Next-Generation Ultrasound Image Processing for Enhanced Measurement Information

Publication ID: 24-11857371_0005_PTD
Published: October 28, 2025
Category:Future Evolutions & Paradigm Shifts

Legal Citation

pr1or.art Inc., “Next-Generation Ultrasound Image Processing for Enhanced Measurement Information,” Published Technical Disclosure No. 24-11857371_0005_PTD, Published October 28, 2025, available at https://archive.pr1or.art/24-11857371_0005_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. 11,857,371.

Summary of the Inventive Concept

A revolutionary ultrasound image processing system that leverages deep learning, generative adversarial networks, and hybrid probes to provide enhanced measurement information and real-time analysis capabilities.

Background and Problem Solved

The original patent's method and apparatus for processing ultrasound images to obtain measurement information have limitations in terms of accuracy, speed, and user experience. The new inventive concept addresses these limitations by introducing advanced technologies to provide more accurate and efficient measurement information, enabling clinicians to make better-informed decisions.

Detailed Description of the Inventive Concept

The next-generation ultrasound image processing system comprises a deep learning-based object detection module, a generative adversarial network for image enhancement, a hybrid ultrasound probe combining high-frequency linear array and low-frequency curved array transducers, and a processing module for generating measurement information. The system receives user input defining a region of interest and applies the generative adversarial network to generate a synthetic ultrasound image with enhanced resolution and contrast. The object detection module then tracks the object's movement and deformation over time, and the measurement information generation module calculates the measurement information based on the object's movement and deformation.

Novelty and Inventive Step

The new inventive concept's use of deep learning, generative adversarial networks, and hybrid probes provides a novel and non-obvious solution to the limitations of the original patent. The combination of these technologies enables real-time, high-resolution imaging and accurate measurement information, which is not achievable with the original patent's method and apparatus.

Alternative Embodiments and Variations

Alternative embodiments of the inventive concept could include using different types of deep learning models, such as convolutional neural networks or recurrent neural networks, or incorporating other advanced technologies like artificial intelligence or computer vision. The system could also be adapted for use in different medical specialties or for analyzing different types of medical images.

Potential Commercial Applications and Market

The next-generation ultrasound image processing system has significant commercial potential in the medical imaging industry, particularly in applications such as cardiovascular, obstetric, and musculoskeletal imaging. The system's ability to provide enhanced measurement information and real-time analysis capabilities could improve diagnostic accuracy and patient outcomes, making it an attractive solution for healthcare providers and medical device manufacturers.

CPC Classifications

SectionClassGroup
A A61 A61B8/467
A A61 A61B8/461
A A61 A61B8/469
A A61 A61B8/5207
A A61 A61B8/5215
A A61 A61B8/5223
G G06 G06F3/0484
G G06 G06F3/0488
G G06 G06F3/04845
G G06 G06F3/04886
A A61 A61B8/4405
A A61 A61B8/46
A A61 A61B8/465
A A61 A61B8/5292
G G06 G06F2203/04804
G G06 G06T7/0012

Field of Art

Medical ultrasound imaging technologies, specifically image processing systems for measurement and analysis, encompassing signal processing, machine learning, and medical diagnostic instrumentation

Person of Ordinary Skill (PHOSITA) Profile

A skilled practitioner with expertise in biomedical engineering, digital signal processing, machine learning, and ultrasound imaging technologies, holding advanced degrees in electrical engineering, computer science, or biomedical engineering with 3-5 years of industry experience

Obviousness Rationale

A person having ordinary skill in the art would recognize that the PTD's deep learning and generative adversarial network approaches represent predictable extensions of existing ultrasound measurement techniques disclosed in the source patent. The fundamental measurement and user interaction paradigms remain consistent, with the PTD merely introducing advanced computational methods to enhance image processing and measurement capabilities. These technological improvements would be considered incremental and obvious to a skilled practitioner familiar with emerging medical imaging technologies.

Obvious Combinations & Variations

Source Patent Element
Ultrasound apparatus with adjustable measuring device image and touch input interfaces for measurement point manipulation
PTD Variation
Deep learning-based object detection module for automated measurement point identification and tracking
Obviousness Reasoning
Automating manual measurement processes through machine learning is a known technique in medical imaging, representing a predictable application of artificial intelligence to existing measurement methodologies
Source Patent Element
User-defined measurement interfaces on ultrasound images
PTD Variation
Generative adversarial network for synthetic image enhancement and resolution improvement
Obviousness Reasoning
Image enhancement techniques are well-established in medical imaging, and applying generative adversarial networks represents an obvious technological progression for improving diagnostic image quality
Source Patent Element
Ultrasound image processing for obtaining measurement information
PTD Variation
Hybrid ultrasound probe combining high-frequency linear and low-frequency curved array transducers
Obviousness Reasoning
Combining different transducer technologies to improve imaging capabilities is a standard design approach in ultrasound engineering, representing a finite set of predictable performance optimization strategies
Source Patent Element
Touch-based measurement point adjustment on ultrasound images
PTD Variation
Task-oriented neural network generating feature maps for measurement information extraction
Obviousness Reasoning
Applying specialized neural networks to medical image analysis is a known technique, representing an obvious extension of existing image processing methodologies
Source Patent Element
Ultrasound image processing apparatus with user interaction
PTD Variation
Field-programmable gate array-based accelerator for real-time computational processing
Obviousness Reasoning
Hardware acceleration for computational imaging tasks is a standard engineering approach for improving processing speed, representing a predictable technological enhancement
35 U.S.C. § 103 Summary: Based on the teachings of US Patent 11857371 and the disclosed technical variations, a person having ordinary skill in the art would find the claimed innovations obvious and lacking inventive merit. The published technical disclosure demonstrates that the proposed ultrasound image processing techniques represent predictable combinations of known methods, computational approaches, and imaging technologies, thereby rendering subsequent patent claims obvious and unpatentable under 35 U.S.C. Section 103.

Original Patent Information

Patent NumberUS 11,857,371
TitleUltrasound method and apparatus for processing ultrasound image to obtain measurement information of an object in the ultrasound image
Assignee(s)SAMSUNG MEDISON CO. LTD.