Foreign Body Detection Using Reference Image Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting retained foreign bodies (RFBs) during or after surgery are inadequate, as they often require manual counting and x-rays, which are time-consuming and prone to false negatives, especially for small objects, and existing automated technologies like ADIC do not significantly reduce the need for x-rays or address partial instrument losses.
Innovation Solution
A system and method using a data processor and reference images to compare images of a patient's internal region, employing a computer algorithm to determine the presence of retained foreign bodies, which includes preprocessing and applying transformations to improve detection accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual counting and x-ray methods are used to detect RFBs, then detection coverage is comprehensive, but detection time increases and false negatives occur especially for small objects
Solution Approach 1:
The patent replaces manual mechanical counting and interpretation with an automated computer vision system that captures images of surgical sites and uses image processing algorithms to automatically detect foreign bodies. This substitution eliminates manual labor and reduces detection time while maintaining or improving accuracy through consistent automated analysis.
Solution Approach 2:
The system creates digital image copies of the surgical site that can be analyzed without requiring physical x-rays for every case. These image copies allow for repeated analysis and can be enhanced through processing to improve detection of small objects without additional radiation exposure or time delay.
2Measurement precision
If radiologists manually determine RFBs from x-rays, then detection can be performed, but accuracy decreases for objects less than 10 mm in length
Solution Approach 1:
The patent segments the detection task into distinct processing stages: image capture, preprocessing, feature extraction, and analysis. This segmentation allows each stage to be optimized independently, with specialized algorithms for detecting small objects at different stages of the pipeline, thereby improving overall precision without requiring a single overly complex system.
Solution Approach 2:
The system performs preliminary image processing and enhancement before final analysis, preparing images in advance to highlight small objects. This preliminary action includes noise reduction, contrast enhancement, and feature detection that primes the system for more accurate identification of small foreign bodies less than 10 mm in length.
3Extent of automation
If ADIC technology is used to detect sponges, then sponge detection is automated, but x-rays are still required in 81% of cases and the process is prolonged
Solution Approach 1:
The patent creates a universal detection system that can identify multiple types of foreign bodies (sponges, instruments, needles, and their fragments) using a single image analysis platform. This multi-functional approach eliminates the need for separate ADIC systems for different object types and removes the requirement for additional x-rays in most cases, as the system can detect all object types through image analysis alone.
Data Source
AI summary
A system for detecting post-operative retained foreign bodies has a data storage unit adapted to receive and store a reference image of a surgical object, and a data processor in communication with the data storage unit. The data processor is configured to receive an image of an internal region of a patient and to receive the reference image from the data storage unit, and the data processor is configured to perform operations based on an algorithm to compare the reference image to at least a portion of the image of the internal region of the patient and determine whether a retained foreign body is present in the patient.