Real-time Pathological Image Analysis Using Neural Networks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for pulmonary disease diagnosis, such as CT-guided needle biopsy, face challenges with prolonged time consumption due to the need for manual examination by a pathologist and delayed analysis results, especially in emergency situations, as they require samples to be sent to a pathology department for evaluation.

Innovation Solution

A real-time pathological microscopic image collection and analysis system that includes a microscopic image collection device, an image analysis device using a trained neural network model, and a display device, enabling real-time scanning and analysis of samples, allowing for immediate diagnosis by breaking down the sample into microscopic image blocks and analyzing each block in parallel.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a pathologist manually examines samples using traditional ROSE technology, then diagnostic accuracy is ensured, but time consumption increases significantly

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent creates a digital copy of the microscopic sample image and processes this copy through neural network algorithms, rather than requiring the original physical slide to be manually examined. This digital copying enables parallel processing and automated analysis, dramatically reducing the time from sample collection to diagnostic result while maintaining accuracy through sophisticated image recognition

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical manual examination process of pathologists with an automated optical system combined with neural network algorithms. The system uses computer vision technology to automatically detect, segment, and classify cells, substituting the mechanical action of manual slide examination with automated digital image processing that operates much faster

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If the entire sample is scanned to generate a complete large microscopic image before analysis, then comprehensive examination is achieved, but analysis time is delayed

Engineering Contradiction:
Improveexamination completenessVSAvoidanalysis delay
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides the large microscopic image into multiple smaller image blocks or regions of interest. Instead of processing the entire large image at once, the system segments it into manageable portions that can be processed in parallel by multiple computational units, significantly reducing the overall analysis time while maintaining complete examination coverage

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary scanning and identification of potential regions of interest before conducting detailed analysis. By pre-identifying areas that require closer examination and preparing the data structure in advance, the system enables faster subsequent analysis without compromising the completeness of the examination

Inventive Principle:
Principle #10Preliminary action

3Reliability

If samples are sent to the pathology department for examination, then specialized expertise is utilized, but the process prolongs diagnostic time

Engineering Contradiction:
Improveexpert evaluationVSAvoidtransport and processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system enables the microscopy platform itself to perform diagnostic analysis through integrated neural network algorithms, eliminating the need to transfer samples or images to a separate pathology department. The platform serves its own diagnostic function by automatically analyzing images and providing results, thereby eliminating transport time and inter-departmental coordination delays while maintaining reliable expert-level analysis

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3839885A1Real-time pathological microscopic image collection and analysis system, method and device and medium
Publication Date: 2021.06.23 SHANGHAI XINGMAI INFORMATION TECH CO LTD
  • EP3839885A1 patent drawingFigure 1~2
  • EP3839885A1 patent drawingFigure 3
  • EP3839885A1 patent drawingFigure 4

AI summary

A system and method capable of implementing real-time scanning and rapidly and efficiently analyzing a pathological state are provided. The system includes: a microscopic image collection device; an image analysis device, connected with the microscopic image collection device and configured to acquire at least one microscopic image block in real time, input the at least one microscopic image block to a trained neural network model for analyzing to obtain at least one microscopic image block analysis result; and a display device, connected with the image analysis device and outputting and displaying the at least one microscopic image block analysis result. The present invention also provides a method or medium corresponding to the device.