Health AI Register Logo
ProductsPlatformsCompaniesNewsContact
ProductsSubtleSYNTH

Reviewed 11 May 2026

Completeness Good (56%)

SubtleSYNTH

Subtle Medical

SubtleSYNTH is a software as a medical device consisting of a software machine learning algorithm that generates a SynthSTIR contrast image of a case from T1-weighted and T2-weighted spine MR images.

No papers to support — we monitor for new evidence.

Key features

Contrast image synthesis

MRI image enhancement

General Information

Product name

SubtleSYNTH

Modality

MR

Main task

Not specified

Subspeciality

Spine

Disease targeted

Performance validation dataset includes pathologies of normal, degenerative, infection, trauma, cord lesion (intramedullary neoplasm, intramedullary inflammatory lesion including Multiple Sclerosis (MS) and NMOSD, spinal cord infarct, compressive myelopathy), non-cord lesion (bony metastatic lesion, intradural extramedullary lesions including meningioma, schwannoma, neurofibroma, arachnoid cyst, arachnoiditis, epidural collection/mass including epidural lipomatosis), vascular (AVM, dAVF, cavernous malformation), and intracranial hemorrhage (intrathecal hematoma, subdural hematoma, epidural hematoma, intramedullary hematoma).

Regulatory Information

CE Certification

Pathway:

MDR

Class:

Class IIa

Not verified by Health AI Register

FDA Certification

Pathway:

510(k) cleared

Class:

Class II

FDA Number:

K241329

View FDA record

Verified by Health AI Register

Other certifications

Not specified

Evidence & Research

No research papers or evidence on file yet.

The registry monitors publications for new evidence.

Technical Specifications

Patient population age

Adult, Pediatric

Input

Sagittal T1 and T2 weighted spine MRI without contrast, field strength: 0.3T, 0.6T, 1.0T, 1.16T, 1.5T, and 3T, vendors: GE, Fonar, Siemens, Toshiba, Philips, and Hitachi

Input format

DICOM

Output

Synthetic STIR image

Output format

DICOM

Integration

Integration CIS (Clinical Information System), Integration in standard reading environment (PACS), Integration RIS (Radiological Information System), Integration via AI marketplace or distribution platform

Deployment

Cloud-based, Locally on dedicated hardware, Locally virtualized (virtual machine, docker)

Trigger for analysis

Automatically, right after the image acquisition, On demand, triggered by a user through e.g. a button click, image upload

Processing time

1 - 10 minutes

Population

Not specified

Market Presence

On market since

Not specified

AI Platforms

Resellers

Not specified

Countries present

Not specified

Paying clinical customers

Not specified

Research/test users

Not specified

Pricing Information

Pricing model

Not specified

Based on

Not specified

First published: Jul 29, 2025 | Last updated: May 11, 2026