Lens-Free Particle Detection Using Z-Stack Sparsity Focus Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing lensless imaging methods struggle to accurately count and classify platelets in whole blood due to high background noise from lysed red blood cells, and existing deep neural network-based methods require extensive and expensive data acquisition and are influenced by measurement machine variability.
Innovation Solution
A lensless imaging particle detection device that processes z-images using a sparsity measure and Gaussian windowing to determine optimal focus planes, followed by a metric calculation to distinguish platelets from background noise, utilizing a modified pq-mean sparsity measure and Gaussian metrics to enhance counting and classification accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deep neural network-based methods are used for particle detection, then counting accuracy may be improved, but data acquisition cost and time increase significantly
Solution Approach 1:
The patent segments the particle detection problem into distinct size-based categories (small particles <3 pixels, medium particles 3-7 pixels, large particles >7 pixels). This segmentation allows the use of simple pixel-counting rules instead of complex deep neural networks, dramatically reducing data acquisition and processing time while maintaining accurate particle classification and counting.
2Measurement precision
If deep neural network-based methods are used for particle detection, then counting accuracy may be improved, but system complexity and cost increase
Solution Approach 1:
The patent extracts and utilizes only the essential feature (particle size in pixels) from the complex image data, discarding the need for complex deep neural network architectures. By focusing on the fundamental size distinction that matters for particle classification, the system achieves accurate counting with minimal computational complexity and lower system costs.
3Measurement precision
If conventional particle detection methods are used in lysed blood, then platelet counting is possible, but background noise from lysed red blood cells obscures particle detection
Solution Approach 1:
The patent applies local quality analysis by examining the spatial distribution and size characteristics of particles in specific regions. By analyzing local particle properties (pixel count, size category) rather than relying on global image features, the method can distinguish platelets from lysed red blood cell debris even in noisy backgrounds, maintaining counting accuracy in challenging samples.
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
The device provides reliable platelet counting and classification in whole blood by reducing background noise interference, improving accuracy and reducing computational complexity, suitable for laboratory integration.
Implementation Method 1
The image sensor thus collects an image of the light intensity transmitted by the sample, also called a hologram, which is formed by interference patterns between, on the one hand, the light wave emitted by the light source and transmitted by the sample, and on the other hand, diffraction waves resulting from the diffraction by the sample of the light wave emitted by the light source.
Implementation Method 2
diffraction waves resulting from the diffraction by the sample of the light wave emitted by the light source
Data Source
Figure 1~4
Figure 5~6
Figure 7~8
AI summary
The invention relates to a device for detecting particles by means of lensless imaging, the device comprising a memory (4) arranged to receive a plurality of z-stack images obtained from a lensless image of a biological sample, a picker (6) arranged to determine, on the basis of the z-stack images, a focus image in which each pixel is associated on the one hand with a z-stack image and on the other hand with the intensity of this pixel in this z-stack image, the picker (6) being arranged to determine the z-stack image for a given pixel by calculating, for each of the z-stack images and for the given pixel, the parsimony score on the basis of the intensity of the given pixel and on the intensities of neighbouring pixels, and by selecting the z-stack image for which the parsimony score is highest, a selector (10) arranged to determine, for each pixel of the focus image, whether this pixel is a maximum in a local neighbourhood centred on this pixel in the focus image or in the z-stack image associated with this pixel in the focus image, and, if if it is, to store this pixel in a list of selected sites, and a computer (12) arranged to calculate a metric value for each pixel in the list of selected sites on the basis of the intensity of these pixels to produce an image of the metric values for distinguishing the particles associated with each pixel in the list of selected sites from one another.