Microstructure Imaging, Inc. (MICSI), a YCombinator backed, NYU Langone Health spinout, is thrilled to announce FDA 510k clearance for its MICSI-RMT software suite, designed to enhance MRI image quality. This clearance marks the clinical translation of advanced MRI research led by Gregory Lemberskiy, CEO, and Benjamin Ades-aron, CTO.

MICSI-RMT employs a random matrix theory-based algorithm to significantly improve MRI image quality through the redundancy of the MRI exam. Unlike traditional AI methods, MICSI-RMT achieves these remarkable results without the need for external training data or high-performance GPUs. Additionally, MICSI-RMT includes processing modules that support weighted linear least squares and Bayesian fitting techniques to facilitate quantitative analysis of diffusion weighted imaging. Lastly, MICSI-RMT features cutting edge DICOM data routing ensuring securing and seamless integration into medical workflows.

Key Insights from the Clinical Study:

• Improved Image Quality: In a randomized, blinded rater study, expert neuroradiologists assessed MRI images processed by MICSI-RMT and standard of care (SOC). The MICSI-RMT processed images were preferred for their clarity and reduced artifacts, achieving higher expert image quality scores compared to standard diagnostic images. Raters found that DTI images processed with MICSI-RMT had improved visualization of small structures in brain white matter and improved contrast to distinguish adjacent tissue types, and for fMRI, more anatomically appropriate activation maps.

• Significant SNR Improvements: The software demonstrated notable enhancements in the signal-to-noise ratio (SNR), with MICSI-RMT showing improvements of up to 4.35x for diffusion MRI (dMRI) and 1.9x for functional MRI (fMRI).

• Precise Parametric Mapping: dMRI enhancement achieved notable improvement parameter precision. Specifically, the precision of ADC maps was improved by over 56.3%.