Grating Interferometer Contrast and Resolution via CNN
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Grating interferometers face challenges in simultaneously achieving high contrast sensitivity and spatial resolution, making it difficult to acquire images with both high sensitivity and resolution.
Innovation Solution
The use of a machine learning-based system that includes a grating interferometer image acquisition unit, a numerical phantom generation unit, a convolution layer generation unit, an activation function application calculation unit, a CNN repetitive machine learning unit, and an image matching output unit to enhance contrast sensitivity and resolution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a grating interferometer is used to achieve high contrast sensitivity, then the ability to detect subtle variations in the sample is improved, but the spatial resolution deteriorates
Solution Approach 1:
The patent segments the imaging process into multiple measurements taken at different sample positions relative to the grating interferometer. By acquiring images at multiple positions and combining them through machine learning, the system achieves both high contrast sensitivity and high spatial resolution that cannot be obtained at any single position alone.
Solution Approach 2:
The patent introduces a new dimension by adding the sample position parameter to the imaging process. Instead of relying on a single imaging configuration, the system varies the sample position relative to the grating interferometer and uses machine learning to synthesize information across this additional dimensional parameter, thereby resolving the contradiction between contrast sensitivity and spatial resolution.
2Measurement precision
If machine learning processing is applied to enhance image quality, then contrast sensitivity and resolution are improved, but computational complexity and processing time increase
Solution Approach 1:
The patent applies preliminary action by performing machine learning training offline to create a pre-trained model. Once trained, the model can be deployed for rapid inference on new images without requiring complex real-time computation during actual imaging, thus reducing the computational burden during operational use.
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
This approach allows for the improvement of both contrast sensitivity and spatial resolution in grating interferometers, enabling the extraction of high-quality image information with enhanced sensitivity and resolution.
Implementation Method 1
phase-contrast imaging using a grating interferometer in which an interference principle is applied to radiation
Data Source
AI summary
The present disclosure relates to an apparatus for enhancing contrast sensitivity and resolution in a grating interferometer by machine learning, which can improve both image contrast sensitivity and spatial resolution in a grating interferometer by machine learning, the apparatus including: an image acquisition unit; a numerical phantom generation unit, a convolution layer generation unit to extract features from input data; an activation function application calculation unit that can apply a rectified linear activation function to an output value of the convolution calculation to perform smooth repetitive machine learning; a CNN repetitive machine learning unit that corrects a convolution calculation factor while repeatedly performing forward propagation and backward propagation processes; and an image matching output unit that matches and outputs features extracted by repetitive machine learning of the CNN repetitive machine learning unit.