Adaptive Phase Unwrapping for Cardiac Strain Analysis in Specialized Environments
Legal Citation
Summary of the Inventive Concept
A novel approach to phase unwrapping for cardiac strain analysis, tailored to meet the unique demands of high-stress, emergency response, extreme weather, high-security, and disaster relief scenarios.
Background and Problem Solved
The original patent disclosed a method for phase unwrapping in dense MRI using deep learning, which, while effective, has limitations in its applicability to specialized environments. The inventive concept addresses these limitations by adapting the phase unwrapping method to operate in real-time, utilizing portable MRI scanners, and incorporating dedicated hardware and software components to ensure robustness and security in these niche scenarios.
Detailed Description of the Inventive Concept
The inventive concept comprises a deep learning module configured to process displacement encoded MRI data in real-time, utilizing a dedicated GPU for accelerated processing. The system is designed to operate in high-stress environments, emergency response situations, extreme weather conditions, high-security environments, and disaster relief scenarios. The deep learning-based phase unwrapping algorithm is optimized for each specific scenario, ensuring accurate and reliable cardiac strain analysis. In high-security environments, the system encrypts displacement encoded MRI data, while in disaster relief scenarios, the system utilizes a portable MRI scanner and a dedicated CNN for epicardial and endocardial segmentation.
Novelty and Inventive Step
The inventive concept's novelty lies in its adaptation of the original phase unwrapping method to specialized environments, incorporating unique components and configurations to address the specific challenges of each scenario. The inventive step resides in the tailored design of the system and algorithm to ensure robustness, security, and accuracy in these niche applications.
Alternative Embodiments and Variations
Alternative embodiments of the inventive concept could include the use of other deep learning architectures, such as recurrent neural networks (RNNs) or transformers, to improve the accuracy and efficiency of the phase unwrapping algorithm. Variations could also include the integration of additional sensors or data sources to enhance the system's robustness and adaptability in different environments.
Potential Commercial Applications and Market
The inventive concept has significant commercial potential in various industries, including healthcare, emergency response, and disaster relief. The system's ability to operate in high-stress environments and provide accurate cardiac strain analysis in real-time makes it an attractive solution for hospitals, emergency responders, and disaster relief organizations.
Section 103 Obviousness Analysis (PHOSITA)
Field of Art
Medical imaging, specifically cardiac magnetic resonance imaging (MRI) with advanced signal processing and deep learning techniques for strain analysis
Person of Ordinary Skill (PHOSITA) Profile
A skilled practitioner with expertise in medical imaging, signal processing, deep learning neural networks, and MRI data analysis, typically holding a PhD or advanced engineering degree with specialized knowledge in medical image processing
Obviousness Rationale
A person having ordinary skill in the art would recognize that the published technical disclosure represents predictable variations of the source patent's core deep learning phase unwrapping methodology by adapting the fundamental technique to specialized environmental contexts. The core algorithmic approach remains substantially unchanged, with modifications representing routine engineering adaptations to different operational scenarios. The PTD's variations demonstrate standard design choices that would be apparent to a skilled practitioner familiar with medical imaging and deep learning techniques.
Obvious Combinations & Variations
Original Patent Information
| Patent Number | US 11,857,288 |
|---|---|
| Title | Systems and methods for phase unwrapping for dense MRI using deep learning |
| Assignee(s) | University of Virginia Patent Foundation |