Connecticut Patent of the Month – February 2025
In the ever-evolving field of medical imaging, noise reduction in magnetic resonance (MR) images has long been a challenge, particularly when dealing with low-field MRI systems. Hyperfine, a pioneer in portable MRI technology, has introduced a groundbreaking method to address this issue using advanced neural network models. Their invention focuses on denoising MR images by leveraging a two-step training process that bridges the gap between high-field and low-field MRI systems.
The method begins by generating noisy MR images using clean data from high-field MRI systems (0.5 T or greater) and combining it with noise data from low-field systems (20 mT to 0.2 T). This synthetic data is used to train an initial neural network model, which is then applied to real low-field noisy images to create a refined training dataset. A second neural network, the denoising model, is trained using this dataset to produce high-quality, denoised MR images. This approach not only improves image clarity but also enhances the diagnostic utility of low-field MRI systems, making them more accessible in resource-limited settings.
Hyperfine’s innovation doesn’t stop there. The method incorporates techniques like data augmentation and nonuniform transformations to further enhance the training process, ensuring the model generalizes well across different anatomical regions and imaging sequences. By simulating noise using empirical measurements and statistical models, the system can adapt to various imaging conditions, including diffusion-weighted imaging (DWI) sequences.
This invention represents a significant leap forward in medical imaging, enabling clearer, more accurate diagnoses while expanding the reach of MRI technology. Hyperfine’s work underscores the transformative potential of combining AI with medical imaging, paving the way for more accessible and effective healthcare solutions.
Are you developing new technology for an existing application? Did you know your development work could be eligible for the R&D Tax Credit and you can receive up to 14% back on your expenses? Even if your development isn’t successful your work may still qualify for R&D credits (i.e. you don’t need to have a patent to qualify). To find out more, please contact a Swanson Reed R&D Specialist today or check out our free online eligibility test.
Who We Are:
Swanson Reed is one of the U.S.’ largest Specialist R&D tax advisory firms. We manage all facets of the R&D tax credit program, from claim preparation and audit compliance to claim disputes.
Swanson Reed regularly hosts free webinars and provides free IRS CE and CPE credits for CPAs. For more information please visit us at www.swansonreed.com/webinars or contact your usual Swanson Reed representative.
