Fluorescence Image ROI Extraction for Artefact-Free Quantification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fluorescence measurements in biological samples are often affected by artefacts such as dust and bubbles, leading to inaccurate results due to the inclusion of non-analyte signals.
Innovation Solution
A method involving the use of a trained model for semantic segmentation to extract a region of interest free from artefacts, such as bubbles, dust, and shadows, from fluorescence images, followed by extrapolating the fluorescence intensity from this region to correct for artefacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If fluorescence measurement is performed on the entire sample area, then the measurement covers all regions including artefacts, but the measurement precision deteriorates due to inclusion of non-analyte signals from dust, bubbles, and cuvette walls
Solution Approach 1:
The patent applies segmentation by dividing the fluorescence image into multiple regions: a region of interest (ROI) free from artefacts and regions containing artefacts. The trained model automatically segments the image to identify and exclude artefact regions, allowing precise measurement from the clean ROI while ignoring contaminated areas.
Solution Approach 2:
The patent extracts the region of interest from the full fluorescence image by applying a trained model that identifies and removes artefact-containing regions. This extraction process isolates the clean signal from the analyte while eliminating contamination from dust, bubbles, and cuvette wall fluorescence.
2Measurement precision
If a trained model for semantic segmentation is applied to extract the region of interest, then the measurement precision is improved by excluding artefacts, but the device complexity increases due to the addition of image processing and model application components
Solution Approach 1:
The patent replaces manual or mechanical artefact removal methods with an automated image processing system based on a trained model. The model automatically identifies and segments artefact regions from the fluorescence image, eliminating the need for manual intervention or complex mechanical filtering systems.
Solution Approach 2:
The trained model performs self-service by automatically identifying and excluding artefact regions without requiring manual intervention. The system autonomously processes the fluorescence image, extracts the clean region of interest, and computes the fluorescence intensity, reducing operational complexity.
3Reliability
If multiple fluorescence images are acquired with different illumination and exposure combinations, then the reliability of the measurement is improved by having multiple options for selection, but the productivity decreases due to increased acquisition time and processing steps
Solution Approach 1:
The patent applies preliminary action by acquiring multiple fluorescence images with different illumination and exposure combinations before performing the final measurement. This allows the system to select the optimal image that provides the most reliable data while minimizing artefact interference, ensuring measurement quality before proceeding to analysis.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances the precision of fluorescence measurements by automatically identifying and excluding artefacts, allowing for accurate quantification of analytes despite their presence.
Implementation Method 1
Fluorescence is the ability from matter to emit light at a certain wavelength after absorbing electromagnetic radiation. Accordingly, a fluorescence measurement is performed by illuminating the sample, which is contained in a reading cuvette, at a selected excitation wavelength which corresponds to the excitation wavelength of an analyte of interest, and detecting and measuring the fluorescence emission of the sample induced by the excitation.
Data Source
AI summary
A method for performing fluorescence measurement on a sample, including: illuminating the sample using a light source, acquiring at least one fluorescence image of the illuminated sample, and processing the fluorescence image to determine a fluorescence intensity of the sample; characterized in that processing the fluorescence image to determine a fluorescence intensity of the sample includes: extracting, from the fluorescence image, a region of interest (ROI) free from artefacts, by application of a trained model, and determining the fluorescence intensity of the sample from the extracted region of interest.