Enhanced Concurrent MRSI and fMRI with Adaptive Gradient Encoding and Machine Learning

Publication ID: 24-11857306_0006_PTD
Published: November 07, 2025
Category:Direct Improvements & Enhancements

Legal Citation

pr1or.art Inc., “Enhanced Concurrent MRSI and fMRI with Adaptive Gradient Encoding and Machine Learning,” Published Technical Disclosure No. 24-11857306_0006_PTD, Published November 07, 2025, available at https://archive.pr1or.art/24-11857306_0006_PTD
This technical disclosure describes improvements that would be readily apparent to a Person Having Ordinary Skill In The Art (PHOSITA) when considered in combination with the foundational architecture disclosed in U.S. Patent No. 11,857,306.

Summary of the Inventive Concept

An improved system and method for concurrent Magnetic Resonance Spectroscopic Imaging (MRSI) and functional Magnetic Resonance Imaging (fMRI) that reduces scan times, enhances signal-to-noise ratio, and enables real-time data analysis and visualization.

Background and Problem Solved

The original patent for concurrent MRSI and fMRI faces limitations of lengthy scan times, which can lead to patient discomfort, motion artifacts, and decreased diagnostic accuracy. The new inventive concept addresses these limitations by introducing novel adaptive gradient encoding schemes, spatial-spectral water excitation RF pulses, and machine learning algorithms to improve the efficiency and accuracy of concurrent MRSI and fMRI.

Detailed Description of the Inventive Concept

The enhanced system and method comprise a modified water readout module with an adaptive gradient encoding scheme that optimizes scan times. The water suppression module is further modified to incorporate a spatial-spectral water excitation RF pulse that pre-localizes the water signal within a slice or a slab. Additionally, the system includes a machine learning algorithm for quantifying metabolite concentrations based on the metabolite signals and the water MRSI image. The fMRI image is used to measure task-based activation and resting-state connectivity simultaneously, and the system features a module for real-time data analysis and visualization. The inventive concept also encompasses a novel water signal amplification technique that enhances the signal-to-noise ratio of the water MRSI image, and a single-shot MRSI data acquisition with automatic correction of motion artifacts.

Novelty and Inventive Step

The new claims introduce novel adaptive gradient encoding schemes, spatial-spectral water excitation RF pulses, machine learning algorithms, and water signal amplification techniques that significantly improve the efficiency and accuracy of concurrent MRSI and fMRI. These advancements are non-obvious and provide a substantial improvement over the original patent.

Alternative Embodiments and Variations

Alternative embodiments of the inventive concept could include using different machine learning algorithms, modifying the spatial-spectral water excitation RF pulse for different applications, or integrating the system with other imaging modalities. Variations of the inventive concept could also include adapting the system for use in different anatomical regions or for different diseases.

Potential Commercial Applications and Market

The enhanced concurrent MRSI and fMRI system has significant commercial potential in the medical imaging industry, particularly in the fields of neurology, oncology, and cardiology. The system's ability to provide fast, accurate, and comprehensive diagnostic information could lead to improved patient outcomes and reduced healthcare costs.

Field of Art

Medical Imaging and Magnetic Resonance Spectroscopy, specifically focused on advanced neuroimaging techniques involving concurrent MRSI and fMRI data acquisition

Person of Ordinary Skill (PHOSITA) Profile

A biomedical engineer or medical imaging specialist with advanced knowledge of MRI technologies, signal processing, machine learning, and expertise in optimizing multi-modal neuroimaging techniques

Obviousness Rationale

A person skilled in the art would recognize that the PTD's modifications represent predictable engineering improvements to the source patent's concurrent MRSI and fMRI methodology. The disclosed adaptive gradient encoding, machine learning metabolite quantification, and motion artifact correction are logical extensions of existing imaging optimization strategies. These variations would be considered routine optimization techniques within the standard problem-solving approach of medical imaging technology development.

Obvious Combinations & Variations

Source Patent Element
Concurrent MRSI and fMRI data acquisition method
PTD Variation
Adaptive gradient encoding scheme to reduce scan times
Obviousness Reasoning
Reducing scan times is a known optimization goal in medical imaging, and modifying gradient encoding represents a predictable solution using standard signal processing techniques
Source Patent Element
Water suppression module for MRSI imaging
PTD Variation
Spatial-spectral water excitation RF pulse for pre-localization
Obviousness Reasoning
RF pulse optimization is a standard technique in MRI, and pre-localization represents a known method for improving signal specificity and reducing noise
Source Patent Element
Metabolite signal quantification
PTD Variation
Machine learning algorithm for metabolite concentration analysis
Obviousness Reasoning
Machine learning is a well-established technique for signal processing and pattern recognition, making its application to metabolite quantification an obvious extension of existing computational methods
Source Patent Element
fMRI image acquisition
PTD Variation
Real-time data analysis and visualization module
Obviousness Reasoning
Adding real-time processing capabilities is a predictable improvement in medical imaging technology, representing a standard approach to enhancing diagnostic workflows
Source Patent Element
MRSI data acquisition method
PTD Variation
Single-shot acquisition with automatic motion artifact correction
Obviousness Reasoning
Motion artifact correction is a known challenge in medical imaging, and developing automated correction techniques represents a standard problem-solving approach for improving image quality
35 U.S.C. § 103 Summary: Based on the teachings of US Patent 11857306 and the disclosed technical variations, a person having ordinary skill in the art would find the claimed innovations obvious and lacking inventive step. The proposed modifications represent predictable engineering improvements that would be readily conceived by a skilled practitioner seeking to optimize concurrent MRSI and fMRI imaging techniques through standard signal processing and machine learning methodologies.

Original Patent Information

Patent NumberUS 11,857,306
TitleConcurrent MRSI and fMRI
Assignee(s)UNM RAINFOREST INNOVATIONS