Medical X-Ray Laterality Detection with Automatic Image Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Incorrect laterality in medical images, particularly due to human error during portable x-ray imaging, leads to inefficiencies in manual correction, degrades diagnostic systems, and affects the performance of computer-aided diagnostics.

Innovation Solution

A neural network model is employed to automatically detect and correct the laterality of medical images, reducing human error and expediting workflow by accurately classifying and, if necessary, flipping images to ensure correct laterality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual correction of laterality is performed by technologists, then correctness of laterality information is improved, but productivity and efficiency deteriorate due to time consumption

Engineering Contradiction:
Improvecorrectness of laterality informationVSAvoidefficiency of image processing
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent replaces the manual mechanical process of technologists visually inspecting and correcting laterality with an automated computer-based system using machine learning algorithms. The system automatically analyzes image features, detects laterality errors, and corrects metadata without human intervention, thereby maintaining reliability while dramatically improving productivity.

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

Solution Approach 2:

The system enables self-service by allowing the computer-aided diagnostic system to automatically detect and correct its own laterality errors using trained machine learning models. The system processes images, identifies flipped or incorrectly oriented images, and automatically corrects the metadata, eliminating the need for external manual intervention.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If manual rotation and correction of images is performed, then accuracy of laterality metadata is improved, but loss of time increases due to technologists' involvement

Engineering Contradiction:
Improveaccuracy of laterality metadataVSAvoidtime for manual correction
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-training machine learning models on large datasets of correctly labeled medical images before deployment. During operation, the pre-trained model automatically and rapidly classifies new images for laterality correctness, eliminating the need for time-consuming manual review while maintaining high accuracy through the model's learned patterns.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If automated systems are used to detect laterality, then productivity is improved, but measurement precision may deteriorate compared to expert manual review

Engineering Contradiction:
Improvespeed of image processingVSAvoidaccuracy of laterality detection
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system implements feedback mechanisms where the machine learning model's predictions are continuously refined through training on annotated data. The system provides feedback loops during the training phase, adjusting model parameters based on prediction accuracy, and can incorporate feedback from user corrections to improve future performance, ensuring high measurement precision while maintaining automated productivity.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3872757B1Systems and methods for detecting laterality of a medical image
Publication Date: 2025.07.16 GE PRECISION HEALTHCARE LLC
  • EP3872757B1 patent drawingFigure 1A~1B
  • EP3872757B1 patent drawingFigure 1C~1D
  • EP3872757B1 patent drawingFigure 2A~2B

AI summary

An x-ray image laterality detection system (200) is provided. The x-ray image laterality detection system includes a detection computing device (202, 800). The processor (814) of the computing device is programmed to execute a neural network model for analyzing x-ray images, wherein the neural network model (204, 338, 600, 1600, 2600, 3600) is trained with training x-ray images as inputs and observed laterality classes associated with the training x-ray images as outputs. The process is also programmed to receive an unclassified x-ray image, analyze the unclassified x-ray image using the neural network model, and assign a laterality class to the unclassified x-ray image. If the assigned laterality class is not target laterality, the processor is programmed to adjust the unclassified x-ray image to derive a corrected x-ray image having the target laterality and output the corrected x-ray image. If the assigned laterality class is the target laterality, the processor is programmed to output the unclassified x-ray image.