients in both internal (HR 2.94) and external (HR 1.91) test sets.
  • The model identified morphological patterns in NHG 2 tumors associated with more aggressive disease, similar to NHG 1 and NHG 3 phenotypes.

Conclusions:

  • DeepGrade offers prognostic stratification for NHG 2 breast cancer patients, adding clinically relevant information beyond routine histological grading.
  • The model's ability to identify high-risk patients provides valuable insights for clinical decisions.
  • DeepGrade presents a cost-effective alternative to molecular profiling for extracting prognostic information from histopathology images.