AI Marketplace for Radiology

One platform for AI-assisted reporting

Vetted AI modules from different vendors — bundled on a single platform and seamlessly integrated with your PACS and RIS.

4Modalities covered
DICOMPACS integration
HL7RIS integration
AI network visualization
The challenge

Plenty of AI potential, too many silos

The number of approved AI tools in radiology keeps growing. Yet each application has to be procured, integrated, and operated on its own — with its own login, its own interface, and its own integration effort.

jung radiology solves this: a curated marketplace that brings together AI modules from different third-party vendors and delivers them straight into your workflow through standardized interfaces.

See how it works

One platform

All AI modules available centrally — instead of many separate systems.

Vendor-neutral

In-house and external algorithms, curated to each customer's needs.

Deeply integrated

DICOM to the PACS, HL7 to the RIS — results land where the work happens.

Traceable

Structured, transparent AI findings and accompanying training.

How it works

From imaging to a structured report

The radiologist keeps working in their familiar environment. AI results flow in automatically through standardized interfaces.

1

Data sources

Image data arrives via DICOM from the PACS, and report context via HL7 from the RIS.

2

AI marketplace

Curated modules from different vendors analyze the data — from brain MRI and DAT-SPECT to chest CT.

3

Results

The radiologist reviews the AI findings in the reporting module. Structured reports go back to the RIS, biomarkers to the PACS.

Quantitative brain analysis
Focal atrophy (MRI) · example visualization
AI Modules

A growing portfolio

In-house developments from years of research with university hospitals, complemented by curated modules from external vendors — organized by modality.

MRI

Brain MRI

Lesion analysis, brain volumetry, neurodegeneration, and focal tissue loss (VBM).

CT

Brain & chest CT

Hemorrhage exclusion plus screening-compliant detection of pulmonary nodules.

NUC

Nuclear medicine

Detection of nigrostriatal degeneration on DAT-SPECT data.

View all modules
In focus · Chest CT

Ready for lung cancer screening

90%
Sensitivity
mean (AI vs. rater)
96%
Specificity
mean (AI vs. rater)
255
Patients
real-world test cohort
4
Modalities
available today

Figures from internal validation against radiological readers. Please verify against current data before external use.

Get started

Bring AI into your radiology environment

Talk to us about connecting to your PACS and RIS — we'll advise you on the right modules.

Get in touch Go to the reporting module