Surgical Instrument Detection Using Learned Classification Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing surgical instrument detection systems require special processing and optically readable symbols, increasing production costs and time for identification, making it difficult to accurately distinguish diverse surgical instruments without visual errors.

Innovation Solution

A surgical instrument detection system that uses an image input section, object extraction section, and determination section with a learned classification model to automatically identify and count surgical instruments without special processing, allowing for real-time monitoring and comparison before and after surgery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If optically readable symbols are applied to surgical instruments for identification, then identification accuracy is improved, but production cost and processing time increase

Engineering Contradiction:

Improveidentification accuracyVSAvoidproduction cost

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses image copying and processing to identify surgical instruments. Instead of applying physical symbols to instruments, the system captures images of instruments in the surgical field and uses image processing algorithms to automatically identify and count them, eliminating the need for special markings on the instruments themselves

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces manual visual inspection with automated image processing systems. Instead of relying on human nurses to visually distinguish similar instruments, the system uses cameras and computer vision algorithms to automatically detect and identify surgical instruments, reducing human error and workload

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If optically readable symbols are applied to surgical instruments for identification, then identification accuracy is improved, but time for reading symbols increases

Engineering Contradiction:

Improveidentification accuracyVSAvoidtime for reading symbols

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system creates digital copies (images) of surgical instruments in their natural state within the surgical field. These images are then processed by computer vision algorithms to automatically identify instruments, eliminating the need for manual reading of symbols and significantly reducing identification time

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system performs preliminary image capture and processing before surgical procedures begin. By capturing images of all surgical instruments and pre-processing them for identification, the system enables rapid verification during surgery without requiring time-consuming symbol reading

Inventive Principle:

Principle #10Preliminary action

3Ease of manufacture

If visual observation is used to distinguish surgical instruments, then no special processing is needed, but identification accuracy deteriorates

Engineering Contradiction:

Improveno special processingVSAvoididentification accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent replaces human visual observation with automated image processing systems. The system uses cameras to capture images of surgical instruments and employs computer vision algorithms to automatically distinguish between similar instruments, providing both high accuracy and eliminating the need for special markings on instruments

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Device complexity

If manual counting of surgical instruments is performed, then no additional equipment is needed, but reliability deteriorates

Engineering Contradiction:

Improveno additional equipmentVSAvoidcounting accuracy

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent replaces manual counting with automated image-based detection systems. The system captures images of surgical instruments and uses computer vision algorithms to automatically count and identify each instrument, providing reliable verification that prevents instruments from being left in patients during surgery

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11256963B2Surgical instrument detection system and computer program

Publication Date: 2022.02.22 EIZO CORP

AI summary

A surgical instrument detection system is provided that can determine the kinds of surgical instruments without special processing, such as application of an optically readable symbol, to the surgical instruments. A surgical instrument detection system 100 includes: an image input section 31 to input an image taken by a camera 1; an object extraction section 32 to clip an object image of a small steel article from the input image; a determination section 33 to input the object image to a learned classification model 331 and determine a kind of the small steel article based on features included in the object image; and an output image generation section 34 to generate an image representing the result of determination by the determination section and output such image to a monitor 2.