Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

A deep learning framework for efficient pathology image analysis.

Peter Neidlinger¹, Tim Lenz¹, Sebastian Foersch²

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

Nature Communications

|July 1, 2026

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

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

Nature medicine·2026

Same author

Functional Outcome Prediction in Young Adults With Mental Health Symptoms Using Machine Learning and Large Language Models: Longitudinal Observational Study.

JMIR mental health·2026

Same author

Counterfactual Diffusion Models Provide Interpretable Explanations of Artificial Intelligence Models in Pathology.

Cancer research·2026

Same author

Towards autonomous medical artificial intelligence agents.

Nature·2026

Same author

Evaluating statistical models for overdispersed multi-omics data: a multiplex immunofluorescence case study.

American journal of epidemiology·2026

Same author

Appendix300: Surgical video and patient metadata of 330 laparoscopic appendectomy cases from five institutions.

Scientific data·2026

Same journal

Chlorinated VSLSs Surpass HCFCs in CFC-11-Equivalent Emissions for Ozone Layer Depletion in China.

Nature communications·2026

Same journal

Vegetation browning patterns under compound soil and atmospheric dryness in northern permafrost ecosystems.

Nature communications·2026

Same journal

Voltage imaging of CA1 pyramidal cells and SST+ interneurons reveals stability and plasticity mechanisms of spatial firing.

Nature communications·2026

Same journal

Radical-omics reveals the hydrogen-abstraction pathway of isoprene oxidation.

Nature communications·2026

Same journal

Toughening elastomer via sequentially activated multi-pathway energy dissipation.

Nature communications·2026

Same journal

De novo EHMT2 variants cause an autosomal dominant EHMT2-related Kleefstra syndrome via loss of G9a methyltransferase activity.

Nature communications·2026

See all related articles

Summary

This summary is machine-generated.

Artificial intelligence in digital pathology is now efficient with EAGLE (Efficient Approach for Guided Local Examination). This deep learning framework rapidly analyzes key regions in whole-slide images, improving biomarker prediction and reducing computational time by over 99%.

Area of Science:

Computational pathology
Artificial intelligence in medicine
Deep learning for image analysis

Background:

Artificial intelligence (AI) has advanced digital pathology, enabling biomarker prediction from whole-slide images.
Current AI methods are computationally intensive, processing numerous redundant image tiles and requiring complex aggregation.
This inefficiency limits the practical application of AI in pathology workflows.

Purpose of the Study:

To introduce EAGLE (Efficient Approach for Guided Local Examination), a novel deep learning framework for digital pathology.
To develop an efficient method that emulates pathologist behavior by selectively analyzing informative regions of whole-slide images.
To benchmark EAGLE against existing foundation models across diverse cancer pathology tasks.

Main Methods:

Related Experiment Videos

EAGLE employs a task-agnostic tile selection strategy combined with detailed feature extraction.
The framework was benchmarked against leading slide- and tile-level foundation models.
Evaluations were conducted on 43 tasks across nine cancer types, including morphology, biomarker prediction, treatment response, and prognosis.

Main Results:

EAGLE demonstrated superior performance compared to patch aggregation methods, with classification accuracy improvements up to 23%.
The framework achieves state-of-the-art overall classification performance.
EAGLE processes a single slide in 2.27 seconds, representing a computational time reduction of over 99% compared to existing models.

Conclusions:

EAGLE significantly enhances computational efficiency in digital pathology, enabling rapid and auditable AI-driven analyses.
The framework's ability to identify informative regions minimizes artifacts and ensures robust, verifiable outputs.
EAGLE's unified embedding facilitates slide search, integration with multi-omics data, and development of clinical foundation models.