Encoded Illumination Focusing for Fast Whole Slide Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current whole slide imaging systems face challenges in achieving fast and accurate focusing due to limited depth of field and require significant time or additional hardware, hindering their clinical application.
Innovation Solution
An encoded illumination real-time focusing scanning imaging device and method utilizing an LED array, liquid lens, and convolutional neural networks to quickly calculate defocusing amounts and adjust the liquid lens for rapid focusing, combining encoded light illumination with depth learning to accelerate image acquisition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional z-stack focusing mode is used to acquire high-resolution images, then image quality is improved, but time expenditure increases significantly
Solution Approach 1:
The patent replaces the mechanical z-stack focusing method with an optical encoding system using LED arrays and convolutional neural networks. Instead of mechanically moving the stage through multiple z-positions to capture multiple images for focus determination, the system uses encoded light patterns and AI-based defocusing amount calculation to achieve rapid focusing, substituting mechanical scanning with optical-information processing
Solution Approach 2:
The patent performs preliminary encoding of illumination patterns before the actual imaging process. By pre-defining multiple LED illumination patterns that encode different defocusing amount information, the system prepares the optical information in advance, allowing the convolutional neural network to directly calculate defocusing amounts from single or few images without requiring time-consuming z-stack acquisition
2Productivity
If focusing map mode is used to reduce focusing time, then time expenditure is reduced, but additional time is required to acquire the focusing map
Solution Approach 1:
The patent enables the system to self-determine defocusing amounts using encoded illumination patterns and convolutional neural network analysis. Instead of requiring a separate focusing map acquisition process, the system uses the encoded light information from the sample itself to calculate defocusing amounts in real-time, making the focusing process self-sufficient and eliminating the need for preliminary map creation
3Measurement precision
If reflection mode with laser light detection is used to determine defocusing amount, then focusing accuracy is improved, but additional hardware equipment is required
Solution Approach 1:
The patent makes the LED array serve multiple functions: it provides both standard illumination for bright-field imaging and encoded illumination patterns for defocusing amount calculation. The same optical path and camera system are used for both imaging and focusing determination, eliminating the need for separate laser detection hardware and making the system multi-functional without additional equipment
Solution Approach 2:
The patent merges the illumination function and focusing measurement function into a single integrated system. The LED array simultaneously performs illumination and encodes defocusing information through patterned lighting, while the camera captures both imaging and focusing data through the same optical path, combining multiple functions into unified hardware
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 enables fast and accurate focusing at a low cost, significantly improving the speed of whole slide image acquisition by using encoded light illumination and a liquid lens for quick adjustment, resulting in high-resolution images.
Implementation Method 1
an LED array, an object stage, an objective lens, a liquid lens, a lens sleeve, and a camera. The LED array is located on one side of the object stage
Implementation Method 2
adjusting a current of the liquid lens at the spatial position with a predetermined step length
Data Source
AI summary
An encoded illumination real-time focusing scanning imaging device includes an LED array, an object stage, an objective lens, a liquid lens, a lens sleeve, and a camera. The object stage is used for placing a sample, the LED array is used for emitting bright field light or encoded light, and the bright field light or the encoded light respectively penetrates through the sample and then successively passes through the objective lens, the liquid lens, and the lens sleeve to reach the camera to shoot a bright field image or an encoded light illumination image by the camera. The present invention also discloses an encoded illumination real-time focusing scanning imaging method, which is performed by using the above-mentioned device. The present invention enables fast and accurate focusing at a low cost.