ECG Image Augmentation Using Signal-Guided Artifact Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Building prediction models based on electrocardiogram (ECG) images is challenging due to varying image quality issues such as poor capture quality, lighting, angle, focus, and motion artifacts.

Innovation Solution

An apparatus and method for training a machine learning model that includes a processor and memory to receive signal data, generate augmented images through transformation models, and train the model using image and signal processing modules to enhance image quality for better prediction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If ECG images are captured using existing equipment and methods, then image acquisition is straightforward, but image quality varies due to lighting, angle, focus, and motion artifacts

Engineering Contradiction:

Improveimage qualityVSAvoidimage artifacts

Core Design Contradiction:

Manufacturing precisionVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary actions by capturing both the ECG image and corresponding motion data simultaneously during the imaging process. This motion data is then used to predict and correct motion artifacts in the ECG image before final processing, preventing the harmful effects rather than correcting them afterward

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Motion data serves as an intermediary element that bridges the gap between the physical motion causing artifacts and the digital image. The motion data is processed through a motion artifact prediction model to generate correction information, which is then applied to the ECG image to remove artifacts

Inventive Principle:

Principle #24Intermediary (Mediator)

2Manufacturing precision

If multiple image processing modules are used to enhance image quality, then image quality improves, but system complexity increases

Engineering Contradiction:

Improveimage qualityVSAvoidsystem complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system merges multiple processing functions into an integrated workflow: the image processing module and motion artifact prediction model work together in a coordinated manner, sharing data and processing steps to achieve comprehensive image enhancement while maintaining system coherence

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The processing system is segmented into distinct functional modules: an image processing module for general image enhancement and a motion artifact prediction model for specific artifact removal. This segmentation allows each module to specialize in specific tasks while working together as a unified system

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250342583A1Apparatus and method for training a machine learning model to augment signal data and image data

Publication Date: 2025.11.06 ANUMANA INC

AI summary

An apparatus and method for training a machine learning model to augment signal data and image data. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to receive a signal data. The memory instructs the processor to generate a digital image, wherein the digital image comprises the signal data. The memory instructs the processor to transmit the digital image to an image processing module, wherein the image processing module produces an augmented image. The memory instructs the processor to transmit the signal data to a signal processing module, wherein the signal processing module produces the augmented image. The memory instructs the processor to train a machine learning model using the augmented image.