Guided 2D Colon Screening with Unseen Area Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Slice-based visual inspection of the colon for polyp detection in virtual colonoscopy is challenging due to the convoluted structure of the colon, leading to potential missed anomalies and inefficiencies, as radiologists must manually scroll through numerous two-dimensional images while avoiding air-filled structures like the small intestine.
Innovation Solution
A method that provides visual feedback by dynamically deriving a centerline within the colon, marking seen areas in a distinctive color, and calculating unseen areas by subtracting seen voxels from the total colon surface, allowing for guided navigation and focus on unobserved regions during two-dimensional colon screening.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If radiologists manually scroll through numerous two-dimensional images for polyp detection, then they can examine the colon surface, but the convoluted structure of the colon causes them to miss areas and inefficiently navigate through air-filled structures
Solution Approach 1:
The system provides visual feedback by dynamically deriving a centerline within the colon and marking seen areas in a distinctive color. This feedback mechanism allows radiologists to see which areas have been examined and which remain unobserved, guiding their navigation through the convoluted colon structure and preventing missed areas while improving examination efficiency
Solution Approach 2:
The centerline derivation acts as an intermediary guide between the radiologist and the complex colon anatomy. By calculating and displaying the centerline path, the system mediates the navigation process, helping radiologists efficiently traverse the convoluted colon structure without getting lost in air-filled structures
2Reliability
If radiologists manually navigate through two-dimensional colon images, then they can detect polyps, but they may inadvertently skip areas due to the convoluted colon structure
Solution Approach 1:
The visual feedback mechanism marks seen areas in a distinctive color, providing real-time information about the navigation path taken. This prevents radiologists from inadvertently skipping areas by making the examined path visible, thereby reducing time wasted on incorrect or redundant navigations
Solution Approach 2:
The system preliminarily calculates and displays the centerline path before the radiologist begins detailed examination. This preliminary guidance establishes the optimal navigation path in advance, preventing time-consuming detours and ensuring comprehensive coverage of all colon segments
3Reliability
If the system calculates and displays unseen areas during two-dimensional colon screening, then polyp detection accuracy improves, but the complexity of the imaging system increases
Solution Approach 1:
The system performs self-service by automatically deriving the centerline and calculating unseen areas without requiring complex manual intervention. The automated algorithms handle the computational complexity internally, presenting simplified visual feedback to the radiologist while maintaining high detection accuracy
Solution Approach 2:
The system changes parameters dynamically by calculating the centerline path and marking seen areas based on the navigation progress. These parameter changes (color marking, centerline derivation) are computed automatically during the examination process, adding complexity only where needed while maintaining overall system simplicity
Data Source
AI summary
A method and system for displaying unseen areas in guided two dimensional (2D) colon screening, includes calculating segmentation and colon surface for a colon; calculating a centerline for the colon; designating as a current focus point a current point of intersection of a current portion of the centerline and a current cross-sectional image of a colon in a current image plane; and extracting a colon surface portion in a connected colon component containing the current focus point; and marking voxels of the colon surface portion as a “seen” area. Unseen areas of the colon surface are calculated by subtracting seen areas from the total colon area of observation. The unseen areas may then be displayed.