Ultrasound Lesion Categorization With Multi-Image Basis Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ultrasound diagnostic systems struggle to accurately determine the medical examination or diagnosis category of a lesion part by referring to multiple ultrasound images, as the basis for the determination may not be clearly understood.
Innovation Solution
An ultrasound diagnostic apparatus that identifies characteristics of a lesion part through multiple ultrasound images, extracts a basis image contributing to the determination, and displays the determination route and basis image on a monitor, enabling accurate categorization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple ultrasound images are referred to for determining lesion characteristics, then the accuracy of determination is improved, but the clarity of determination basis for users deteriorates
Solution Approach 1:
The extraction unit extracts at least one basis image from multiple ultrasound images that contributed to the determination result. This separates the essential visual evidence from the complete image set, allowing users to clearly see which specific images formed the basis of the determination while maintaining access to all original images if needed.
Solution Approach 2:
The determination result display serves as an intermediary between the multiple ultrasound images and the user's understanding. It presents the extracted basis images alongside the determination result, creating a clear visual link between the evidence (images) and the conclusion (determination result), thereby enhancing transparency without requiring users to analyze all original images.
2Reliability
If multiple ultrasound images are analyzed for lesion characteristics, then the reliability of diagnosis is improved, but the complexity of the system increases
Solution Approach 1:
The system segments the determination process into distinct functional units: an identification unit that analyzes multiple ultrasound images to identify lesion characteristics, an extraction unit that selects basis images, and a display unit that presents results. This modular segmentation maintains high diagnostic reliability through comprehensive image analysis while managing system complexity through clear functional separation.
Solution Approach 2:
The extraction unit creates a copy of the essential basis images from the multiple original ultrasound images. This copy serves as a simplified representation that retains the diagnostic information needed for understanding the determination basis, reducing the cognitive load on users without sacrificing diagnostic reliability.
3Adaptability or versatility
If comprehensive determination procedures with multiple branches are implemented, then the versatility of diagnosis is improved, but the ease of operation deteriorates
Solution Approach 1:
The system provides visual feedback by displaying the extracted basis images alongside the determination result and procedure information. This feedback mechanism allows users to verify which images supported each determination step, making the complex multi-branch procedure more transparent and easier to follow without reducing diagnostic versatility.
Solution Approach 2:
The extraction unit performs preliminary action by pre-selecting and preparing the basis images before user review. This preliminary processing organizes the visual evidence in advance, so users receive a curated set of relevant images rather than having to search through all original images, thereby simplifying the operation of interpreting complex determination results.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
There are provided an ultrasound diagnostic apparatus and a control method of the ultrasound diagnostic apparatus which can determine a medical examination category or a diagnosis category of a lesion part and accurately understand the basis of the determination by referring to a plurality of ultrasound images. Characteristics of the lesion part for a determination item for route selection in a plurality of branches of a determination procedure stored in a determination procedure memory are identified on the basis of a plurality of ultrasound images in which the same lesion part is imaged, at least one ultrasound image contributing to identification of the characteristics in the plurality of branches of the determination procedure is extracted from the plurality of ultrasound images as a basis image, the route selection in the plurality of branches of the determination procedure is performed by applying the identified characteristics to the determination item to determine the medical examination category or the diagnosis category of the lesion part, and a route in the determination procedure in a case where the medical examination category or the diagnosis category is determined and the extracted basis image are displayed on the monitor.