Related Experiment Video
Updated: Jul 26, 2025
13:01
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
Published on: June 3, 2022
3.8K
Automated Curation and AI Workflow Management System for Digital Pathology
V K Cody Bumgardner1, Sam Armstrong1, Alexandr Virodov1
1University of Kentucky, Lexington, Kentucky.
Summary
This study introduces a platform for managing digital pathology data, enabling efficient processing, storage, and AI model development across distributed systems. It addresses challenges in handling gigapixel images for research and clinical applications.
Area of Science:
- Digital pathology
- Computational pathology
- Artificial intelligence in medicine
Background:
- Digital pathology involves processing and storing large gigapixel images.
- Challenges include distributed storage, access, and AI model development.
Purpose of the Study:
- To present a platform for managing and processing multi-modal pathology data across multiple locations.
- To enable AI model development and data sharing for research and clinical use.
Main Methods:
- An agent-based system coupled with open-source automated machine learning tools.
- Platform covers end-to-end AI workflow: data acquisition, curation, model training, and evaluation.
Main Results:
- Dynamic load-balancing and cross-network operation for pathology data management.
- Facilitates the development of research and clinical AI models.
Conclusions:
- The presented platform effectively manages multi-modal pathology data.
- Enables AI model development for cancer research, demonstrated by colon and prostate cancer case studies.
