Ultrasound–Optoacoustic Feature Scoring for Axillary Lymph Node Metastasis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Breast cancer prognosis and therapeutic approaches are hindered by the heterogeneous nature of the disease, and current ultrasound imaging lacks sufficient prognostic information, limiting clinical value beyond tumor size assessment.
Innovation Solution
A system and method for analyzing ultrasound and optoacoustic images to obtain feature scores, applying them to a classification model to provide prognostic and predictive results, including likelihood of malignancy, lymph node metastasis, and molecular subtypes, using a graphical user interface to manage feature score entry and display prognostic indicia.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional ultrasound imaging is used for breast cancer assessment, then the examination process is simple and quick, but the prognostic information provided is insufficient and limited to tumor size assessment
Solution Approach 1:
The patent combines ultrasound imaging with optoacoustic imaging modalities to create a hybrid system that provides both structural information from ultrasound and functional/biochemical information from optoacoustic signals, thereby overcoming the information limitation of traditional ultrasound while managing complexity through integrated hardware and software architecture
Solution Approach 2:
The imaging system is designed to perform multiple functions: standard ultrasound imaging, optoacoustic imaging, and automated feature score calculation for multiple cancer traits simultaneously, allowing a single system to provide comprehensive prognostic information across multiple parameters without requiring separate specialized devices
2Measurement precision
If feature scores are calculated for multiple zones (internal, boundary, peripheral) to improve diagnostic accuracy, then the measurement precision increases, but the ease of operation decreases due to complex scoring procedures
Solution Approach 1:
The system implements automated image analysis algorithms that automatically calculate feature scores for internal, boundary, and peripheral zones without requiring manual intervention, thereby maintaining high measurement precision through consistent automated scoring while improving ease of operation by eliminating complex manual scoring procedures
Solution Approach 2:
The system pre-processes images to automatically identify and delineate the internal, boundary, and peripheral zones before score calculation, and provides real-time guidance and validation during the scoring process, thereby ensuring measurement precision through proper zone definition while simplifying operation by preparing the scoring framework in advance
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances prognostic and predictive capabilities of breast cancer assessment, providing semi-quantitative diagnostic biomarkers and enabling more informed therapeutic decisions by overcoming limitations of traditional ultrasound imaging.
Implementation Method 1
optoacoustic images acquired in connection with an examination for a region of interest (ROI)
Data Source
AI summary
Systems, methods and computer program products are provided for analyzing at least one of ultrasound (US) images or optoacoustic (OA) images (US/OA images), comprising: a display configured to display at least a first image from at least one of OA images or US images acquired in connection with an examination for a region of interest (ROI), the first image including a lesion, the first image overlaid with an interior ROI outline separating an internal zone from a boundary zone of the ROI, the first image overlaid with an exterior ROI outline separating the boundary zone from a peripheral zone; a graphical user interface (GUI); memory configured to store program instructions; and one or more processors configured to execute the programmable instructions to: obtain feature scores in connection with at least the boundary zone and peripheral zone of the first image; apply the feature scores to a classification model to obtain predictive result indicative of a trait of the lesion, the predictive result indicating at least one of a presence or absence of metastasis lymph nodes and several lymph nodal metastasis; and output the predictive result.