Related Experiment Video
Updated: Nov 5, 2025
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
2.0K
Deep learning in histopathology: the path to the clinic.
Jeroen van der Laak1,2, Geert Litjens3, Francesco Ciompi3
1Department of Pathology, Radboud University Medical Center, Nijmegen, the Netherlands. jeroen.vanderlaak@radboudumc.nl.
Nature Medicine
|May 15, 2021
Summary
Machine learning in histopathology shows promise for improving medical diagnostics and easing clinician workloads. However, significant challenges remain before artificial intelligence achieves widespread clinical value.
Area of Science:
- Histopathology
- Medical Diagnostics
- Artificial Intelligence
Background:
- Machine learning (ML) offers potential improvements in medical diagnostics, including accuracy, reproducibility, and speed.
- Deep learning algorithms in histopathology demonstrate performance comparable to human pathologists in tasks like tumor detection and grading.
Purpose of the Study:
- To review the current state of artificial intelligence (AI) in histopathology.
- To identify challenges hindering clinical implementation of AI in this field.
Main Methods:
- Literature review of current AI applications in histopathology.
- Analysis of performance metrics and clinical integration barriers.
Main Results:
- AI algorithms show comparable performance to pathologists in specific histopathological tasks.
- Few AI algorithms have transitioned from research to clinical practice.
Conclusions:
- AI holds significant promise for enhancing histopathology diagnostics.
- Overcoming implementation challenges is crucial for realizing AI's clinical value in histopathology.
