Touch-Based Region of Interest Annotation for Medical Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical viewers are not amenable to touch-based interaction for annotating medical images, making it inefficient for healthcare professionals to annotate and analyze medical data.
Innovation Solution
A method and apparatus that enable touch-based interaction to generate and modify regions of interest on medical images using a touch-enabled device, allowing users to create, expand, shrink, disjoin, or merge annotations defined by virtual discs based on touch gestures, providing a simple and intuitive mechanism for annotating medical images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If control points are used for annotating medical images, then annotation precision is maintained, but ease of operation deteriorates due to lack of touch-based interaction support
Solution Approach 1:
The patent replaces traditional mouse-based control point manipulation with touch-based gestures. Users can create, select, and manipulate annotation regions directly by touching and dragging on the display screen, eliminating the need for precise control point handling with external devices. This substitution of interaction mechanism directly improves ease of operation while maintaining annotation functionality.
Solution Approach 2:
The patent introduces virtual discs as intermediary elements between the user's touch input and the final annotation region. When a user touches the screen, a virtual disc appears at that location, serving as a mediator that translates the touch gesture into a selectable annotation region. This intermediary simplifies the interaction by providing a visual feedback mechanism that guides users through the annotation process without requiring knowledge of complex control point systems.
2Productivity
If traditional medical viewers are used, then annotation functionality is provided, but productivity deteriorates due to inefficient interaction methods
Solution Approach 1:
The patent performs preliminary actions by automatically creating a default annotation region (virtual disc) at the user's touch location before any further manipulation is needed. This preliminary region creation eliminates the time required to manually define annotation boundaries from scratch. Users can immediately begin selecting and adjusting pre-created regions, significantly reducing the time required for annotation tasks compared to traditional methods where each annotation must be constructed step-by-step.
Solution Approach 2:
The patent implements dynamic manipulation of annotation regions through touch-based dragging. Users can select an annotation region and drag it to reposition, resize, or reshape it in real-time based on their needs. This dynamic interaction allows users to quickly adapt annotation regions without deleting and recreating them, improving annotation efficiency by enabling fluid, continuous adjustments during the workflow.
3Ease of operation
If control point-based annotation is used, then precise annotation control is achieved, but ease of operation worsens due to complexity of interaction
Solution Approach 1:
The patent uses color changes and visual transformations of the virtual disc to indicate different states and selection statuses. When a user touches and drags to create a selection, the virtual disc changes appearance to show it is selected and ready for manipulation. Visual feedback through color and appearance changes makes the interface more intuitive by clearly communicating system state without requiring users to understand complex control point mechanics.
Solution Approach 2:
The patent segments the annotation creation process into distinct phases: touch initiation, virtual disc creation, selection confirmation, and manipulation. Each phase has its own visual indicators and interaction patterns. This segmentation makes the overall process more intuitive by breaking down the complex task of creating precise annotations into manageable, visually distinct steps that users can follow naturally.
Data Source
AI summary
An apparatus is provided for generating a region(s) of interest for a medical image(s). The apparatus includes at least one memory and at least one processor configured to receive an indication of one or more touches at corresponding locations on a touch enabled display. The respective touches define a touch point at the corresponding location. The processor is further configured to generate one or more regions of interest associated with areas of a medical image(s) responsive to receipt of the indications. A location of respective regions of interest corresponds to locations of touch points. The processor is further configured to define a diameter of regions of interest based on a width/pressure of the touch points and define the regions of interest to include a disc including a contour(s). The regions of interest correspond to an area for annotating the medical image(s). Corresponding computer program products and methods are also provided.


