Colonoscopy Polyp Tracking GUI With 3D Coverage Feedback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing colonoscopy procedures face challenges in accurately detecting and removing polyps due to operator fatigue, inattention, and limitations in visualization, leading to missed polyps and potential cancer risks.

Innovation Solution

A system and method for dynamically tracking 3D movement of an endoscopic camera within the colon, using neural networks to reconstruct 2D images into 3D, and generating a GUI that provides real-time feedback on polyp locations, coverage, and camera movement directions to ensure comprehensive imaging and polyp removal.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If real-time 3D reconstruction and tracking is implemented, then polyp detection accuracy is improved, but computational complexity and processing time increase

Engineering Contradiction:
Improvepolyp detection accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system pre-processes endoscopic images by segmenting the colon wall and lumen, and pre-computes 3D coordinates for pixels before polyp detection is needed. This preliminary 3D reconstruction enables faster real-time tracking and detection during the actual procedure, reducing computational burden during critical detection phases.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary coordinate system that maps 2D image pixels to 3D colon wall coordinates. This intermediary representation serves as a bridge between the endoscopic camera views and the actual polyp locations, enabling accurate detection without requiring complex direct 3D reconstruction during real-time operation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If comprehensive coverage tracking is implemented, then polyp detection completeness is improved, but system complexity increases

Engineering Contradiction:
Improvepolyp detection completenessVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system continuously tracks the 3D position of the endoscopic camera and provides real-time feedback on which portions of the colon have been imaged and which remain uncovered. This feedback mechanism guides the operator to ensure comprehensive coverage and prevents missed polyps, while the tracking complexity is managed through efficient coordinate transformation algorithms.

Inventive Principle:
Principle #23Feedback

3Measurement precision

If 3D reconstruction neural network is used, then visualization accuracy is improved, but processing speed decreases

Engineering Contradiction:
Improvevisualization accuracyVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSSpeed

Solution Approach 1:

The neural network performs 3D reconstruction on pre-captured endoscopic images before the procedure begins or during setup phases. This preliminary reconstruction creates accurate 3D models and coordinate mappings that can be reused during the actual colonoscopy, avoiding the need for real-time neural network processing during the procedure and thus maintaining both accuracy and speed.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3979892B1Systems and methods for processing colon images and videos
Publication Date: 2025.12.31 MAGENTIQ EYE LTD
  • EP3979892B1 patent drawingFigure 1
  • EP3979892B1 patent drawingFigure 2
  • EP3979892B1 patent drawingFigure 3

AI summary

There is provided a method of generating instructions for presenting a graphical user interface (GUI) for dynamically tracking at least one polyp in a plurality of endoscopic images of a colon of a patient, comprising: iterating for the plurality of endoscopic images: tracking a location of a region depicting at least one polyp within the respective endoscopic image relative to at least one previous endoscopic image, when the location of the region is external to the respective endoscopic image: computing a vector from within the respective endoscopic image to the location of the region external to the respective endoscopic image, creating an augmented endoscopic image by augmenting the respective endoscopic image with an indication of the vector, and generating instructions for presenting the augmented endoscopic image within the GUI.