Colonoscopy Performance Evaluation via Fold-Inspection Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for evaluating colonoscopy performance, such as total withdrawal time, are inaccurate and misleading, as they do not accurately measure the quality of the examination and can lead to poor adenoma detection and removal rates (ADR and APC).

Innovation Solution

A computer-implemented method that classifies colonoscopy images into fold-inspection and non-fold-inspection groups based on criteria like clarity, haustrum, and colonic lumen presence, using the elapsed time of valid views to assess performance, allowing real-time feedback to physicians.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If total withdrawal time is used as the main reference for quality evaluation, then the evaluation process is simple, but the measurement precision is poor and does not accurately reflect adenoma detection capability

Engineering Contradiction:

Improveevaluation process complexityVSAvoidquality evaluation accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the continuous colonoscopy video into discrete image frames and further classifies them into fold-inspection and non-fold-inspection groups. This segmentation allows for precise measurement of valid inspection time versus total withdrawal time, resolving the contradiction between simple evaluation processes and accurate quality assessment by creating measurable units of inspection quality.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an image classification algorithm as an intermediary between the raw colonoscopy video and the quality evaluation metric. This intermediary automatically identifies and marks valid fold-inspection images, transforming the subjective assessment of inspection quality into an objective, measurable parameter that accurately reflects adenoma detection capability without requiring complex manual review.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If conventional time-based requirements are followed, then the examination process is standardized, but the adenoma detection rate and per capita yield are reduced due to misleading evaluation criteria

Engineering Contradiction:

Improveexamination process standardizationVSAvoidadenoma detection rate

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements a feedback mechanism where the classification algorithm provides real-time or post-examination feedback to physicians about their fold-inspection performance. This feedback loop allows physicians to adjust their inspection techniques based on objective metrics, improving adenoma detection rates while maintaining standardized evaluation criteria that genuinely reflect inspection quality rather than arbitrary time requirements.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent changes the evaluation parameter from total withdrawal time to fold-inspection time ratio and valid image count. This parameter change transforms the evaluation system from one that rewards prolonged withdrawal (which may indicate inefficiency) to one that rewards effective, quality inspection, thereby aligning evaluation metrics with actual adenoma detection performance and encouraging higher productivity.

Inventive Principle:

Principle #35Parameter changes

3Duration of action of moving object

If spiral withdrawal technique is used to fulfill time requirements, then the withdrawal time is extended, but the lesion detection accuracy is reduced compared to experienced physicians using forward-viewing methods

Engineering Contradiction:

Improvewithdrawal timeVSAvoidlesion detection accuracy

Core Design Contradiction:

Duration of action of moving objectVSReliability

Solution Approach 1:

The patent extracts the essential quality element from the colonoscopy process - the fold-inspection images - and separates them from the non-essential portions (non-fold-inspection images). By taking out only the valid inspection images for evaluation, the system eliminates the incentive to extend withdrawal time for its own sake and focuses measurement on the actual detection-relevant portions of the examination, thereby preserving lesion detection accuracy while allowing flexible withdrawal techniques.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS11684239B2Method, system and computer readable medium for evaluating colonoscopy performance

Publication Date: 2023.06.27 CHENGDU WISION MEDICAL DEVICE CO LTD

AI summary

A computer-implemented method for evaluating colonoscopy performance includes: (S1) splitting a video acquired during a colonoscopy examination into a plurality of colonoscopy images; (S2) assigning each of the colonoscopy images into a fold-inspection group or a non-fold-inspection group according to a first classification criterion and a second classification criterion, wherein the first classification criterion comprises at least one of clarity, exposure, level of tissue wrinkling, and level of occlusion in each of the colonoscopy images; and the second classification criterion comprises at least one of an amount of haustrum, an amount of colonic lumen, and a position of the colonic lumen in each of the colonoscopy images; and (S3) determining a performance rating of the colonoscopy examination according to an elapsed time of the fold-inspection group. The method classifies colonoscopy images more accurately and reliably, thereby providing an effective tool for quality assessment and guidance of colonoscopy examinations.