Expanding Dense MRI Applications through Deep Learning-based Phase Unwrapping

Publication ID: 24-11857288_0002_PTD
Published: November 07, 2025
Category:New Applications & Use Cases

Legal Citation

pr1or.art Inc., “Expanding Dense MRI Applications through Deep Learning-based Phase Unwrapping,” Published Technical Disclosure No. 24-11857288_0002_PTD, Published November 07, 2025, available at https://archive.pr1or.art/24-11857288_0002_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. 11,857,288.

Summary of the Inventive Concept

This inventive concept leverages the core technology of dense MRI using deep learning for phase unwrapping to tackle diverse applications beyond cardiac strain imaging, including crop growth monitoring, soil moisture evaluation, composite material defect detection, fluid dynamics analysis, and biomechanical property monitoring of implantable medical devices.

Background and Problem Solved

The original patent focused on cardiac strain imaging using dense MRI with deep learning-based phase unwrapping. However, this technology has the potential to address various other industries and challenges. The new inventive concept tackles the limitation of the original patent by exploring new applications and use cases, thereby expanding the technology's reach and impact.

Detailed Description of the Inventive Concept

The inventive concept involves adapting the core technology of dense MRI with deep learning-based phase unwrapping to various new applications. In crop growth monitoring, dense MRI can encode displacement information of plant tissues into phase data, which is then unwrapped using a deep learning module. The resulting unwrapped phase data is analyzed to quantify plant growth. Similarly, in soil moisture evaluation, DENSE MRI is used to acquire displacement encoded MRI data of soil samples, which is then analyzed using a deep learning-based phase unwrapping algorithm to determine soil moisture levels. Other applications include detecting defects in composite materials, analyzing fluid dynamics in industrial pipelines, and monitoring biomechanical properties of implantable medical devices.

Novelty and Inventive Step

The new inventive concept introduces novel applications and use cases for dense MRI with deep learning-based phase unwrapping, going beyond cardiac strain imaging. The inventive step lies in recognizing the potential of this technology to address diverse challenges and developing new methods and systems to achieve this.

Alternative Embodiments and Variations

Alternative embodiments may include using different deep learning architectures or optimization techniques for phase unwrapping, or integrating the technology with other imaging modalities. Variations may include applying the technology to other biological tissues or materials, or using it for quality control in manufacturing processes.

Potential Commercial Applications and Market

The new inventive concept has significant commercial potential across various industries, including agriculture, construction, manufacturing, and healthcare. The market for these applications is substantial, with potential customers including farmers, construction companies, manufacturers, and medical device companies.

Field of Art

Medical imaging, specifically magnetic resonance imaging (MRI) with advanced signal processing and deep learning techniques for displacement and strain analysis

Person of Ordinary Skill (PHOSITA) Profile

A skilled practitioner with expertise in medical imaging, signal processing, machine learning, and MRI technologies, holding advanced degrees in biomedical engineering, electrical engineering, or related fields with demonstrated knowledge of deep learning neural network architectures

Obviousness Rationale

The published technical disclosure represents a straightforward extension of the source patent's core technology by applying the established deep learning-based phase unwrapping method to alternative domains. A PHOSITA would recognize that the fundamental signal processing technique of encoding displacement information into phase data and using neural networks for unwrapping is universally applicable across multiple material and biological systems. The technical principles of phase encoding, deep learning phase unwrapping, and displacement measurement remain consistent across different applications, making the variations predictable and obvious.

Obvious Combinations & Variations

Source Patent Element
U-Net structured convolutional neural network for phase unwrapping in cardiac MRI
PTD Variation
Applying U-Net CNN to phase unwrapping for crop growth monitoring and soil moisture evaluation
Obviousness Reasoning
Known machine learning technique applied to a predictable alternative domain with similar signal processing requirements
Source Patent Element
Displacement encoding technique using stimulated echo (DENSE) MRI
PTD Variation
Extending DENSE MRI to industrial pipeline fluid dynamics and composite material defect detection
Obviousness Reasoning
Transferring established imaging technique to alternative measurement scenarios with substantially similar technical challenges
Source Patent Element
Phase image generation and segmentation using convolutional neural networks
PTD Variation
Implementing CNN-based phase analysis for biomechanical property monitoring of implantable medical devices
Obviousness Reasoning
Predictable application of existing neural network segmentation and analysis techniques to a structurally similar measurement problem
Source Patent Element
Quantification of global and segmental strain from MRI data
PTD Variation
Adapting strain quantification methods to measure plant tissue displacement and growth
Obviousness Reasoning
Extending well-established measurement technique to biologically analogous systems using known signal processing methods
35 U.S.C. § 103 Summary: Based on the teachings of US Patent 11857288 and the published technical disclosure, a person having ordinary skill in the art would find the proposed variations in MRI phase unwrapping and displacement encoding across diverse domains to be obvious and predictable extensions of the existing technological framework, thereby rendering potential patent claims in these areas unpatentable under 35 U.S.C. ยง 103.

Original Patent Information

Patent NumberUS 11,857,288
TitleSystems and methods for phase unwrapping for dense MRI using deep learning
Assignee(s)University of Virginia Patent Foundation