Unlocking Molecular Diagnosis for Every MRI
Native AI for MR Spectroscopy
Every MRI already holds metabolic insight waiting to be read. METLiT makes it accessible.
Clinical Evidence
MRS has always had the potential. What’s been missing is a way to use it — everywhere.
The diagnostic utility of MRS-based metabolite biomarkers has been established through decades of academic research and 180,000+ publications. The problem was never a lack of evidence — it was a lack of accessibility.
Neurological Differential Diagnosis
MRS generates a metabolic fingerprint of living brain tissue — measuring neuronal integrity, membrane turnover, energy metabolism, and neurotransmitter balance simultaneously. Each disorder produces a distinct metabolic signature that structural MRI alone cannot reveal.
Drug Response Monitoring
MRS can detect metabolic changes before structural changes appear, enabling early and objective assessment of drug treatment response — critical for pharmaceutical clinical trials and personalized treatment strategies.
Non-invasive Molecular Profiling
Brain biopsy is virtually impossible. MRS is the only clinical examination that can obtain molecular-level information from brain tissue non-invasively — a core diagnostic tool in the era of precision medicine.
The Unmet Need
A proven science, waiting to be unlocked
MR Spectroscopy can reveal molecular-level information hidden inside every MRI — yet the gap between its potential and clinical reality remains vast.
180K+
Publications on PubMed
Decades of scientific validation
PubMed search: "magnetic resonance spectroscopy"
Nearlyall
MRI Scanners Already Capable
MRS sequences available on most systems
J Nucl Med 2011;52:492
Rare
Clinical Adoption
Limited to select research centers
J Nucl Med 2011;52:492
Expert
Dependent Analysis
Steep learning curve with specialized training required
MRspecLAB, Front Neuroimaging 2025
AI Agentic Architecture
Not just AI.
A system that reasons autonomously.
METLiT’s AI is not a single model. When spectrum data is received, specialized AI Agents autonomously collaborate to complete the entire workflow — from preprocessing to quality assessment, quantification, clinical interpretation, and reporting — without human intervention.
Self-orchestrating
Agents that think for themselves
Each Agent executes autonomously based on its own decision criteria, automatically exploring alternative paths when anomalies arise.
Physics-informed
Grounded in physical law, not just data
AI built on the first principles of MRS physics. Not a black box — reasoning grounded in the laws of physics.
Uncertainty-aware
Every result comes with a confidence score
Bayesian deep learning-based uncertainty quantification. Confidence scores accompany every result to support clinical decision-making.
Core Technology
The World’s Most Advanced
MRS AI Quantification Engine
Metabolites Quantified
Including Glu, Gln, GABA, GSH and other clinically critical metabolites — 3× more than conventional methods. Brain MRS as a representative example; applicable to other organs.
Published in Magnetic Resonance in MedicineFully Automated
No expert required. End-to-end autonomous pipeline from raw scanner data to clinical report — replacing hours of manual Ph.D.-level analysis.
Universal Compatibility
Consistent performance validated across all major clinical MRI platforms. No vendor lock-in, no workflow disruption.
Global Partners
Partnering with World-Leading Institutions
MoU / NDA established with leading medical institutions across North America, Asia, and Europe for multi-center collaborative research and clinical partnerships.
Ready to unlock the clinical value of MRS?
Discover how METLiT fits your institution's clinical and research environment.
References (8)
- [1]Lee HH, Kim H. Magn Reson Med 82.1 (2019): 33-48.
- [2]Lee HH, Kim H. Magn Reson Med 84.4 (2020): 1689-1706.
- [3]Lee HH, Kim H. Magn Reson Med 88.1 (2022): 38-52.
- [4]Shiino A, et al. J Neurol Neurosurg Psychiatry. 2004;75(8):1141-8.
- [5]Andersson J, et al. PloS one 14:e0217705. 2019.
- [6]Chen CH, et al. J Clin Neurosci. 2022;105:9-15.
- [7]Rydja J, et al. Fluids Barriers CNS 18, 18. 2021.
- [8]Marjańska M, et al. Magn Reson Med 87.1 (2022): 11-32.