Redness Differentiation Calibration for Endoscopic Image Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Endoscopic imaging systems face inadequate red color gradation due to unclear spectral discrimination in red wavelength bands, leading to difficulties in diagnosis and surgery.

Innovation Solution

A redness differentiation calibration method that converts RGB to CIELAB color space, performs redness intensity estimation and edge information extraction, and applies calibration to enhance red color gradation in medical images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional endoscopic imaging is used, then the imaging system is simple and easy to operate, but the red color gradation is inadequate and spectral discrimination is unclear

Engineering Contradiction:
Improvespectral discrimination precisionVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces CIELAB color space as an intermediary representation between the captured RGB image and the final displayed image. By converting to L*a*b* color space and processing the a* and b* channels separately, the system achieves improved spectral discrimination without requiring complex hardware modifications. The intermediary color space allows for selective enhancement of red wavelength discrimination while maintaining overall image integrity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent applies parameter changes by modifying the a* and b* channel values through nonlinear transformation functions. Specifically, it applies gain adjustments and gamma corrections to these channels to enhance the discrimination of red wavelength reflections from mucosa, blood vessels, and tissues. This parameter manipulation improves spectral precision without adding physical complexity to the imaging system.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If red color gradation is enhanced through processing, then color differentiation improves, but processing time and computational load increase

Engineering Contradiction:
Improvecolor differentiation precisionVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the color processing task by separating the L*, a*, and b* channels and applying different processing strategies to each. The L* channel (luminance) is processed separately from the a* and b* channels (color information). This segmentation allows for optimized processing where only the color channels require intensive nonlinear transformation, while the luminance channel can be handled more efficiently, reducing overall processing time.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by focusing computational resources only on the a* and b* channels which contain the red wavelength information, rather than processing the entire image uniformly. The L* channel is processed with simpler operations, and the enhancement is applied selectively to regions containing blood vessels and mucosal tissue, reducing unnecessary computational overhead in areas where color differentiation is less critical.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4693171A1Redness differentiation calibration (RDC) method for medical image
Publication Date: 2026.02.11 WEYO SURGICAL TECHNOLOGY LTD
  • EP4693171A1 patent drawingFigure 1~2
  • EP4693171A1 patent drawingFigure 3~4
  • EP4693171A1 patent drawingFigure 5~6

AI summary

The present invention relates to the technical field of image processing, and in particular to a redness differentiation calibration (R.D.C.) method for medical images. The method includes the following steps: acquiring an original image to obtain L, a, and b values of the original image, performing redness intensity estimation on the original image using the a and b values, performing edge information extraction on the original image using the L value, performing calibration on the original image by calculation to obtain a calibration result LQ, and converting a CIELAB color space of the original image to an RGB color space using the obtained LQ, a, and b values, and outputting a resulting image. Compared with conventional methods, the present technical solution can effectively estimate the redness intensity, calibrate mucosal structures and tissue features, and highlight micro-vessels in the superficial mucosa and submucosa of endoscopic images, while introducing minimal alterations to non-red regions, thus making processed images more suitable for doctors to make observation and make diagnoses.