Medical Image Contrast Enhancement via Pixel Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Medical images, such as X-ray fluoroscopic images, often suffer from noise due to limitations in imaging speed and radiation dosage, making it difficult to visualize structures like blood vessels and implanted devices effectively.

Innovation Solution

An apparatus using processors to enhance the contrast between the object of interest and the background in medical images by determining specific pixel values and applying adjustments or filters, such as sharpening filters, to generate a target image with improved visibility of the object of interest.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If medical images are acquired using existing medical imaging technologies, then imaging speed and radiation dosage are limited, but noise increases and visibility of structures deteriorates

Engineering Contradiction:
Improvevisibility of structuresVSAvoidnoise
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent extracts and enhances the object of interest from the noisy medical image by identifying pixels associated with the object versus background, then selectively adjusting only the object pixels to improve visibility without amplifying background noise

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies different processing to different regions of the image: object pixels receive contrast enhancement while background pixels maintain their original characteristics, creating local quality differentiation that improves target visibility without degrading overall image quality

Inventive Principle:
Principle #3Local quality

2Reliability

If contrast enhancement is applied to improve visibility of the object of interest, then visibility improves, but image processing complexity increases

Engineering Contradiction:
Improvevisibility of object of interestVSAvoidimage processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the image into object-associated pixels and background pixels using a segmentation mask, then applies contrast enhancement only to the object pixels. This segmentation approach simplifies the processing by avoiding full-image manipulation while achieving targeted enhancement

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent modifies pixel values through controlled parameter adjustments (adding constants, applying multipliers) rather than complex transformations, achieving contrast enhancement through simple arithmetic operations that reduce processing complexity

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS12190508B2Systems and methods for enhancing medical images
Publication Date: 2025.01.07 SHANGHAI UNITED IMAGING INTELLIGENCE CO LTD
  • US12190508B2 patent drawing
  • US12190508B2 patent drawing
  • US12190508B2 patent drawing

AI summary

Described herein are systems, methods, and instrumentalities associated with medical image enhancement. The medical image may include an object of interest and the techniques disclosed herein may be used to identify the object and enhance a contrast between the object and its surrounding area by adjusting at least the pixels associated with the object. The object identification may be performed using an image filter, a segmentation mask, and/or a deep neural network trained to separate the medical image into multiple layers that respectively include the object of interest and the surrounding area. Once identified, the pixels of the object may be manipulated in various ways to increase the visibility of the object. These may include, for example, adding a constant value to the pixels of the object, applying a sharpening filter to those pixels, increasing the weight of those pixels, and/or smoothing the edge areas surrounding the object of interest.