Medical Image Transfer Functions from 2D and 3D Annotations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional medical imaging software relies on pre-defined transfer functions that are not always adapted to the specific analysis, requiring tedious manual adjustments and lacking optimal optimization, and there is a need for improved communication between radiologists using 2D interfaces and surgeons using 3D interfaces for disease diagnosis and surgery preparation.
Innovation Solution
A semi-automatic method for visualizing medical images using annotations to adapt transfer functions, allowing dynamic and interactive adjustments between 2D and 3D interfaces, enabling users to optimize the representation based on image content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If multiple separate applications are used to represent different views of the same object, then comprehensive information is provided, but navigation complexity and time increase
Solution Approach 1:
The patent combines multiple separate application instances into a single integrated application that can display multiple views simultaneously. The system merges the functionality of what would otherwise require separate applications (e.g., 2D plan view, 3D model view, schedule view) into one unified interface, allowing users to access comprehensive information without navigating between multiple applications.
Solution Approach 2:
The patent creates a universal application interface that performs multiple functions simultaneously. A single application instance can display different views (2D, 3D, Gantt chart, etc.) of the same construction project, and users can switch between views or display multiple views concurrently within the same application window, making the application multi-functional rather than requiring separate specialized applications for each view type.
2Loss of information
If multiple separate applications are used to represent different views of the same object, then comprehensive information is provided, but interface complexity increases
Solution Approach 1:
The patent merges multiple view types and information representations into a single unified application interface. Instead of having separate applications for 2D plans, 3D models, and schedules, the system integrates all these views within one application, reducing the number of interfaces users must navigate and manage.
Solution Approach 2:
The patent adds a temporal dimension to the interface by allowing users to synchronize multiple views to the same point in time. The interface evolves from static separate views to a dynamic multi-dimensional display where spatial views (2D/3D) and temporal views (schedules) are coordinated, enabling comprehensive information display without proportionally increasing interface complexity.
3Stability of the object's composition
If traditional synchronization methods are used between separate applications, then view consistency is maintained, but synchronization accuracy deteriorates due to timing issues
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors and adjusts the synchronization between different views. When a user interacts with one view (e.g., selecting a component in the 3D model), the system provides feedback by automatically updating related views (e.g., highlighting the corresponding element in the 2D plan and updating the schedule view), ensuring consistent state across all views without manual intervention.
Solution Approach 2:
The patent establishes predetermined synchronization rules and relationships between different views before user interaction. The system pre-configures which views should be linked and how they should synchronize, so that when data changes in one view, the appropriate updates are automatically propagated to related views according to pre-established rules, improving synchronization accuracy without requiring real-time manual coordination.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention concerns a method implemented by computer means for visualizing at least a zone of an object in at least one interface, said method comprising the following steps: obtaining at least one image of said zone, said image comprising at least one channel, said image being a 2-dimensional or 3-dimensional image comprising pixels or voxels, a value being associated to each channel of each pixel or voxel of said image, a representation of said image being displayed in the interface, obtaining at least one annotation from a user, said annotation defining a group of selected pixels or voxels of said image, calculating a transfer function based on said selected pixels or voxels and applying said transfer function to the values of each channel of the image, updating said representation of the image in the interface, in which the colour and the transparency of the pixels or voxels of said representation are dependent on the transfer function.