GE Healthcare Launches 'Edison Magic Box': A Unified Interface for Multi-Domain AI Applications in Radiology

On July 8, GE Healthcare officially launched its first one-stop, cross-brand integrated AI application platform at the 2021 World Artificial Intelligence Conference — the Edison Box.

2021 World Artificial Intelligence Conference GE Healthcare Booth

Meanwhile, GE Healthcare announced the signing of a Memorandum of Strategic Cooperation with multiple domestic software development enterprises, including Yizhun Intelligent, Shukun Technology, Qianglian Zhichuang, Ande Yizhi, Deepwise Healthcare, Infervision, and Keya Medical, as well as leading venture capital firm Sinovation Ventures and the Yangtze River Delta Smart Healthcare Development Alliance, which will provide standard guidance and quality control, to further expand the Edison ecosystem.

A platform-based ecosystem will not only drive the deep integration of AI into clinical practice and accelerate the development and commercialization of advanced algorithms, but also harness cross-industry collaboration to build a digital healthcare infrastructure tailored to the needs of Chinese patients and physicians, thereby enabling the scaled deployment of precision medicine to grassroots healthcare settings.

Liu Shiyuan, Chairman-elect of the Radiology Branch of the Chinese Medical Association and Chairman of the China Medical Imaging AI Industry-Academia-Research-Application Innovation Alliance, stated: “The COVID-19 pandemic in 2020 accelerated the development of digital healthcare. For the medical imaging AI industry, 2021 has entered a new critical phase of tackling key challenges. Only by determining how to select, utilize, and manage multiple imaging AI solutions, and how to achieve the ‘seamless’ integration of AI into clinical workflows, can we address these pain points and build a patient-centric imaging AI ecosystem. Only then can digital healthcare be truly implemented and transition to large-scale practice, accelerating the decentralization of high-quality medical resources, the tiered diagnosis and treatment system, and balanced regional distribution, ultimately enabling digital healthcare to take real root and benefit patients.”

Dai Ying, Vice President and Chief Innovation Officer of GE HealthCare China, stated: “We believe that practical application is the sole criterion for evaluating digital healthcare. GE HealthCare aims to build an open, integrated, empowering, and service-driven ecosystem paradigm. On one hand, we are committed to leading the industry into an era of unified gateway access, providing hospital users with one-stop AI services, and consolidating fragmented solutions to facilitate the effective real-world deployment of AI applications. Meanwhile, we will establish an industry ecosystem community that bridges clinical and developer mindsets, offering a suite of development tools, cloud storage, and resources to collaborate with AI developers in addressing real-world medical challenges. At this World Artificial Intelligence Conference, GE HealthCare presented a comprehensive overview of the Edison ecosystem’s progress over the past two years, which also marks a significant milestone in the concurrent advancement of our strategies for full-scale production in China, digital empowerment, and win-win collaboration.”

Clear Access Point to the Digital Ecosystem

To address the pressing challenge of the current supply-demand imbalance in medical resources, medical imaging AI applications based on deep convolutional neural network technology and big data learning are developing rapidly, empowering hospitals to enhance diagnostic accuracy and efficiency.

However, for the end-users—the radiology departments in hospitals—the practical application and clinical deployment of AI remain mired in challenges: cramped reading rooms are cluttered with various AI workstations, forcing physicians to constantly switch between workstations, hardware, and software interfaces to complete their tasks.

How to efficiently execute a one-time procurement, how to avoid redundant software and hardware installations during implementation, and how to maintain application upgrade capabilities for future use are real-world pain points.

Driven by the needs of hospital users, the newly released "Edison Magic Box" is the latest R&D achievement from the GE HealthCare team.

GE Healthcare "Edison Magic Box"

This product integrates leading Chinese AI applications, delivering a comprehensive suite of multi-disease AI solutions to hospitals in a single, integrated package. Through a unified interface and API, the "Edison Magic Box" serves as a key to unlocking AI applications—enabling centralized lifecycle management and access either on-premises or in the cloud, while ensuring continuous update and upgrade capabilities. This effectively eliminates resource waste caused by siloed application deployment and redundant development.

Currently, the platform supports:

Single Deployment, Enabling Multi-Domain AI Applications in Radiology: The "Edison Magic Box" offers a selection of leading AI applications across multiple domains, including chest pulmonary nodules, fractures, cardiac, neurological, breast, and liver imaging. Coupled with GE HealthCare's time-tested AWS post-processing software, all these solutions can be procured and deployed through a single platform purchase and installation, thereby eliminating redundant hardware and software investments. The system can be installed on-premises within a clinical department or deployed in the cloud, accessible via web-based login.

A Workflow Integrating AI Software from Different Vendors: During use, the platform utilizes a unified Edison AI pop-up tool to intelligently identify the patient ID from the current report and provide a link to the processing results. Doctors can conveniently access the processing results pages of multiple applications directly with a single click.

One Interface, Unlocks an Entire Ecosystem“The ‘Edison Magic Box’ can provide an online marketplace that offers customers introductions to applications across multiple clinical domains and facilitates the submission of procurement intent. All applications can be centrally purchased via the Edison platform. Within this marketplace, applications will be continuously launched, updated, and expanded, seamlessly integrating without disrupting existing workflows. In the future, the Edison AI platform will further extend its services to additional clinical departments.”

GE Healthcare Edison Ecosystem Partner — Li Kaifu, Chairman and CEO of Sinovation Ventures and Dean of the AI Institute of Sinovation Ventures, stated: “Now is the optimal time for the development of ‘AI + Healthcare’. The integration of vast, long-accumulated data with AI yields valuable algorithms that assist physicians in disease early warning, diagnosis, treatment, monitoring, and long-term management. However, the real challenge in transitioning AI from technology to application lies in the incompleteness of existing data and the unsuitability of real-world application and commercial scenarios. The ‘Edison Magic Box’ originates from a global healthcare leader like GE Healthcare, which boasts a total installed base of over 300,000 devices in the Chinese market. Such resources will unlock more practical application scenarios and generate richer deep learning data. Meanwhile, GE’s robust commercialization capabilities will also be highly effective in supporting healthcare AI companies.”

Edison China Ecosystem Continues to Expand

Since 2019, GE Healthcare has partnered with multiple Chinese AI companies to jointly develop disease-specific imaging-assisted diagnostic applications.

The launch of the Edison AI Platform has established foundational platform capabilities for ecosystem development, encompassing image transmission, storage, display, algorithm integration, resource allocation, and data security. This further streamlines development processes and reduces costs for AI companies, accelerating the development of AI algorithms.

Meanwhile, with the continuous innovation of GE imaging equipment, while providing more comprehensive imaging information, partners are also able to acquire a sufficient volume of high-quality images in a shorter timeframe, laying a solid foundation for the development of downstream AI applications and the clinical implementation of precision medicine.

Zhu Renming, Chairman of the Yangtze River Delta Smart Healthcare Development Alliance, stated: “During the 14th Five-Year Plan period, the healthcare industry has entered a stage of high-quality development. As the leading organization for smart healthcare scientific and technological innovation in the Yangtze River Delta, the Alliance aims to be rooted in the region and drive the advancement of smart healthcare across the Yangtze River Delta economic belt and China. The Edison Ecosystem, co-developed with GE Healthcare, provides full-path, closed-loop support spanning from ideation, technology development, and incubation to product refinement, validation, and commercialization. It will not only serve as a cornerstone for smart healthcare development in the Yangtze River Delta, but also act as a bridge to integrate into global development through the Edison Ecosystem.”

GE Healthcare "ImagingTech Companion" Remote Imaging Quality Control Platform

Currently, partners within the Edison ecosystem include developers of disease imaging algorithms—Yizhun Intelligent, Shukun Technology, Qianglian Intelligent, Ande Medical Intelligence, Deepwise Healthcare, Infervision, and Keya Medical; cloud service provider Tencent Cloud; the Yangtze River Delta Smart Healthcare Development Alliance, an industry organization that establishes development and application standards; and Sinovation Ventures, which operates an AI Engineering Institute and pioneered the “technology investment + AI” model. All of the aforementioned AI developers have integrated with GE Healthcare’s advanced imaging equipment, including CT, MRI, DSA, and X-ray systems, on the Edison platform, forming multi-disease solutions for precision lung screening, precision breast screening, precision stroke diagnosis and treatment, precision coronary diagnosis, precision liver imaging, and intelligent fracture analysis. The “Technician-Image Companion” 5G remote imaging quality control platform, which assists technicians in the standardized management of scanning protocols, was also selected for the Top 30 list of the 2021 WAIC SAIL Outstanding AI Leaders awards.