Pathology Image Analysis for Liquid Biopsy Patient Selection

Solution Overview

Problem

Current methods for selecting patients for liquid biopsies are time-consuming and costly, and there is no effective way to determine which patients should undergo liquid biopsy at the biopsy stage.

Innovation Solution

A method and apparatus that use a computing device to analyze pathological slide images, predict the ratio of circulating tumor DNA (ctDNA) to cell-free DNA (cfDNA), and generate guidance for follow-up examinations based on this ratio.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If liquid biopsy is performed on all patients, then detection accuracy is improved, but time and cost increase significantly

Engineering Contradiction:

Improvedetection accuracyVSAvoidtime for selecting liquid biopsy targets

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of pathology slide images to predict ctDNA/cfDNA ratios before liquid biopsy is conducted. This preliminary action identifies which patients are most likely to benefit from liquid biopsy, allowing clinicians to prioritize patients who need further genetic testing while avoiding unnecessary procedures on patients with low predicted ratios.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The AI system automatically analyzes pathology images and generates predictions about ctDNA/cfDNA ratios without requiring manual review by pathologists. This self-service capability streamlines the patient selection process, reducing the time clinicians would otherwise spend evaluating each patient's suitability for liquid biopsy.

Inventive Principle:

Principle #25Self-service

2Reliability

If liquid biopsy is performed on all patients, then detection accuracy is improved, but cost increases significantly

Engineering Contradiction:

Improvedetection accuracyVSAvoidcost of liquid biopsy

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The system performs preliminary analysis of pathology slide images to predict ctDNA/cfDNA ratios before liquid biopsy is conducted. This preliminary action identifies which patients are most likely to benefit from liquid biopsy, allowing clinicians to prioritize patients who need further genetic testing while avoiding unnecessary procedures on patients with low predicted ratios.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The AI system automatically analyzes pathology images and generates predictions about ctDNA/cfDNA ratios without requiring manual review by pathologists. This self-service capability streamlines the patient selection process, reducing the time clinicians would otherwise spend evaluating each patient's suitability for liquid biopsy.

Inventive Principle:

Principle #25Self-service

3Reliability

If comprehensive liquid biopsy screening is performed, then false negatives are reduced, but workflow complexity increases

Engineering Contradiction:

Improvenumber of false negativesVSAvoidworkflow complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary analysis of pathology slide images to predict ctDNA/cfDNA ratios before liquid biopsy is conducted. This preliminary action identifies which patients are most likely to benefit from liquid biopsy, allowing clinicians to prioritize patients who need further genetic testing while avoiding unnecessary procedures on patients with low predicted ratios.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The AI system automatically analyzes pathology images and generates predictions about ctDNA/cfDNA ratios without requiring manual review by pathologists. This self-service capability streamlines the patient selection process, reducing the time clinicians would otherwise spend evaluating each patient's suitability for liquid biopsy.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20250069691A1Method and apparatus for providing examination-related guide on basis of tumor content predicted from pathology slide images

Publication Date: 2025.02.27 LUNIT

AI summary

A computing device includes: at least one memory; and at least one processor, wherein the at least one processor is configured to obtain information related to tissues or cells represented in a pathological slide image by analyzing the pathological slide image, predict a ratio of circulating tumor deoxyribonucleic acid (DNA) to cell free DNA, based on the information, and generate guidance related to a follow-up examination, based on the ratio.