mdbrain

mediaire
mdbrain enables AI-powered evaluations of brain MRIs. Currently available modules are Brain Volumetry, Lesion Characterization, Aneurysm Detection, and Tumor Differentiation. As output radiologists receive quantitative reports as well as visual overlays directly into the PACS.
Information source: Vendor
Last updated: October 7, 2024

General Information

General
Product name mdbrain
Company mediaire
Subspeciality Neuro
Modality MR
Disease targeted Dementia, multiple sclerosis, MSA/CBD/PSA, aneursyms, glioma/glioblastoma
Key-features Segmentation of brain regions, quantification of brain volume and white/gray matter (global and regional, including hippocampus and ventricles) with longitudinal follow-up, lesion detection including anatomical localization (MAGNIMS criteria) and longitudinal follow-up, aneurysm detection with longitudinal follow-up, tumor differentiation through delineation and quantification of tumor core and surrounding oedema incl. longitudinal follow-up
Suggested use Before: stratifying reading process (non, single, double read)
During: perception aid (prompting all abnormalities/results/heatmaps)

Technical Specifications

Data characteristics
Population Early diagnostics and follow up of neurological and neurodegenerative diseases
Input 1.5 or 3T MR. Brain volumetry: 3D-T1-MPRage, 1.0 x 1.0 mm²; Lesion characterization: (3D-)T1 and 3D-T2-FLAIR, 1.0 x 1.0 mm²; Aneurysm detection: TOF, 1.0 x 1.0 mm²; Tumor differentiation: 3D-T1, 3D-T2-FLAIR, 1.0 x 1.0 mm², T1 with contrast agent, 3.0 x 3.0 mm², and T2 spin-echo, 3.0 x 3.0 mm²
Input format DICOM
Output Structured PDF report including: diagnostically relevant slices from the current exam, tables with quantitative metrics from the current exam (and comparison with previous exam), diagrams with color-coded deviations from norm values. Color-coded segmentation overlays (static + longitudinal).
Output format PDF, DICOM-PDF, browser-based platform, CSV-Export file
Technology
Integration Integration in standard reading environment (PACS), Integration RIS (Radiological Information System), Integration via AI marketplace or distribution platform, Stand-alone third party application
Deployment Locally on dedicated hardware, Locally virtualized (virtual machine, docker), 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

Regulatory

Certification
CE
Certified, Class IIb , MDR
FDA No or not yet
Intended Use Statements
Intended use (according to CE) The product is intended for automatic labeling, visualization and volumetric quantification of 3D MRI data (in DICOM format) of the head. The software automates the currently manual process of identifying, labeling and volumetric calculation of segmented brain structures on 3D MRI images. The calculated volumetric data, in addition to the image data at hand, can assist radiologists in detecting neurological diseases. The volumetric data obtained alone is not sufficient to establish a diagnosis and is not intended to do so.

Market

Market presence
On market since 01-2019
Distribution channels Calantic, deepcOS, Sectra Amplifier Store, Angionautix, Bender, Medecon, Medavis, Sanova, Supermedical, Tatramed
Countries present (clinical, non-research use) 11 (Germany, Switzerland, Austria, Spain, Portugal, Italy, Romania, Czech Republic, Slovakia, UAE, Israel)
Paying clinical customers (institutes)
Research/test users (institutes)
Pricing
Pricing model Subscription
Based on Number of analyses

Evidence

Evidence
Peer reviewed papers on performance
  • AI supported detection of cerebral multiple sclerosis lesions decreases radiologic reporting times (read)

  • External evaluation of a deep learning-based approach for automated brain volumetry in patients with huntington’s disease (read)

    • AI supported detection of cerebral multiple sclerosis lesions decreases radiologic reporting times (read)

    • Changes in MRI Workflow of Multiple Sclerosis after Introduction of an AI-Software: A Qualitative Study (read)

    • Impact of an AI software on the diagnostic performance and reading time for the detection of cerebral aneurysms on time of flight MR-angiography (read)

    • Automated Detection of Cerebral Aneurysms on TOF-MRA Using a Deep Learning Approach : An External Validation (read)

    • Triplanar U-Net with lesion-wise voting for the segmentation of new lesions on longitudinal MRI studies (read)

Non-peer reviewed papers on performance
Other relevant papers

  • Brain Volume Changes after COVID-19 Compared to Healthy Controls by Artificial Intelligence-Based MRI Volumetry (read)

  • Evaluation of Cerebral Volume Changes in Patients with Tremor Treated by MRgFUS Thalamotomy (read)