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

How to benchmark medical AI agents.

PLoS medicine·2026
Same author

AI-based selection of tumor regions for genomic profiling in neuropathology.

Neuro-oncology advances·2026
Same author

Hepatic multimodal phenotyping in AL amyloidosis with cardiac involvement: the D-Amy-LIPHE study.

Amyloid : the international journal of experimental and clinical investigation : the official journal of the International Society of Amyloidosis·2026
Same author

Author Correction: Teclistamab-based induction treatment in transplant-eligible, newly diagnosed multiple myeloma: a phase 2 trial.

Nature medicine·2026
Same author

Excess Weight May Account for More Than 10% of All Cancers: The Underestimated Impact of the Obesity Epidemic.

Cancer communications (London, England)·2026
Same author

Clinical decision support in hematological malignancies using a case-grounded AI agent.

Nature medicine·2026

Related Experiment Video

Updated: Jul 3, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K

Regression-based Deep-Learning predicts molecular biomarkers from pathology slides.

Omar S M El Nahhas1, Chiara M L Loeffler1,2, Zunamys I Carrero1

  • 1Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.

Nature Communications
|February 10, 2024
PubMed
Summary

Deep learning regression accurately predicts continuous cancer biomarkers from histopathology images, outperforming classification methods. This approach enhances prognostic value and offers a promising tool for computational pathology analysis.

More Related Videos

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
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

755

Related Experiment Videos

Last Updated: Jul 3, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K
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
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

755

Area of Science:

  • Computational pathology
  • Digital pathology
  • Artificial intelligence in oncology

Background:

  • Deep learning (DL) is increasingly used to predict biomarkers from cancer histopathology images.
  • Current DL applications often predict categorical labels, which is a limitation as biomarkers are frequently continuous measurements.
  • The hypothesis is that regression-based DL models will outperform classification-based models for continuous biomarker prediction.

Purpose of the Study:

  • To develop and evaluate a self-supervised, attention-based, weakly supervised regression method for predicting continuous biomarkers directly from histopathology images.
  • To compare the performance of regression-based DL against classification-based DL for biomarker prediction.
  • To assess the clinical relevance and prognostic value of DL-predicted continuous biomarkers.

Main Methods:

  • Development of a novel self-supervised, attention-based, weakly supervised regression framework.
  • Application of the method to 11,671 histopathology images from patients across nine cancer types.
  • Testing on clinically relevant biomarkers, including homologous recombination deficiency score and tumor microenvironment markers.

Main Results:

  • Regression-based DL significantly enhanced the accuracy of continuous biomarker prediction compared to classification-based DL.
  • The regression approach improved the correspondence of predictions to clinically relevant regions within the histopathology images.
  • In colorectal cancer patients, regression-based prediction scores demonstrated higher prognostic value than classification-based scores.

Conclusions:

  • Regression-based deep learning is a superior approach for predicting continuous biomarkers from cancer histopathology.
  • The developed open-source method provides a valuable alternative for continuous biomarker analysis in computational pathology.
  • This approach holds promise for improving diagnostic accuracy and prognostic assessment in oncology.