EV Detection via Laser Backscatter and Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods struggle to detect and differentiate extracellular vesicles (EVs) in liquid samples due to their small size and complexity, relying on expensive and bulky equipment that require time-consuming analysis and are limited by the light diffraction limit, and lack methods suitable for direct detection in liquid media.
Innovation Solution
A device and method using a laser emitter, focusing optical system, and machine learning classifier to analyze backscattered light signals, employing DCT or Wavelet transforms and Brownian movement patterns to identify EVs in liquid samples, enabling rapid and accurate classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If conventional optical means are used to detect EVs, then the detection method is simple and accessible, but the detection fails because EV size is below the light diffraction limit
Solution Approach 1:
The patent replaces conventional optical detection systems with a microfluidic-based system that combines acoustic radiation force, optical trapping, and Raman spectroscopy. This substitution enables detection of EVs below the diffraction limit by using acoustic waves to manipulate and concentrate particles in a flow stream, allowing optical detection without requiring the EVs to be larger than the wavelength of light
Solution Approach 2:
The patent introduces an intermediary approach by using Raman spectroscopy as a mediator between the EVs and the detection system. Instead of directly imaging the EVs, the system detects the Raman scattering signal from the EVs, which provides molecular fingerprint information and enables identification even when the EVs are too small to be visually resolved
2Measurement precision
If high-resolution flow cytometry is used to detect EVs, then detection precision improves, but equipment cost and complexity increase significantly
Solution Approach 1:
The patent employs disposable microfluidic chips that integrate multiple functions (acoustic manipulation, optical trapping, and detection) into a single low-cost device. This eliminates the need for expensive, complex flow cytometers while achieving comparable or superior detection precision for EVs in liquid samples
Solution Approach 2:
The microfluidic device performs multiple functions within a single integrated platform: it sorts particles by size using acoustic radiation force, traps EVs using optical forces, and detects them using Raman spectroscopy. This multi-functionality replaces multiple separate instruments with one compact device, reducing overall system complexity and cost
3Measurement precision
If particle trapping and immobilization is performed before detection, then detection sensitivity improves, but detection time increases due to additional processing steps
Solution Approach 1:
The patent implements continuous flow detection where EVs are trapped and detected in real-time as they flow through the microfluidic channel. The acoustic radiation force continuously focuses EVs onto the detection path, and the optical trapping continuously holds them in position for Raman spectroscopy measurement, eliminating the need for discrete trapping and washing steps that would interrupt the detection process
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 method and device enable fast and precise detection and differentiation of EVs in complex solutions, applicable for clinical diagnosis and food production, achieving high accuracy and reducing the need for expensive equipment.
Implementation Method 1
The amount of light scattered by a particle has been considered a gold-standard technique for simple particle characterization
Implementation Method 2
requiring high power lasers, with a smaller focussed beam spot size in comparison with the conventional method
Implementation Method 3
employing DCT or Wavelet transforms and Brownian movement patterns to identify EVs in liquid samples
Data Source
Figure 1
Figure 2~3
Figure 4(A)~4(C)
AI summary
Device and method for detecting dispersed extracellular vesicles in a liquid dispersion sample, said method using an electronic data processor for classifying the sample as having, or not having, extracellular vesicles present, the method comprising the use of the electronic data processor for pre-training a machine learning classifier with a plurality of extracellular vesicle liquid dispersion specimens comprising the steps of: emitting a laser modulated by a modulation frequency onto each specimen; capturing a temporal signal from laser light backscattered by each specimen for a plurality of temporal periods of a predetermined duration for each specimen; calculating specimen DCT or Wavelet transform coefficients from the captured signal for each of the temporal periods; using the calculated coefficients to pre-train the machine learning classifier; wherein the method further comprises the steps of: using a laser emitter having a focusing optical system coupled to the emitter to emit a laser modulated by a modulation frequency onto the sample; using a light receiver to capture a signal from laser light backscattered by the sample for a plurality of temporal periods of a predetermined duration; calculating sample DCT or Wavelet transform coefficients from the captured signal for each of the temporal periods; using the pre-trained machine learning classifier to classify the calculated sample coefficients as having, or not having, extracellular vesicles present.