Medical Image Lesion Annotation Layout for Reduced Display Clutter
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical imaging technologies display excessive information on multiple lesions, obstructing the original image and prolonging diagnosis time, with practitioners potentially missing important details.
Innovation Solution
A method and device for generating contours around lesions based on lesion information, considering overlapping regions, relevance, and probability, and optimizing arrow and text placement to prioritize and clarify lesion information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all information on multiple detected lesions is displayed on one medical image, then complete lesion information is provided, but the original image is obstructed and diagnosis time increases
Solution Approach 1:
The patent segments lesion information display by creating separate contour representations for different lesions. Each lesion is outlined with a contour that can be individually controlled, allowing the system to display multiple lesions without overwhelming the original image. The segmentation is further refined by categorizing lesions into different groups (e.g., suspicious, benign, malignant) and applying different display priorities to each group.
Solution Approach 2:
The patent applies local quality by making different parts of the displayed information have different visual properties. Contours for different lesions are displayed with varying line thicknesses, colors, or transparency levels based on their diagnostic importance. This allows critical lesions to stand out while less critical ones remain subtle, enabling rapid diagnosis without information loss.
2Loss of information
If all lesion information is displayed on the medical image, then comprehensive diagnosis data is available, but the information becomes excessive and obstructs the original image
Solution Approach 1:
The patent implements partial action by selectively displaying only the most relevant lesion information based on diagnostic priorities. The system determines which lesions require immediate attention and displays their contours prominently, while suppressing or minimizing the display of less critical lesions. This partial display approach prevents information clutter while ensuring that essential diagnostic information remains visible.
Solution Approach 2:
The patent resolves information clutter by transitioning from a two-dimensional overlay problem to a multi-dimensional solution space. It introduces additional dimensions such as display priority levels, temporal sequencing (displaying lesions in order of importance), and interactive filtering capabilities. This allows comprehensive lesion information to be organized in a structured manner that prevents visual clutter on the original image.
3Loss of information
If multiple lesion contours are displayed on the medical image, then all lesions are visualized, but the original image clarity is reduced
Solution Approach 1:
The patent applies dynamics by making the display of lesion contours adaptive rather than static. The system dynamically adjusts contour visibility, opacity, and prominence based on factors such as lesion type, location, diagnostic urgency, and the specific viewing context. This dynamic display approach ensures that contour information is always present for complete lesion detection while automatically optimizing image clarity by reducing contour prominence in areas where they would most interfere with viewing the original anatomy.
Data Source
AI summary
A method for operating a medical imaging device includes obtaining lesion information on at least one lesion detected from a medical image, determining a shape and a position of at least one contour corresponding to the at least one lesion based on the obtained lesion information, determining a position of at least one text region that includes a text indicating the lesion information on the at least one lesion in the medical image, and displaying the at least one contour and the text included in the at least one text region on the medical image, based on the determined shape and position of the at least one contour and the determined position of the at least one text region.