Explore a comprehensive lecture on understanding scanner utilization through real-time DICOM metadata extraction. Learn about Niffler, an open-source DICOM framework for machine learning pipelines and processing workflows. Discover how this framework analyzes scanner utilization in healthcare networks by retrieving radiology images and processing metadata. Compare the accuracy of this method to traditional RIS data approaches. Gain insights into the implementation of Niffler for real-time and on-demand execution of machine learning pipelines on radiology images. Delve into topics such as data integration, federation, challenges in healthcare data processing, and the architecture of distributed environments for medical imaging analysis.
Understanding Scanner Utilization with Metadata Extraction - Pradeeban Kathiravelu
Stanford University via YouTube
Overview
Syllabus
Introduction
Data Integration and Federation
Data Sources
Data Integration
Challenges
Nifla Modules
Sample Extraction Profile
Architecture
First Use Case
Second Use Case
Third Use Case
Scanner Utilization
Observations
Data Visualization
Distributed Environments
Hybrid Environment
Virtual Internet Services
External Consumers
Peers
Questions
Learning Mechanisms
RealTime Images
Distributed Environment
Taught by
Stanford MedAI
