Enhanced Systems and Methods for Optimizing Functional Images of a Lesion Region using Guided Diffuse Optical Tomography
Legal Citation
Summary of the Inventive Concept
This inventive concept improves upon existing guided diffuse optical tomography (DOT) systems by integrating machine learning, artificial intelligence, deep learning, and computer vision modules to enhance image quality, reduce noise, and optimize functional images of a lesion region.
Background and Problem Solved
The original patent, 'Systems and methods of optimizing functional images of a lesion region using guided diffuse optical tomography,' has limitations in image quality and noise reduction. This new inventive concept addresses these limitations by leveraging advanced computational techniques to improve the accuracy and efficiency of DOT systems.
Detailed Description of the Inventive Concept
The enhanced system comprises a DOT device integrated with a machine learning module, an artificial intelligence module, a deep learning module, or a computer vision module. These advanced computational modules are trained using datasets of images from multiple subjects to improve image quality and reduce noise. The system acquires lesion functional data from the lesion region and reference functional data from a healthy tissue region, applying the advanced computational techniques to generate optimized functional images. This integration enables the system to better distinguish between healthy and diseased tissues, leading to more accurate diagnoses and treatments.
Novelty and Inventive Step
The novelty of this inventive concept lies in the integration of advanced computational modules with DOT devices to improve image quality and reduce noise. This integration is non-obvious and provides a significant improvement over the original patent, enabling more accurate and efficient diagnoses.
Alternative Embodiments and Variations
Alternative embodiments of this inventive concept could include integrating different types of machine learning algorithms, using various deep learning architectures, or incorporating computer vision techniques for image segmentation. Additionally, the system could be adapted for use in other medical imaging applications, such as imaging other types of cancer or diseases.
Potential Commercial Applications and Market
This enhanced system has significant commercial potential in the medical imaging industry, particularly in the diagnosis and treatment of breast cancer. The improved image quality and reduced noise enable more accurate diagnoses, leading to better patient outcomes and reduced healthcare costs. The system could be marketed to hospitals, clinics, and research institutions, and could also be used in other medical imaging applications.
Section 103 Obviousness Analysis (PHOSITA)
Field of Art
Medical imaging, specifically diffuse optical tomography (DOT) for breast cancer diagnostics, requiring expertise in optical imaging, signal processing, computational methods, and medical image analysis
Person of Ordinary Skill (PHOSITA) Profile
A skilled practitioner with advanced degrees in biomedical engineering, medical physics, or computational imaging, possessing knowledge of medical imaging techniques, machine learning, signal processing algorithms, and image optimization strategies
Obviousness Rationale
A person having ordinary skill in the art would recognize that integrating machine learning and computational modules with existing DOT systems represents a predictable and logical extension of the source patent's imaging optimization techniques. The PTD's proposed computational enhancements directly address known challenges in medical image quality and noise reduction using standard machine learning approaches. These variations would be considered obvious improvements that leverage well-established computational techniques to enhance the original DOT imaging methodology.
Obvious Combinations & Variations
Original Patent Information
| Patent Number | US 11,857,289 |
|---|---|
| Title | Systems and methods of optimizing functional images of a lesion region using guided diffuse optical tomography |
| Assignee(s) | Washington University |