Joint Imaging Platform - Decentralized Compute Infra for On-site Medical Image: Jonas Scherer (DKFZ)

VI Seiminar 27:
"The Joint Imaging Platform - Decentralized Compute Infrastructure for On-site Medical Image Analyses" by Jonas Scherer, a PhD student in the department of Medical Image Computing at German Cancer Research Center (DKFZ Heidelberg). This talk is presented on 17. March 2022.

Relavant websites:
https://www.dkfz.de (German Cancer Research Center)
https://www.kaapana.ai (Kaapana: open source toolkit for state of the art platform provisioning in the field of medical data analysis)

Abstract:
Image analysis is one of the most promising applications of artificial intelligence (AI) in health care, potentially improving prediction, diagnosis, and treatment of diseases. Although scientific advances in this area critically depend on the accessibility of large-volume and high-quality data, sharing data between institutions faces various ethical and legal constraints as well as organizational and technical obstacles.
The Joint Imaging Platform (JIP) addresses these issues by providing federated data analysis technology in a secure and compliant way. Using the JIP, medical image data remain in the originator institutions, but analysis and AI algorithms are shared and jointly used. Common standards and interfaces to local systems ensure permanent data sovereignty of participating institutions.

Key Objective:
To create a digital infrastructure for federated artificial intelligence (AI)–based medical image analysis
with the goal of facilitating and enabling multicenter trials between the partner sites of the German Cancer Consortium and beyond.

Keywords:
Kaapana, cloud computing infrastructure, federated learning, DICOM, metadata, Docker, Kubernetes