Lens-Free Pathology Imaging for Wide-Field High-Resolution Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pathological section imaging methods face challenges with the contradiction between visual field and resolution, repetitive and time-consuming processes, tissue damage from staining, and the unsuitability of stimulated Raman microscopy for clinical use due to small field of view and complex systems.
Innovation Solution
A pathological section analyzer with large field of view, high throughput, and high resolution, utilizing a lens-free coaxial computing microscopic multi-height image collection system, data preprocessing, image super-resolution, and analysis circuits, including a monochromatic laser light source, CMOS image sensor, and convolutional neural networks for image analysis without staining.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If optical microscope or electronic reading is used to obtain high-resolution image, then resolution is improved, but visual field becomes smaller
Solution Approach 1:
The patent transitions from 2D optical microscopy to 3D optical coherence tomography imaging, adding the depth dimension to achieve both high resolution and large visual field simultaneously. The OCT system captures three-dimensional structural information of tissue sections without the resolution-visual field tradeoff inherent in traditional microscopy.
Solution Approach 2:
The patent replaces the mechanical optical microscope system with an optical coherence tomography system that uses low-coherence interferometry. This substitution enables simultaneous acquisition of high-resolution cross-sectional images and three-dimensional structural data with large visual field coverage.
2Reliability
If pathologist marks WSIs repeatedly for diagnosis, then diagnostic accuracy is improved, but time consumption increases and errors occur
Solution Approach 1:
The patent implements automated artificial intelligence algorithms that perform self-diagnosis on pathological images. The system automatically identifies and marks suspicious regions, reducing reliance on repeated manual marking by pathologists while maintaining or improving diagnostic accuracy and significantly reducing time consumption.
Solution Approach 2:
The patent incorporates feedback mechanisms where the automated diagnosis system continuously learns from pathologist corrections and adjustments. This feedback loop improves the reliability of automated marking over time while reducing the need for repetitive manual verification.
3Measurement precision
If staining is performed to improve observation, then image quality is improved, but tissue damage occurs and time is consumed
Solution Approach 1:
The patent replaces chemical staining methods with optical coherence tomography imaging that uses low-coherence light interference. This substitution enables high-quality imaging of unstained tissue sections, eliminating chemical tissue damage while maintaining excellent image quality through three-dimensional optical contrast.
Solution Approach 2:
The patent creates optical copies of tissue structures through OCT interferometry without requiring physical or chemical modification of the tissue. The low-coherence light generates detailed structural copies that provide excellent observation quality without the harmful effects of staining chemicals.
4Productivity
If stimulated Raman microscopic imaging is used to achieve rapid mark-free imaging, then imaging speed is improved, but field of view becomes small and system complexity increases
Solution Approach 1:
The patent replaces the complex stimulated Raman microscopy system with optical coherence tomography that uses low-coherence interferometry. This substitution achieves rapid imaging with large visual field while reducing system complexity by eliminating the need for stimulated Raman scattering components and complex spectral analysis systems.
Solution Approach 2:
The patent creates a multi-functional OCT system that can rapidly image large tissue areas without staining while providing three-dimensional structural information. The system achieves universal applicability for various tissue types without the specialized complexity of stimulated Raman microscopy.
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
Enables large-field, high-throughput imaging with reduced cost and complexity, accurate super-resolution without complex algorithms, and intelligent analysis of pathological conditions, avoiding errors from repetitive operations and subjective judgments.
Implementation Method 1
a monochromatic laser light source
Implementation Method 2
a spherical wave emitted by the monochromatic laser light source is filtered by the pinhole and then transmitted to a plane of the pathological section sample
Implementation Method 3
the surface wave and the reference wave interfere to form a hologram, which is recorded by the CMOS image sensor
Implementation Method 4
a first convolutional neural network model processes the low-resolution reconstructed image to generate a high-resolution reconstructed image
Data Source
AI summary
A large-field-of-view, high-throughput and high-resolution pathological section analyzer includes an image collector for collecting a set of computing microscopic images of a pathological section sample; a data preprocessing circuit for iteratively updating the set of computing microscopic images by a multi-height phase recovery algorithm to obtain a low-resolution reconstructed image; an image super-resolution circuit for super-resolving the low-resolution reconstructed image according to a pre-trained super-resolution model to obtain a high-resolution reconstructed image; and an image analysis circuit for automatically analyzing the high-resolution reconstructed image according to different tasks, and specifically selecting different analysis models according to the different tasks to obtain corresponding auxiliary diagnosis results. Imaging visual field of the pathological section analyzer is hundreds of times that of the traditional optical microscope, a deep learning network is adopted to analyze pathological conditions of unstained pathological sections, so that the analysis process of pathological sections is simplified.