Automated Image Segmentation for Medical Diagnosis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual enhancement of complex, large, irregular-shaped anatomical features in medical images is time-consuming for physicians, hindering efficient diagnosis.

Innovation Solution

An automated method and system for image segmentation and visualization that separates images into tissue clusters, selects foreground clusters, generates contours, and displays them, utilizing a processor and imaging scanner to facilitate efficient contouring and quantification of heterogeneous objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual enhancement of anatomical features is performed by the physician, then the ability to enhance relevant features is improved, but the time consumption increases significantly

Engineering Contradiction:

Improvefeature enhancement qualityVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic segmentation and contour generation using computer algorithms that analyze image data independently, without requiring continuous physician intervention. The processor automatically identifies anatomical structures, generates contours, and produces segmented images, enabling the system to serve itself in the enhancement process while maintaining high quality results

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of physician-based feature enhancement is replaced with an automated computational system. The processor executes algorithms that perform segmentation, contour generation, and image enhancement tasks that were previously performed manually, substituting human manual work with automated computational mechanisms

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated segmentation is implemented, then productivity is improved, but measurement precision may be reduced

Engineering Contradiction:

Improvecontouring efficiencyVSAvoidsegmentation accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system incorporates feedback mechanisms where the processor analyzes the segmented regions and contours generated, and can iteratively refine the segmentation results. The system provides feedback on the quality of segmentation and allows for adjustment of parameters to optimize both speed and accuracy, ensuring high measurement precision is maintained while achieving automated productivity

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The image processing is divided into distinct segmentation steps including tissue clustering, foreground cluster identification, and contour generation. This multi-stage segmentation approach allows each step to be optimized independently, maintaining high precision while achieving automated processing efficiency through systematic division of the enhancement task

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS9262834B2Systems and methods for performing segmentation and visualization of images

Publication Date: 2016.02.16 GE PRECISION HEALTHCARE LLC

AI summary

A method for visualizing an object of interest includes obtaining an image of an object of interest, automatically separating the image into tissue clusters, automatically selecting foreground clusters from the tissue clusters, automatically generating a contour based on the selected foreground clusters, and displaying an image of the object of interest including the foreground clusters and the contour. A system and non-transitory computer readable medium are also described herein.