A general-purpose AI assistant embedded in an open-source radiology information system

TL;DR

This paper presents an open-source radiology information system with integrated AI that supports human-AI collaboration, continuous learning, and model sharing, enhancing radiologist workflows and AI model adaptability.

Contribution

It introduces a novel platform combining DICOM SR annotations, active learning, and swarm learning for personalized and continuously improving radiology AI models.

Findings

Successful integration of AI into open-source RIS

Enabling radiologists to actively improve AI models

Effective model sharing via swarm learning

Abstract

Radiology AI models have made significant progress in near-human performance or surpassing it. However, AI model's partnership with human radiologist remains an unexplored challenge due to the lack of health information standards, contextual and workflow differences, and data labeling variations. To overcome these challenges, we integrated an AI model service that uses DICOM standard SR annotations into the OHIF viewer in the open-source LibreHealth Radiology Information Systems (RIS). In this paper, we describe the novel Human-AI partnership capabilities of the platform, including few-shot learning and swarm learning approaches to retrain the AI models continuously. Building on the concept of machine teaching, we developed an active learning strategy within the RIS, so that the human radiologist can enable/disable AI annotations as well as "fix"/relabel the AI annotations. These annotations are then used to retrain the models. This helps establish a partnership between the radiologist user and a user-specific AI model. The weights of these user-specific models are then finally shared between multiple models in a swarm learning approach.