KEROS is an artificial intelligence augmented radiology solution for knee MRI. It automatically analyzes the main anatomical structures of the knee and detects lesions of ligaments, menisci and cartilages.
Information source: Vendor
Last updated: Jan. 21, 2024

General Information

Product name KEROS
Company Incepto
Subspeciality MSK
Modality MR
Disease targeted Meniscus and ligament tears, chondropathies
Key-features Detect and characterize lesions of ligaments, menisci and cartilages
Suggested use Before: flagging acute findings
During: report suggestion
After: diagnosis verification

Technical Specifications

Data characteristics
Population Patient over 16 yo with no history of knee surgery
Input 2D, 3D, proton density fat saturation, T2 fat saturation
Input format DICOM
Output Pre-filled report including finding and location
Output format PDF or DICOM Secondary Capture
Integration Integration in standard reading environment (PACS), Integration RIS (Radiological Information System), Integration via AI marketplace or distribution platform
Deployment Cloud-based
Trigger for analysis Automatically, right after the image acquisition, On demand, triggered by a user through e.g. a button click, image upload, etc.
Processing time 1 - 10 minutes


Certified, Class IIa , MDR
FDA No or not yet
Intended Use Statements
Intended use (according to CE) KEROS is a software application based on artificial intelligence and intended to be used as a tool in knee MRI interpretation. Its usage is dedicated only to clinicians. KEROS should not be used alone to recommendÔÇ»medical care.


Market presence
On market since 01-2021
Distribution channels Incepto
Countries present (clinical, non-research use)
Paying clinical customers (institutes)
Research/test users (institutes)
Pricing model Subscription
Based on Number of analyses


Peer reviewed papers on performance

  • Deep learning to detect anterior cruciate ligament tear on knee MRI: multi-continental external validation (read)

  • Meniscal lesion detection and characterization in adult knee MRI: A deep learning model approach with external validation (read)

Non-peer reviewed papers on performance
Other relevant papers