OXALIA · Medical AI
OXALIA is an AI decision-support tool that analyses chest radiographs and detects pathologies.
- Analysis
- < 2 min
- Pathologies
- 20
- Integration
- PACS/
DICOM - Institutional partners
- 3
Illustrative display
Our partners



Vision & Mission
AIVRA focuses its research on artificial intelligence applied to medical imaging, with particular emphasis on chest diagnosis.
The founding insight comes from an alarming figure: according to the Tunisian Society of Radiology's 2025 report, Tunisia has four radiologists per hundred thousand inhabitants, against thirteen in France. That shortage creates genuine imaging deserts, where thousands of patients sometimes wait on a diagnosis that cannot wait.
With that in mind, AIVRA builds clinical decision-support software, for the benefit of radiologists, clinicians and patients.
To that end, AIVRA introduced OXALIA, the first medical AI platform for chest radiology developed in Tunisia on purely Tunisian data. It analyses a radiograph in two minutes, integrates with existing PACS and DICOM systems without any infrastructure change, and gives the radiologist a reliable second read, twenty-four hours a day.
Source: Tunisian Society of Radiology, 2025 report.
The three pillars of OXALIA
Chest radiography
A single modality, treated in depth: the frontal chest X-ray, the most prescribed exam and the one most often read under pressure.
Explainable AI
Every detection is localised on the image. The radiologist sees what the model saw, and can disagree with it — a black box cannot be validated.
PACS & DICOM integration
OXALIA sits inside the existing flow: the exam arrives through the PACS, the report goes back out through it. No infrastructure change, no double entry.
Supporting the radiologist
Transform your diagnostic approach with OXALIA: a reliable second read, available twenty-four hours a day, with no change to your existing infrastructure.
Diagnostic aid — the final decision rests with the radiologist.
Chest radiography: free yourself from triaging the queue, and focus your expertise where it truly counts.
The product in the real workflow, not in isolation.
Every exam lands in a prioritized worklist. One click opens the preliminary report generated by OXALIA, ready for the radiologist to validate.

Preliminary report
- Exam
- EXM-2024-1847
- Technique
- Frontal chest radiograph
Findings
Diagnostic aid — the final decision rests with the radiologist.
4 exams analyzed · 1 urgent cases prioritized
Every abnormality, located and named.
Twenty classes across eight pathophysiological families. Hover a family to see what it covers.
Cardiovascular
- Cardiomegaly
- Pericardial effusion
- Hilar enlargement
20 classes across 8 families
Diagnostic aid — the final decision rests with the radiologist.
Frequently asked questions
Give your radiologists back their time.
Request a demo or explore OXALIA in detail.
See OXALIA in a setting close to your own radiology workflow.

